Computer Vision and Pattern Recognition Experts
It-Jim is a group of experts with PhD degrees in various mathematical disciplines. We conduct the high-quality research in the fields of computer vision, pattern recognition, machine learning, artificial intelligence, augmented reality, signal and image processing.
Here are the top reasons why you should consider working with us:
- Our extensive academic background and solid practical experience help us to identify a best-fit solution for your business problem. We offer our clients all kinds of computer vision engineering: from technical consulting and algorithm construction to custom computer vision software development.
- Team’s overwhelming R&D experience with 300+ scientific publications, 10+ best paper awards at international conferences and symposia.
- From mobile devices and embedded boards up to distributed systems in the cloud, our dedicated team integrates solutions into various platforms and hardware.
- Our computer vision research is based on the fusion of traditional approaches with different types of machine learning algorithms and up to state-of-the-art deep learning architectures.
- From semantic and instance segmentation, object detection and recognition, multiple object tracking, 3D vision and reconstruction to abnormality detection and biometric identification of animals – any type of your image and video analysis tasks are covered.
- With image being the most popular way of 2-dimensional data representation, it does not really matter what is the origin: optical camera, radar, IR or X-ray device. We can extract the hidden knowledge from visual data of any nature, sensors and conditions.
- We deliver computer vision development and consulting services for any type of business and a substantial majority of industries including healthcare, entertainment, automotive, sports, retail, manufacturing, real estate, security and surveillance, agriculture, gaming, building construction, or quality inspection.
headquarters
other locations
-
30 N Gould StSheridan, WY 82801United States
Recommended Providers
Focus
Portfolio
Esticom, VisionLab, Foresight automotive, Geomagical labs, Vastmindz, Oldprogrammer
Gaze Tracking
The goal of the project is to build the gaze tracking system as a part of an anti-cheating complex that should detect suspicious gaze directions when the user looks outside a monitor, for example. We consider both cases with a static head normally oriented to a screen and when user turns his head. As “suspicious gaze directions” we consider situations when user's gaze is outside a monitor.
The first solution is done in C++ in combination with Mediapipe Iris. Estimation of gaze and head pose angles is done by a MediaPipe. The rest of processing is done in C++. The second solution is based on ptgaze package for Python, which provides a set of gaze estimation deep neural networks pretrained on various datasets. The model pretrained on MPIIFaceGaze dataset was chosen as the most suitable for our task.
The model predicts gaze angles, so we’ve added our custom module for converting them to screen position based on initial calibration. We’ve also updated the GUI to have proper visualization both for calibration part and for screen point estimation after the calibration. HIGHLIGHTS: 1. Mediapipe-based solution 2. DL-based gaze estimator with custom postprocessing for a monitor geometry
Real-time Background Replacement
The goal of the project was to develop software that would replace the background behind a person on a video. Firstly, we have utilized two different concepts : silent object detection and monocular depth estimation. For the former idea we used the U2-Net model. For the latter, we applied DenseDepth model trained with the NYU dataset. U2-Net was trained on the Supervisely Person dataset and it managed to give more accurate background replacement compared to the depth estimation approach. Also, unlike depth estimation models, it correctly handled cases when a person walked away from a camera view, leaving an empty background.
To avoid frame-by-frame segmentation while keeping interframe foreground mask consistency, we have incorporated of the optical flow between adjacent frames to track movements. As a result, our solution provides accurate person segmentation in real-time. To get a binary mask, we added two options: selecting a manual threshold or applying Otsu method which does the job automatically.
Finally, some post-processing was applied to filter out the false contours from the background. An alternative solution was based on the U2-Net model that is usually used for salient object detection. HIGHLIGHTS: 1. Combination of salient object and monodepth concepts 2. Interframe optical flow tracking for segmentation mask consistency 3. Real-time person segmentation and background replacement
Fiducial Markers on RasPi
Fiducial markers are widely used in various applications like robot navigation, logistics, augmented reality. Their advantages are obvious: high contrast, simple code generation, resistance to extremal angles of view. Our specific goal was to develop an extremely effficient algorithm for usage of multiple fiducials recognition using a low-power CPU like Raspberry Pi. By using improved marker code extraction, dynamic rescaling and advanced marker tracking and motion model, we were able to achieve ultra-fast fiducial marker recognition of 60+ FPS.
HIGHLIGHTS:
1. Optimized for different image sizes
2. Advanced tracking algorithm
3. Custom motion model
4. 60+ FPS on RasPI
Space mapping with LiDAR
The goal of this project was to develop an engine for processing and interpreting the 3d-point cloud acquired by the LiDAR sensor. First, we created an iOS logger application to store depth data, camera frames, and mobile sensors recordings. Second, we developed an algorithm that returns semantic representations of the point cloud. These data were then used as input to the processing pipeline which found a semantic model of a box fitting the input point cloud.
HIGHLIGHTS:
1. iOS application for data storage
2. A custom algorithm for 3d cloud processing
Radar Target Recognition
A specific case of object recognition is an automatic target recognition (ATR) on radar images. ATR can be effectively used for border security, safety systems to identify either man-made objects (such as buildings, ground and air vehicles) or people, as well as for target surveillance. In this project, we have built two pipelines: classical and deep learning (DL) based. For the former, we have constructed several feature sets, optimized parameters of the classifier using K-fold cross-validation and conducted comparative experiments. The highest recognition accuracy of 94.1% was achieved using the fusion of vertical and horizontal image profiles along with SVM classifier. The CNN-based solution provided the state-of-the-art level of recognition accuracy of 99.5%, which is the best result in the community for the public MSTAR database. HIGHLIGHTS: 1. Custom hand-crafted features combined with an optimized SVM classifier 2. Custom end-to-end CNN architecture 3. State-of-the art recognition performance on MSTAR dataset (99.5%)
Drones vs. Birds
Computer vision and deep learning algorithms are widely used for both indoor and outdoor scenarios. In the project, we have developed a custom algorithm for automatic object localization and recognition. In order to improve the robustness and performance, we have integrated the tracker. It has covered the cases where the detector was not able to properly locate the target. The combining of signal processing knowledge, classical computer vision algorithms for tracking, and the latest advances in CNN architectures gave very good outcomes. The created solution successfully classifies drones and birds even in the case of challenging conditions like dynamic illumination, fast-moving cases and extremely small-scale appearance.
KEY POINTS:
1. Custom 2-stage classification model
2. Combining of multiple frames for recognition confidence
3. Optimized tracking algorithm for lowering of computational resources
GRrass segmentation
Automating process of mowing the lawn saves time and nerves. For the lawnmower to understand which part of the area is grassy and where it might be stuck over stones, twigs, and other unexpected things, some computer vision algorithms are required for segmentation. In this project, we trained a fully convolutional neural network to segment into three classes: grass, leaves, and everything else. The dataset has been created manually. The network was tuned to provide the minimum size and CPU requirements results and deployed on Raspberry Pi.
HIGHLIGHTS:
1. Custom FCN for grass segmentation
2. Post-processing for segmentation mask refinement
3. Deployed on Raspberry PI
Mobile Indoor SDK
Indoor positioning systems are becoming popular nowadays. Indeed, there is plenty of opportunities for real-time user navigation in GPS-denied environments. The most widespread use cases include indoor navigation in airports, hospitals, museums, shopping malls, warehouses.
We have developed the positioning algorithm based on cheap Bluetooth beacons and built-in IMU sensors on a mobile device.
BLE signal processing module is based on custom algorithms providing stable positioning results. IMU signal processing module provides robust step detection and device heading estimation on a real-time basis. Specifically developed fusion scheme provides stable and precise user positioning. Our algorithms are implemented in C++ and integrated on Android and iOS platforms.
Developed positioning engine provides 1-2m accuracy in real-time.
HIGHLIGHTS:
1. Proprietary positioning engine providing stable 1-2m precision
2. Full framework for calibration, system setup and management
3. Works in both open spaces and narrow corridors
4. Successfully installed in several locations
Multi-Player Sport Tracker
Computer vision has a broad list of interesting applications in sports. In particular, multiple player tracking, ball tracking, action recognition, automatic goal-scoring, view generation and many more.
We have built a large-scale system for real-time sports analytics. The main goal of the project was to replace the human operator and automatically find the most interesting area on the hockey/football/ basketball pitch. The region-of-interest (ROI) control algorithm required pitch mask segmentation for avoiding false detections of the player blobs, panorama stitching from multiple cameras in real time, adaptive filtering and thresholding to detect the player candidates and custom tracker for robust keeping the traces of players. A specific clustering procedure was developed in order to build a proper logic for selection and smooth control of the ROI.
The key advantage of the created tracker is extremely high performance. It works at 120 FPS and multiple system instances can be simultaneously installed in the cloud. This makes the solution quite cheap and flexible, ROI tracking and streaming of the outputs are performed for many clients all over the globe on a real-time basis.
KEY POINTS:
- Multiple objects are tracked on a real-time basis
- The tracker can combine results from multiple cameras
- The solution provides data for sport analytics
- Region of interest for live broadcasting can be extracted automatically
Voice separation
In this project, we created an audio processing system that automatically splits audio with any song into vocal and instrumental parts. Separated vocals and instruments can be then used for creating karaoke version as well as for making remixes or creating samples. By further analysis of the extracted vocal part, it is possible to determine whether the track is instrumental or vocal.
HIGHLIGHTS:
1. Decomposition into multiple tracks
2. Vocalness classification
View Generation
Image generation and view generation in particular is a very challenging task. However, in the latter case, it is slightly simplified by natural geometrical constraints that arise from the defined position of the virtual camera relative to real ones. Still, such things like illumination changes, occlusions due to a parallax bring difficulties in reconstruction.
The authors of the DeepView paper have proposed a series of novel solutions for syntectic camera view generation. One of the most important things is an iterative improvement of so-called multiplane images via learned gradient descend when the output of the model is initially predicted from reprojected images by the trained CNN and then refined is by another NN learned to do a gradient step.
There is no open implementation of the paper so we had to do everything from a scratch. We implement most parts of the proposed method except the learned gradient stuff due to limited time and GPU resources. There are two most popular datasets (Real Estate and Spaces) for that task. We implemented data loaders for both of them and trained initial minimally working models that prove a concept and validate the correctness of geometrical transformations within a model.
HIGHLIGHTS:
1. Paper implementation from a scratch
2. View generation pipeline with strict geometrical transformations and a learnable CNN part
3. Model trained on two known datasets
Floor segmentation
Image segmentation is one of the key topics in computer vision. Сorrect separation of different classes may be a challenge due to varying illumination, noise, occlusions, shades, light spots, reflections, and camera perspective changes.
In this project, we have constructed an engine for automatic room floor segmentation. We have applied both classical computer vision and deep learning techniques for this task. Firstly, we constructed a custom classical pipeline based on superpixels, region adjacency graphs, and graph hierarchical merging. Secondly, we selected two typical CNN architectures and compared their output predictions. Finally, we have built a fusion scheme that combined outputs from two branches and applied post-processing based on textural features analysis.
KEY POINTS:
1. Custom classical computer vision pipeline
2. Optimized DL architecture
3. Custom fusion procedure for segmentation improvement
WebAR application
Augmented reality is widely used in many businesses. It provides a great immersive experience. One of the hottest topics is the so-called WebAR. In this case, there is no need for the installation of any mobile apps. Everything works directly in the browser! We have successfully built such a system in both server-based mode as well as in a purely front-end regime. We have implemented, integrated, and optimized the custom planar object tracking algorithm. It works with 40+ FPS directly in the mobile browser. In addition, we have created an admin tool for easy management of AR content. Finally, we have developed a specific image marker quality evaluation engine, which helps the user to pick the best images for future AR experiences.
KEY POINTS:
1. Custom hybrid planar tracking
2. Works without internet connection in a mobile web browser
3. 100+ AR markers support
4. Admin tool for the management of AR content
DOCUMENT ANALYSIS AND RECOGNITION
Automatic document analysis is a key part of the overall document recognition process. A common scenario is when the user takes a picture by mobile phone or tablet and the goal is to automatically parse and recognize content from the captured document. Such as pictures, tables, text data, links, etc. There are several challenges in this case: geometric distortions of the paper, varying illumination, occlusions.
Nevertheless, we have built the page unwrapping engine, which successfully handles the above problems. The developed algorithm contains several key components: Preprocessor, Feature Extractor, Geometric Model Estimator and Refiner. The preprocessor performs image filtering, roughly locates the document boundaries and extracts vertical and horizontal spans (lines and text regions). Feature Extractor module performs parsing of document content. For robustness, we have fused several types of features including corners and edges from images preprocessing in different ways. The output nonlinear grid of points is used as an input for the next system component: Geometric Model Estimator. In order to properly account for the nonlinear geometric distortions of the document, we have constructed a specific 2D-3D model, where page shape is reconstructed as a 3D surface together with the 6 DoF camera position in 3D space.Finally, after the estimation of model parameters, the document is dewarped and most of the existing distortions are corrected. Developed dewarping engine works very accurately and performs distortion correction within a reasonable time frame.
KEY POINTS:
- Handling illumination changes
- Correction of nonlinear geometric distortions
- Automatic page border detection
- 2-step procedure returns well-refined document layout
SYMBOL RECOGNITION
Pattern recognition is an extensive field of research since there are a number of things to detect and recognize from the real world.
In this project, our goal was to develop an engine for automatic counting of the various symbols on scanned building plans. Our custom algorithm was able to handle hundreds of different symbols, including complex ones consisting of multiple small sub-patterns and text. It is robust to rotation, scaling and partial symbol occlusions. Develop engine is based on a purely classic computer vision algorithm, works very fast and does not require GPU, which makes it very cheap to use in the cloud. In addition, a comparative test with market competitors indicates an advantage from both accuracy and performance points of view.
KEY POINTS:
- Automatic recognition of symbols with different complexity
- Optimized search using multi-threading
- Custom decomposition algorithm
- Rotation and scale-invariant recognition engine
- Successfully integrated into an engineering platform
PLANAR TRACKER FOR MOBILE AR
Marker-based augmented reality (AR) is extremely popular nowadays. However, full user immersion is possible only in the case of robust real-time computer vision solutions working on the mobile device. We have developed a custom hybrid tracking system based on local feature tracking and template-based matching. The tracking engine tracks the homography changes using an optical flow algorithm and then refines the residual warp using the optimized template matcher. Developed tracker is robust to extremal angles, drift-free and very accurate. Algorithms work at 60 FPS on Android and iOS.
KEY POINTS:
- Custom tracker is resistant to extremal angles and drift
- 60 FPS on mobile device (iOS+Android)
- Fusion of feature-based and template-based trackers provides high robustness
- Successfully used in custom mobile AR SDK
3D-INSPECTION BY DRONES
Drones are widely used for various tasks including visual inspection, facades and buildings reconstruction, surveillance and tracking, object detection and recognition, etc.
In this project, we have built a web-tool for visual inspection of buildings. The core technology was a customized 3D reconstruction pipeline working with both image sequences or videos from the drone camera. We have implemented structure-from-motion (SfM), point cloud densification, meshing and texturing modules. The resulting pipeline was integrated into the web-service, where the user was able to load the data for reconstruction, analyze the resulting 3d model, view the fine details and save the results for further steps.
KEY POINTS:
- 3D point cloud reconstruction engine is implemented
- Successfully integrated into web-service
- Full pipeline including SfM, meshing and texturing is created
MOBILE IMAGE RETRIEVAL
Visual image search and content-based image retrieval (CBIR) is a very hot topic in computer vision and machine learning communities. It is a core of many systems in retail, entertainment, biometrics, robotics, and other domains. The main technical challenge is to be able to create a reliable solution capable to retrieve correct results from millions of images. Moreover, such a system should work in real-time and, ideally, without internet connection on mobile devices or tablets. In our project, we have successfully developed a mobile image retrieval system for augmented reality applications. For this purpose, we have optimized and customized the bag-of-words (BoW) algorithm using a properly constructed hierarchical tree for the features vocabulary. As a result, local features from the test images were matched extremely fast. Our CBIR system worked on a mobile device without an internet connection and returned the visual search results within only 2 milliseconds.
KEY POINTS:
- Instant retrieval offline on a mobile device
- 2 ms time for 1000 images database
- Works on iOS and Android
- Integrated into custom mobile AR SDK
Reviews
the project
Proof of Concept Development for IT Software Company
"Overall, we were satisfied."
the reviewer
the review
A Clutch analyst personally interviewed this client over the phone. Below is an edited transcript.
Introduce your business and what you do there.
I'm the chief software architect at Teamwork Commerce, an IT software company that produces retail management systems.
What challenge were you trying to address with It-Jim?
We have a lot of existing customers and demand for our services. At the same time, we're constantly looking for other investment opportunities, especially in the AI space. From time to time, we ran projects to see if any of our ideas were technically possible and the cost. We ran one of these projects with It-Jim in the visual AI space. We wanted to create a proof of concept to determine what was technically possible in that field.
What was the scope of their involvement?
At the beginning of the project, we had a call with It-Jim to outline the project. We had the project outlined for 5–6 iterations; their team used a generative adversarial network (GAN) model for the project.
What is the team composition?
I worked with two teammates from It-Jim: the CEO and the AI specialist.
How much have you invested with them?
We invested $10,000 with It-Jim.
What is the status of this engagement?
Our engagement was from April–June 2022. However, we may work with them in the future.
What evidence can you share that demonstrates the impact of the engagement?
We completed one iteration of the project with It-Jim. During that iteration, coupled with information from market research, we realized there was no need to continue the project because we had enough information. Overall, we were satisfied — we had a good grasp of the project's viability and areas for further research. Since there were no deliverables outside of the small proof of concept prototype, there were no specific KPIs.
How did It-Jim perform from a project management standpoint?
The AI specialist delivered biweekly reports highlighting the project's next steps, and the CEO was usually present during meetings. Typically, we communicated through emails and Zoom meetings. Since the project was smaller, we didn't have to worry about needing a project manager.
What did you find most impressive about them?
This was a good partnership for us.
Are there any areas they could improve?
At some points, we felt as if It-Jim was busy with other projects and couldn't focus on us. It would be great if they could provide more resources; it was hard to schedule calls with them.
Do you have any advice for potential customers?
You should go ahead and give It-Jim a try.
the project
Videography Tracking System Dev for Sports Tracking Company
"They deliver everything on time and the results we get are great."
the reviewer
the review
A Clutch analyst personally interviewed this client over the phone. Below is an edited transcript.
Introduce your business and what you do there.
I’m the CEO and founder of a sports tracking company.
What challenge were you trying to address with It-Jim?
We needed help with the development of a videography system.
What was the scope of their involvement?
They developed a videography system that features two images resulting in a panoramic view. We have two cameras recording a sports field where one is looking at one side, and the other looking at another side. The system will then combine those images together to track the ball and movement digitally.
Users will then receive a video that looks like it’s recorded from the TV going left to right. The team used C++ for the backend development, and provided us with research and discovery — they also did the documentation of the system.
What is the team composition?
We work with the team lead who handles the communication between us and them. There’s a developer and two other people involved in the project.
How did you come to work with It-Jim?
I found them on Upwork. They had really good projects that were very similar to what we were looking for, so I tried them. We like that they have good communication, They deliver on time, and they’re experts at what they do.
How much have you invested with them?
We’ve invested about $15,000.
What is the status of this engagement?
We started working together in January 2020 and our partnership is still ongoing.
What evidence can you share that demonstrates the impact of the engagement?
They deliver everything on time and the results we get are great.
How did It-Jim perform from a project management standpoint?
Project management is a simple structure. They work really well and if we need some more details on the project, our point of contact arranges a meeting with them. We communicate via Upwork, WhatsApp, and Google Meet and they’re very communicative.
What did you find most impressive about them?
They’re really good at what they do.
Are there any areas they could improve?
No, everything was great.
Do you have any advice for potential customers?
I would suggest not to try to do anything cheap when trying to have a product developed. Before working with them, I tried to do it with some other people in a cheaper way, but I ended up having to develop the project with them. I paid more for It-Jim, but they were great. I would also recommend consulting with them before fully committing.
This review was published on June 26 2020
Founder, Sports Tracking Company
Consumer Products
1–10 Employees
Miami, Florida
Less than $10,000
June 2020 – Ongoing
Project summary
It-Jim was brought on to provide consulting services to a sports app startup. The mobile app allows athletes to record their games.
Feedback summary
It-Jim’s advice helped increase video processing speed from 15 frames per second to 120, a monumental improvement that surpassed expectations. The team is highly skilled and demonstrated excellent communication skills.
BACKGROUND
Introduce your business and what you do there.
I’m the founder of a small startup made up of myself and two developers. We provide video services for sports facilities. We give athletes the option to record their games through a mobile app.
OPPORTUNITY / CHALLENGE
What challenge were you trying to address with It-Jim?
We needed some consulting support regarding our development efforts.
SOLUTION
What was the scope of their involvement?
We’d had a lot of challenges throughout the project, including video stitching, camera calibration, color correction, and the tracking of the players. We record games in 180 degrees, and we use computer vision to follow the action.
This is what we needed to develop, and I had a discussion with It-Jim and found that they’d already done what we were looking to do, from stitching and calibration to the tracking of the players. They gave us insights into the whole pipeline.
What is the team composition?
I worked with Ievgen (CEO) and Vitalii (Head of R&D).
How did you come to work with It-Jim?
I posted the project on Upwork, and we received five proposals. We narrowed it down to three, and the best one came from It-Jim.
How much have you invested with them?
We’ve only received an hour of consultancy from them, at the cost of $100.
What is the status of this engagement?
We started working with It-Jim in June 2020. We have an ongoing collaboration for consulting and support, and we go to them only when we need assistance.
RESULTS & FEEDBACK
What evidence can you share that demonstrates the impact of the engagement?
Before we met with It-Jim, we had a processing speed of 15 frames per second. They helped us reach 120. That surpassed all our expectations.
How did It-Jim perform from a project management standpoint?
The overall communication was perfect. We used Skype and Upwork to communicate, and we also had a meeting through Zoom.
What did you find most impressive about them?
We’re most impressed by their level of experience. They have a very talented team of developers.
Are there any areas they could improve?
The pricing could be better.
Do you have any advice for future clients of theirs?
If the client has the money, they should go ahead with It-Jim and not spend it with another company.
Star Ratings
Overall rating: 5
Quality: 5
Schedule: 5
Cost: 5
Willing to refer: 5
the project
Custom Software Dev for Startup Company
"They delivered a good code and were ready to help in case of any problems."
the reviewer
the review
The client submitted this review online.
Please describe your company and your position there.
I am part of a research team in a Startup Company
For what projects/services did your company hire It-Jim, and what were your goals?
We are doing research on channel Estimation technics using Machine Learning. The project was to estimate the channel using Generative Adversarial Networks on different modulation schemes such as BPSK and QPSK
How did you select this vendor and what were the deciding factors?
We searched for programmers on Upwork who had worked on similar projects. Then we went through the applicants and based on It-Jim profile, we felt that they could do the job. So, we had few calls to talk more about the project, and exchange ideas on how to implement this technic.
Describe the scope of work in detail, including the project steps, key deliverables, and technologies used.
It-Jim built a channel estimation model using Generative Adversarial Networks for 2 different modulation schemes on AWGN and Rayleigh fading channel.
How many people from the vendor's team worked with you, and what were their positions?
There were 2, The CEO and the Engineer
Can you share any measurable outcomes of the project or general feedback about the deliverables?
They delivered a good code and were ready to help in case of any problems.
Describe their project management style, including communication tools and timeliness.
The project management was great. We received regular updates on the progress of the project.
What did you find most impressive or unique about this company?
It-Jim cares for their client. They make sure to give regular updates on how the project is going. Also, proposing other ways to improve the project.
Are there any areas for improvement or something they could have done differently?
No, not that I can think of. We are planning to work with It-Jim on other similar projects.
the project
Custom Software Dev for Consulting Company
"We were impressed by their availability and the way they conducted themselves throughout the project process."
the reviewer
the review
The client submitted this review online.
Please describe your company and your position there.
I am the Chief Technologist at OldProgrammer.io, LLC where we offer software consulting services. Our staff consists of highly skilled Engineers with a range of skills that vary from software to hardware. We provide different services from web-based to desktop to machine control software.
For what projects/services did your company hire It-Jim, and what were your goals?
We were looking for a company which had experience with Lidar point cloud analysis, particularly in 3-D space. Our goal was to look into research and development of a custom software which would analyze Lidar point cloud and see if it could be used as a solution to our project.
How did you select this vendor and what were the deciding factors?
Having worked with previous vendors in point cloud analysis we came across this vendor online and were impressed by the work that they performed in the area of point cloud analysis as well as augmented reality.
Describe the scope of work in detail, including the project steps, key deliverables, and technologies used.
They provided our firm with complete scripts which would analyze Lidar point cloud data as we requested. The project was divided into four week sprints in which we had weekly call meetings to monitor project progress as well as communicate any and all requirements.
How many people from the vendor's team worked with you, and what were their positions?
There were two primary people that we worked with, one of which was the CEO and the other was the Engineer responsible for developing the scripts.
Can you share any measurable outcomes of the project or general feedback about the deliverables?
We were able to test and verify Lidar technology in relation to our project and whether it would be a technology which would provide a solution to our project. The deliverables and outcome of this project provided us with enough information on the technology to be able to consider it for our project as a viable solution.
Describe their project management style, including communication tools and timeliness.
The project management was conducted in a timely manner with the vendor being always available for communication. The primary communication tool used was Slack.
What did you find most impressive or unique about this company?
We were impressed by their availability and the way they conducted themselves throughout the project process. They were open to discussions as well as providing us what we asked of them. Very professional and easy to communicate with.
Are there any areas for improvement or something they could have done differently?
Overall we were satisfied with their services.
the project
Computer Vision Dev Support, IT Service Company
"Thanks to IT-Jim, we managed to build a POC model."
the reviewer
the review
The client submitted this review online.
Please describe your company and your position there.
I am the owner of an IT service company
For what projects/services did your company hire It-Jim, and what were your goals?
We hired IT-Jim to support development of a Computer vision model, to detect and track a fast-moving object and related events, via an RGB camera.
How did you select It-Jim and what were the deciding factors?
We shortlisted 3 companies via LinkedIn, and selected IT-Jim, because they made the relevant efforts to suit our requirements.
Describe the scope of work in detail, including the project steps, key deliverables, and technologies used.
Thanks to IT-Jim, we managed to build a POC model, then a smart pre-production CV model. We later adapted this model to embedded constraints.
How many people from the vendor's team worked with you, and what were their positions?
We worked with 3 people from IT-Jim: - CEO - CTO - Developper
Can you share any measurable outcomes of the project or general feedback about the deliverables?
We managed to develop, in time, a CV model with the required standards (recall, precision).
Describe their project management style, including communication tools and timelines.
For our project IT-Jim used a Scrum methodology with 2-week sprints.
What did you find most impressive or unique about this company?
We found it reassuring to work with experts who, on a very specific project, gave us a correct view of the state-of-the-art in CV, what was feasible or not within our given constraints.
Are there any areas for improvement or something they could have done differently?
During the project course we improved communication and objective alignment, by joint efforts.
the project
Development for Cloud-Based AR Solution
"They’re experts in their field."
the reviewer
the review
A Clutch analyst personally interviewed this client over the phone. Below is an edited transcript.
Introduce your business and what you do there.
I’m the CEO of a boutique agency. We recently moved to expand our augmented reality services by creating proprietary software.
What challenge were you trying to address with IT-Jim?
We had architected a solution that was rooted in web-based augmented reality and we needed a development team to build it out and advise us on the project.
What was the scope of their involvement?
There was a heavy research phase. There were several ideas we wanted to try and they helped us determine which areas of our solution would be worth pursuing. They used a mix of coding languages including C++ and JavaScript to build us a cloud-based solution.
We provided 3D models and some assets to demonstrate the computer vision algorithm since they were building a utility solution.
What is the team composition?
My main point of contact was Ievgen (CEO & Founder). There were also several developers that I worked with.
How did you come to work with IT-Jim?
I found them online. I chose them because of their prior experience in computer vision.
How much have you invested with them?
We’ve invested around $30,000.
What is the status of this engagement?
We began working with them in November 2019, and the engagement is ongoing.
What evidence can you share that demonstrates the impact of the engagement?
We measured the success of the engagement by looking at the quality of the demo. We’re seeing success in terms of being able to make continuous improvements with each version we develop.
How did IT-Jim perform from a project management standpoint?
Communication was fluid. We used Slack, email, and Zoom to communicate. We also worked in a cloud-based environment where we hosted our work so it was easy to share files.
What did you find most impressive about them?
They’re experts in their field. We were able to take their advice and make gains based on that. They were also skilled in planning a research phase.
Are there any areas they could improve?
I don’t think there’s anything they could’ve done differently. I’m happy with what they delivered within our deadlines.
the project
Custom Software Dev for SaaS Construction Platform
"Nothing we tried before came close to the quality and accuracy we’ve achieved with It-Jim."
the reviewer
the review
A Clutch analyst personally interviewed this client over the phone. Below is an edited transcript.
Introduce your business and what you do there.
I’m the founder of a construction estimation SaaS platform.
What challenge were you trying to address with It-Jim?
We deal with a lot of blueprints that involve symbols and numbers, and we wanted to find a way to automatically count those symbols from the PDF image files. We tried to find a solution in-house and try some image recognition platforms, but we weren’t able to get the accuracy and results we needed.
What was the scope of their involvement?
It-Jim worked on the symbol recognition engine that underlies our products. They’re highly structured to work with. They gathered requirements and defined them. They delivered the desired output from a typical engineering sprint with great communication throughout. I think the team is primarily made of academics based on their work output and detailed artifacts. We appreciate that; it allows us to assess where we are in terms of future delivery.
What is the team composition?
Ievgen (CEO) is our main point of contact. He handled the scoping exercise and now interfaces with me and my engineering team.
How did you come to work with It-Jim?
I found them by googling around for agencies that specialized in image recognition software. Our engineering team is in the Czech Republic, so I was looking for folks in Central and Eastern Europe to align with their time zones. It-Jim had a good portfolio, and Ievgen has a very academic background — he’s a member of the faculty at the University of Kharkiv, I believe — as well as business acumen.
How much have you invested with them?
We’ve spent about $75,000.
What is the status of this engagement?
We started working together at the beginning of 2018. It took six months for the initial delivery of the engine. We’ve subsequently done smaller projects with It-Jim on a one-off basis.
What evidence can you share that demonstrates the impact of the engagement?
One of the key goals we wanted to achieve was the engine’s accuracy: we wanted our customers to have confidence in the results we’re delivering. After a whole host of tests and tuning, we got to a very, very accurate engine.
Working with It-Jim is very easy. There have been times where we pull in new deadlines or change the scope for certain reasons, and they are very accommodating. They make sure we achieve the right business outcomes without penalizing us financially.
How did It-Jim perform from a project management standpoint?
We use Slack and Skype to communicate, and we’ve given them access to our Jira. However, they do a self-managing on their side. Our communication was clear; we always understood when we were going to get something, and we got a heads up a few days in advance before something arrives. They've never missed a deadline.
What did you find most impressive about them?
I’ve worked with similar contractors and am used to them having a defined structure and attention of detail. But It-Jim takes that to the next level. Their technical ability defines them when it comes to symbol recognition and image manipulation. We tried other companies and industry SaaS platform, and nothing we tried before came close to the quality and accuracy we’ve achieved with It-Jim.
Are there any areas they could improve?
I don’t think so. Our original engagement was flawless, and so were our follow-up projects.
Any advice for potential customers?
It-Jim is a detail-oriented group. Be very clear in your upfront requirements to accelerate delivery.
the project
AI & Computer Vision Dev for Automotive Software Company
"I’ve stayed with them for one and a half years because of the success of the work."
the reviewer
the review
A Clutch analyst personally interviewed this client over the phone. Below is an edited transcript.
Introduce your business and what you do there.
We work with OEMs and Tier-1 manufacturers from Israel, Europe, and the rest of the world. We develop algorithms, software, and hardware, including machine vision systems. I’m the R&D manager of the company.
What challenge were you trying to address with It-Jim?
We’ve worked with them on the algorithms and software side of our business.
What was the scope of their involvement?
I have 6–7 algorithm developers on my team, and I go to It-Jim when I need extra resources. They work on new algorithms and improve or optimize the ones made by our internal team.
My company is divided into two parts: AI and deep learning, and classical computer vision. I’ve also worked with It-Jim on both of these topics. They’re experts in AI and deep learning. They know the field well and have a lot of knowledge in it.
Thirdly, I go to them when we need a new idea or way of thinking about something. After each project, they send us full documentation of what they did, what they could improve and the timelines for those, and how we can go forward.
What is the team composition?
We work with their project manager, their CTO, and their algorithm team. I don’t know whether the algorithm people are also the software people or whether they have separate roles. They have C++, Python, and MATLAB developers.
How did you come to work with It-Jim?
It was either through Upwork or through the recommendation from one of my friends in Israel.
What is the status of this engagement?
We started working with It-Jim around December 2018, and it’s ongoing.
What evidence can you share that demonstrates the impact of the engagement?
We make statements of work for all the projects we start, stating with our success criteria for them. It-Jim has always met the success criteria we wrote for them.
I’m managing seven teams, so I’m not always aware of the details. Every three months, I ask the people working with It-Jim how things are going, and they always tell me that everything is good. I don’t have a bad comment to give.
How did It-Jim perform from a project management standpoint?
They’ve visited us in Israel, and we have a very good vibe. They’re very good guys. We have good communication with the team members, as well as the CTO and the project manager.
They really stand by the timelines they give us, and they make the algorithm optimizations they promise. We use email, WhatsApp, Jira, Teams, Microsoft Project, and phone calls to communicate. Ievgen (CEO, It-Jim) is available 24/7 on WhatsApp or over the phone.
What did you find most impressive about them?
They communicate clearly and they respect deadlines. I’d worked with a few companies in Ukraine, Bulgaria, and Belgium before starting with It-Jim, and I’ve stayed with them for one and a half years because of the success of the work. I normally don’t take the time to give referrals when asked for them, but I’ve done it for It-Jim.
Are there any areas they could improve?
I don’t have something for them to improve. I want to believe that our companies will grow together. Israeli companies use software houses in Ukraine and Belgium, and my dream is that we’ll grow together with It-Jim and turn into a big company.
Do you have any advice for future clients of theirs?
With any provider, everything that needs to be done should be written down, in terms of success criteria, timeline, and price. That way, everyone on both sides will understand what needs to be done.
the project
Development Services for IT Company
"We improved communication and objective alignement during the project life."
the reviewer
the review
The client submitted this review online.
Please describe your company and your position there.
I am the owner of an IT service company.
For what projects/services did your company hire It-Jim, and what were your goals?
We hired IT-Jim because we needed a particular expertise in the field of Computer Vision, for an on-going project.
How did you select It-Jim and what were the deciding factors?
We shortlisted 3 companies via LinkedIn, and finally chose IT-Jim.
Describe the scope of work in detail, including the project steps, key deliverables, and technologies used.
The project required developping and finetuning a computer vision model, able to detect and track a fast-moving object via RGB camera, as well as related events.
How many people from the vendor's team worked with you, and what were their positions?
3 people from IT-Jim took part in the project:
- CEO
- CTO
- CV expert
Can you share any measurable outcomes of the project or general feedback about the deliverables?
We sucessfully managed, via efficient common work, to build and train the CV model that met the industrial standards (precision, recall) we were looking for.
Describe their project management style, including communication tools and timelines.
On our project IT-Jim worked with Scrum methodology, with 2-week sprints.
What did you find most impressive or unique about this company?
We found it reinsuring to work with a team of experts, who know the state-of-the-art for a specific project and can correctly assess what we can do or not in a reasonable time.
Are there any areas for improvement or something they could have done differently?
We improved communication and objective alignement during the project life.
the project
Computer Vision Dev for Digital Healthcare Startup
“The team has exceptional capabilities in scientific research, and we’ve learned from them.”
the reviewer
the review
A Clutch analyst personally interviewed this client over the phone. Below is an edited transcript.
Introduce your business and what you do there.
I’m the CEO and founder of a digital healthcare startup. We specialize in developing innovative and groundbreaking solutions for the healthcare industry.
What challenge were you trying to address with It-Jim?
We’re working with them on several projects to decrease the cost of healthcare around the world while increasing accessibility to world-class diagnostics.
What was the scope of their involvement?
They’ve served as an extension of our business team. Their team had the right talent to excel in our research. Our goal was to be able to diagnose health conditions in patients noninvasively. They’ve aided us in accelerating the research process by looking into new ways of diagnosing COVID-19 in ways that can be accessible to everyone with a consumer technology device, such as a smartphone.
They were researching computer vision and software development work. Together, we’ve come up with proprietary techniques that work well for our project. We’ve been focused most closely on face tracking, motion tracking, signal processing, signal cleaning, and examining the relation of biomedical signals and specific health conditions.
What is the team composition?
We work directly with their CEO.
How did you come to work with It-Jim?
I initially found them on LinkedIn and began following their page. Soon after, I began engaging in conversation with their CEO. They proved themselves to be a good fit to collaborate with our research team pretty quickly.
How much have you invested with them?
We’ve spent about $100,000 at this point.
What is the status of this engagement?
We’ve been working together since February 2020. We’re anticipating the relationship to continue for a minimum of two years at this point.
What evidence can you share that demonstrates the impact of the engagement?
They’ve given us the opportunity to accelerate and scale. We can now handle millions of users. One of our main ways of tracking our success is through accuracy metrics. We’ve been consistently getting accuracy rates of 98% or above. We’re beating out competitors in the industry.
How did It-Jim perform from a project management standpoint?
They’ve been strong project managers in all areas. We communicate regularly on Slack and through calls.
What did you find most impressive about them?
Their expertise and specialization within the computer vision field are fantastic. The team has exceptional capabilities in scientific research, and we’ve learned from them.
Are there any areas they could improve?
I have no complaints. I wish I could hire more people like them.
Do you have any advice for potential customers?
Clearly define your success metrics to ensure that everyone is working toward the same goals.
The client received all the information they needed about the project's viability and areas for further research after the first iteration, so they ended the partnership. It-Jim delivered biweekly reports highlighting the project's progress and next steps; communication was through email and Zoom.