Deep Learning in Computer Vision, Machine Learning
Digica is an independent Data Science and Artificial Intelligence company. We help our clients by applying the latest Data Science and AI tools and techniques to their systems and products. This leads to highly customized solutions for our customers. Based on our own extensive research program our experienced team makes sure that the best available approach is applied in any situation. We have deep expertise in the field of image processing including Deep Learning for Computer Vision and leading-edge commercial implementation of Synthetic Imaging. Our work also covers the fields of Financial Trading, Audio Analysis, and Predictive Maintenance.
As a group of engineers and engineering managers, we are experts in the practical application of Artificial Intelligence and Machine Learning. We help to innovate by applying Machine and Deep Learning techniques. If you believe your product or solution can be improved by AI, but to do so seems to be too complex or risky, our well-experienced team will help you to overcome challenges and will guide you into the World of “new electricity”.
headquarters
-
Atlantic Business Center, Atlantic St.Broadheath, Altrincham, WA14 5FAUnited Kingdom
other locations
-
-
1201 3rd Ave. Ste. 3400Seattle, WA 98101United States
Focus
Portfolio
LEGO, T-Mobile US, Teledyne, NHS, Meta, Ayla
DL in detection of microscopic tissue features
Digica was tasked with detecting features
in microscopic tissue images - digitized slides observed through a microscope. The slides were stained with H&E method. The project was unorthodox due to the scarcity of labeled examples and the target images having a resolution in the order of thousands of megapixels.
The project demanded segmentation or detection
of features such as:
-
cell nuclei (figure on the right)
-
artifacts
-
microvessels
Technologies: PyTorch, TensorFlow, state of the art CNN architectures.
Detecting people in masks on thermal images
Facial recognition technology has come a long way, but during the COVID-19 crisis systems with infrared cameras were failing to detect many people due to them wearing facemasks.
How we helped:
We used RGB pictures of people in masks and thermal images that we created in-house using an adaptation technique. Once the detector had been trained using these image sets it was able to identify people wearing masks and send their location to the temperature measuring algorithm. We could describe the result as an ‘automated remote thermometer’ and it helped scanning stations to prevent the spread of COVID-19.
Results:
Recall increased from 90% to over 99%.
Technologies:
TensorFlow, MobileNet, SSD
Deep learning in CV in optimizing surgical process
Digica created an application that allows medical personnel to automatically identify medical trays and their contents to be used in surgery. The application was based on Deep learning in computer vision algorithms with an in-house Enigma AI tool suite dedicated to working with synthetic data.
Before surgery, staff take a picture of a surgical tool tray using their mobile phone and are notified if instruments and implants are missing from trays.
After surgery staff will be able to determine which instruments and implants have been used during surgery by identifying what has been removed from trays.
Images of objects need to be presented at different angles, under differing lighting conditions, and also occluded by other objects to reflect how objects might be seen in the real-world.
Target classification with FMCW radar signal
Digica developed a method for training CNN models to classify objects in FMCW radar data. The team developed a unique way of processing domain-specific signals. The model manages to self classify versatile objects.
TECHNOLOGIES
Convolution Neural Networks, TensorFlow, scikit-learn, scikit-image
RESULTS
Scalar data (azimuth, distance, speed, etc.), 1s observation:
gain in Recall: 5%-10%
Scalar data + microDoppler spectra, 1s observation:
gain in Recall: 20%-25%
Scalar data + microDoppler spectra, 5s observation:
gain in Recall: 30%
Preventive maintenance – No Trouble Found modeling
Using a continuous stream of information, individual to every mobile device, consisting of:
- internal state (OS, make, model, set of installed applications)
- user's behavior (number and time of phone calls, number and time of SMSs, WiFi on / off, etc.)
Digica trained a model that predicts if a specific mobile device will crash in the near future.
Additionally, the model was able to advise customer service on preventative maintenance actions such as upgrade/downgrade of OS, removal of applications etc.
Results:
Model predicting failure of a mobile device with 91% accuracy.
Technologies: SHAP, decision trees (XGBoost)
DL in classification of any LEGO elements
Project description:
Digica has created a new type of Deep Neural Network that allows real-time detection and classification of LEGO items out of 400.000 different LEGO elements. For training, it requires only synthetic images.
Challenges:
-
Lack of real pictures of LEGO elements taken in different lighting conditions reflecting possible scenarios of children’s play.
-
Speed and accuracy of the selected method on mobile devices.
Technologies and methods used:
TensorFlow, TensorFlow Lite, CoreML, Unity 3D, our proprietary “Synthesis” method
Results: mAP 89%, real time detection and classification experience
Deep Learning in classification of electronics
Project description:
One of the biggest distributors of Electronics in the World has employed Digica to create a solution that will allow the detection and classification of all 300,000 products using deep neural networks.
Challenges:
The main challenge was the number of pictures available - 15 per SKU, the secondary challenge was related to the very high quality of those pictures as they were taken in a professional environment in perfect lighting conditions.
Technologies and methods used:
Neural Networks, Keras, TensorFlow, Triplet Loss, VGG16, Computer Vision techniques
Results:
Classification of main categories: 97%
Classification of subcategories: 92%
Classification of a SKU: 87%
ML in detecting chemical compounds in measurements
Overview: Digica developed CNN models capable of detecting a predetermined set of chemical compounds in IMS spectra of gaseous samples. The method is resilient to noise and changes in measurements originating from different ambient conditions.
The secondary goal was to determine which parts of the measured spectrum are the most important to the classification process. EP’s approach to dataset augmentation allowed for
efficient learning on a limited training dataset, whose collection and labeling is especially expensive,
compared to other domains.
Results: Enigma Pattern has identified a subset of features comprising 25% of the original information. The model trained on such data retained over 96% of the full model’s detection performance.
Technologies: Tensorflow, Keras
Deep Learning in Road Signs Classification
Road Signs Detection - Mapping systems for autonomous vehicles:
Road mapping cars receive a vast quantity of visual data per second. It is crucial to analyze such data efficiently and to process it quickly.
The model enabled immediate visual recognition and segmentation of road-related signs and markings through neural network systems. Such processes proved to be essential e.g. for autonomous cars’ driving systems, as they required precise road markings for correct mode of operation.
Results:
The system achieved 90% accuracy in visual signs’ recognition with set Jaccard Index parameters preserved.
Technologies:
Python, Keras, TensofFlow on GPU.
SSD Algorithms: Single Shot MultiBox Detector
Deep Learning in Image Reconstruction
Fixed Pattern Noise Removal from Thermal Images:
The objective of the project was to remove the fixed pattern noise on thermal cameras which are susceptible to both external (environmental) and internal (built-in) conditions.
Challenges:
The primary concern was to remove the noise from the screen while preserving the actual image, this means that no additional data (hallucinations) should appear after noise removal. Additionally, since there are three different types of noises affecting thermal images, each of the noises had to be removed separately.
Results:
The low-frequency noise was decreased by 80%.
The number of artifacts was decreased by 30%.
The high-frequency noise was reduced by 20%.
Target of achieving threshold of 25 dB achieved, where
30 dB is believed as fully denoised picture.
Technologies:
Keras, TensorFlow
R&D of usage of synthetic data pipeline for DL
Development of a process to train CNN with synthetic images
Digica was contracted to develop a unique method to generate and train convolutional neural network models basing on synthetic images. The entire process comprised:
- development and preparation of the environment basing on Caffe
- development of steering scripts for simulation of a natural environment using Unity 3D
- development of variants of the image object classifiers
- modification of hyperparameters of the network in order to improve detection precision
- improvement of results by the transformation of synthetic images
Results:
Repeatable process of building neural networks
based on synthetic images
See a separate presentation about the results of this project.
Technologies:
Caffe, Unity3D
Object detection inspection payload with robots
Overview:
Anybotics Robots provide factory plant operators the information to maximize equipment uptime and improve safety while reducing costs. Currently, they were looking for a solution to make inspection more robust and easy to setup by using intelligent computer vision.
How Digica helped the customer
The Digica team worked on inspection payload improvement that is responsible for inspecting points of interest by detecting objects and performing readouts and interpretation. There were 8 objects shortlisted for detection, including gauges that required reading of values and metrics from images of objects.
What we achieved
Digica with Anybotics team created an improved inspection payload that consisted of a detector and interpreter that allowed to detect and interpret objects within the factory area on the physical robot based on the ROS framework.
Technologies used
The solution consisted of Tensorflow 2 object detection API training and evaluation pipeline where 8 objects could be continuously trained and improved. Furthermore C++, ROS, and OpenCV has been used to develop an interpreter of detected objects and values shown on those objects.
Reviews
the project
IT & Cloud Services for Electronics Manufacturing Company
''We met the final milestone with good accuracy, and it was delivered on time.''
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 a product engineering manager for Teledyne DALSA. We design and manufacture detectors for the medical X-ray market.
What challenge were you trying to address with Digica?
We needed help with custom software development.
What was the scope of their involvement?
Digica did IT and cloud consulting services for us remotely. The concept of this project was a specific failure mode that we encountered with our large area detectors. We explained the requirements to Digica and provided them with the data to help them develop the software.
After that, we asked them to develop software to identify the numerical data and images within the software to detect the failure mode, and they showed us that they could do it with good precision for failure mode detection.
What is the team composition?
We worked with three members of their team.
How did you come to work with Digica?
A colleague had met Digica and was interested in their track record regarding intelligence software; preventative maintenance is very interesting to us as a company, so we had asked them to work on this project together.
How much have you invested in them?
We spent $25,000–$50,000 with them on this project.
What is the status of this engagement?
We worked together from December 2021–March 2022.
What evidence can you share that demonstrates the impact of the engagement?
We worked according to the project plan, which Digica nicely monitored. They came with a proposal for the project planning, and they ensured we met all of that planning. We assessed the software, checking its accuracy in predicting the failure mode correctly and, of course, seeing what the software made false predictions. Overall, they were able to achieve everything with good numbers.
How did Digica perform from a project management standpoint?
Project management was great; we had weekly meetings via Teams. Also, according to the project planning, they monitored all the activities successfully — they took clear ownership of the process and ensured to make everything quickly.
We also scheduled an extra meeting to sort things out if there were any issues, and it all went well. We met the final milestone with good accuracy, and it was delivered on time.
What did you find most impressive about them?
Their ability to lead and manage all the processes was outstanding.
Are there any areas they could improve?
I don't think there's anything they can improve on — I have to say that the outcome was good, the conversations were good, and, as mentioned, the project planning went well.
Do you have any advice for potential customers?
If someone is looking for a company to support them with intelligence software, I would recommend Digica.
the project
Radar Clutter Classification for Radar Products Manufacturer
"They knew what they were doing, worked independently without us having to manage them."
the reviewer
the review
The client submitted this review online.
Please describe your company and your position there.
I'm a radar algorithms developer working for company that develop radar products for the surveillance market.
For what projects/services did your company hire Digica, and what were your goals?
We needed to prototype a new kind of classifier to remove unwanted detections in the radar.
How did you select this vendor and what were the deciding factors?
I was put in touch with Digica through someone at my company who thought they would be interesting for me considering that they have radar experience. We then held a meeting where they presented their previous radar projects and that gave us confidence to continue with a prototype project.
Describe the scope of work in detail, including the project steps, key deliverables, and technologies used.
This was a data science project. The goal was to develop a machine learning-based classifier that would be lightweight enough to run on an IoT-device. We supplied the data and Digica developed and evaluated a number of classifiers. The result was delivered to us in the form of a code repository with scripts for training and evaluating the proposed solutions.
How many people from the vendor's team worked with you, and what were their positions?
All in all, 4 data scientists.
Can you share any measurable outcomes of the project or general feedback about the deliverables?
We saved substantial time in prototyping, and have selected one of the proposed solutions for further development productification.
Describe their project management style, including communication tools and timeliness.
We used Google meet for week-to-week video meetings, and slack for the day-to-day discussions.
What did you find most impressive or unique about this company?
They knew what they were doing, worked independently without us having to manage them. They also acted in an agile fashion when we gave feedback during the project.
Are there any areas for improvement or something they could have done differently?
Not really.
the project
Data Processing App for Radar System Supplier
"Digica was a knowledgeable team with accessible services."
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 CTO and co-founder of a radar system supplier. We design and supply radar systems for border security, perimeter security, and critical asset protection.
What challenge were you trying to address with Digica?
We needed their expertise in custom software development.
What was the scope of their involvement?
Digica developed our data processing application from scratch. We specifically needed a military-grade AI product that was compatible with Windows 10 and Linux. The app was embedded into our system so that we could streamline our data identification efforts based on our targets of interest.
What is the team composition?
We worked with one project manager and one developer.
How did you come to work with Digica?
One of Digica’s managers reached out to me through a cold call. I was convinced that they could deliver the results I needed, so I gave their services a try.
How much have you invested with them?
The total project cost was £30,000 (approximately $42,000 USD).
What is the status of this engagement?
Our engagement with Digica ran from April–June 2021.
What evidence can you share that demonstrates the impact of the engagement?
Digica met all the KPIs we set at the beginning of our engagement. They delivered an efficient platform that allowed us to accurately classify and identify our individual target types, which was our main success metric for their work.
How did Digica perform from a project management standpoint?
We mainly communicated via Microsoft Teams. Digica was particularly on top of their project management game — they followed thorough yet technical processes, which allowed them to meet every deadline we set. Additionally, they were a cooperative team that took our feedback and data into ample consideration.
What did you find most impressive about them?
Digica was a knowledgeable team with accessible services. They were a professional partner that respected our methods and ideas throughout the project.
Are there any areas they could improve?
I’m not much of a technical person, but I was told that the coding could use some improvement. There were some inconsistencies identified in Digica’s coding methods that prolonged our implementation phase. Refining their code work would lead to a more functional and seamless platform.
Do you have any advice for potential customers?
Have a detailed description of everything you want to achieve and make sure to communicate your standards to their team as well. Defining both of these would help Digica to deliver more tailored solutions for you.
the project
ML-Based Visual Inspection Framework for Robotics Company
"We knew that Digica was a genuine partner from the start because they always had our best interests in mind."
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 VP of software engineering at ANYbotics. We focus on building autonomous robots for industrial inspection.
What challenge were you trying to address with Digica?
We needed their expertise in machine learning and computer vision to improve and expand the performance of our visual inspection framework use on our robots.
What was the scope of their involvement?
We needed to address redevelop our visual inspection framework to be based on machine learning object detection, such that our robots would more intelligently correct detect industrial objects and extract digital information from those detected objects. With the help of Digica's development, we are able detect a larger range of objects and help our industrial clients digitally transform their inspection missions.
What is the team composition?
We worked with two main engineers who separately worked on machine learning and computer vision. We profited from the additional part-time involvement of a senior technical lead from Digica.
How did you come to work with Digica?
We found them online after thoroughly searching for potential agencies to hire for this project. We chose Digica because they knew how to work with our tech stack, and they showed an evident interest in delivering our needs at a reasonable price.
What is the status of this engagement?
Our project ran from April–July 2021.
What evidence can you share that demonstrates the impact of the engagement?
Digica’s team helped us successfully implement an entirely new machine-learning-based framework for visual robotic inspection. The information extraction works well and helped us identify the limits of classical computer vision vs. machine learning-enabled computer vision. All product metrics, including the number of new object types we wished to analyze, were delivered.
How did Digica perform from a project management standpoint?
ANYbotics had the main project management lead, yet Digica was at the top of their game when interacting with and supporting and efficient project management. They knew how to ask the right questions, and their adaptability helped us achieve a structured scope. On top of that, they delivered innovative solutions without compromising our own ideas and preferences.
What did you find most impressive about them?
We knew that Digica was a genuine partner from the start because they always had our best interests in mind. They strongly cooperated with our team, so we were able to make the most of our engagement. Overall, we were pleased to have worked with a team that delivered what we wanted with utter sincerity and dedication.
Are there any areas they could improve?
I didn’t encounter any areas that needed improvement. Any adjustments that we had to address throughout the process were from our end.
Do you have any advice for potential customers?
Trust their team to deliver what your business needs and involve them in both the problems and solution discovery. Digica showed that they could work in a highly interactive project and remain effective, so don't be afraid of working with Digica to discover and clarify project requirements as you progress through the project.
We established a clear image of the desired outcome, then we took the time to collaboratively refine the goals of each upcoming development phase as we all became smarter through the project - and it worked beautifully. The Digica developers were able to very effectively work from these project goals and drive their own in partnership and technical discussion with our engineers.
the project
ML Development for Electrical Manufacturing Company
"Their communication was impressive, especially since it was a tight project plan and they really stuck to it."
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 head of radar system design for an electrical manufacturing company. We design human-machine interfaces for washing machines and dishwashers. I develop the electronics for the human-machine interfaces like touch. In this case, it was a radar interface.
What challenge were you trying to address with Digica?
We wanted to try and implement some machine learning algorithms.
What was the scope of their involvement?
Digiga developed source code for us. Their team demonstrated an electronic device that gives them raw data, which they then recorded. They came up with some algorithms and then delivered back the result to us. The final deliverable was a report and source code.
What is the team composition?
We worked with one project manager and two technical people from Digica.
How did you come to work with Digica?
We got in contact at a trade fair in 2018 or 2019. They approached us at an exhibition and we ended up deciding to work with them.
How much have you invested with them?
We have invested €10,000–€30,000 euros (approximately $12,000–$36,000 USD).
What is the status of this engagement?
We worked together from August–October 2020.
What evidence can you share that demonstrates the impact of the engagement?
The code was professionally done and well documented. I was able to use the code and work with it afterward.
How did Digica perform from a project management standpoint?
Digica's project management was great, there was nothing to complain about. We had a weekly meeting with them where they would give us reports of the prior week. We also had a phone call once a week using Google Meet, and between those meetings, we corresponded through email.
What did you find most impressive about them?
Their communication was impressive, especially since it was a tight project plan and they really stuck to it. It was good working with them.
Are there any areas they could improve?
The only thing I asked to be made better was the code documentation. The first results weren’t documented in the source code. I asked them to and they did.
Do you have any advice for potential customers?
I’d have no reservations to recommend working with them.
the project
AI Software Development for Medical Device Company
"They’re just really a tremendous organization to work with."
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 surgical process optimization software company.
What challenge were you trying to address with Digica?
We were trying to solve the issues around instrument and implant management within hospitals and surgery centers.
What was the scope of their involvement?
We’re working with Digica to develop a proprietary image recognition technology for surgical instruments, equipment, and implants.
They are able to deliver on a very complex set of instruments that are laid out for a large number of surgical procedures. Utilizing common technology such as iPhones or Android phones, they are able to build a software that will enable everyday employees and workers within a hospital system, to snap pictures of surgical trays, and identify what’s there and what’s missing.
This technology will greatly increase our ability to get surgery right. It creates a better work environment for the people, and the guesswork will be removed thanks to what Digica is building.
What is the team composition?
We’re working with about 6 people on this project. It’s a broad spectrum of data engineers, developers, graphic artists, and a project manager — a full team essentially.
How did you come to work with Digica?
It was actually our CTO who found and connected with them through The World Economic Forum. Our CTO sits on the forum’s council for AI, so I believe they connected that way.
What is the status of this engagement?
We started working together in July 2020, and we’re still continuing to work with them.
What evidence can you share that demonstrates the impact of the engagement?
Everything was based on average precision scores and chaos models, where we determine the accuracy in real-time against a tray with a human in the loop interaction.
And in terms of anecdotal feedback, they’re just really a tremendous organization to work with. I had concerns in the beginning that there might be language barriers, but everything has been really seamless — it’s been a great experience.
How did Digica perform from a project management standpoint?
We have a shared communication platform that we work on together. We have bi-weekly progress reports and they constantly update us on their progress. Moreover, they’re really good at documenting the testing throughout the project. As they go, they leave us with the confidence that the algorithms continue to gain as they move through different projects.
What did you find most impressive about them?
We are impressed with their speed.
Are there any areas they could improve?
Nothing comes to mind at the moment. I don’t have anything to declare.
Do you have any advice for potential customers?
Clearly define your goals and objectives, and give them targets to shoot for. They’re a task-driven team that works hard to achieve their goals in a timely, if not early, manner. They reached our desire threshold a month earlier than expected.
the project
Native C++ & Python Mobile Solution Dev for Research Firm
"Their deep knowledge and technical know-how impressed us."
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 am the founder of a research firm that focuses on visual or video analytics.
What challenge were you trying to address with Digica?
We wanted to explore how we could extract health metrics from video analytics. This goes beyond traditional computer vision techniques which is why we needed outside help.
What was the scope of their involvement?
Digica was in charge of developing the algorithms based on machine learning. It was a mobile app made for internal use. It is a pretty straightforward project. It wasn’t an easy task, but they delivered it. They used Native C++ and Python for development.
What is the team composition?
We have worked with three people from Digica including Rafal (CEO), the lead data scientist, and the project manager, who was our main point of contact.
How did you come to work with Digica?
We found them through Clutch before they merged with another company to form Digica. We chose them because of their experience with computer vision.
How much have you invested in them?
We have invested $150,000 USD.
What is the status of this engagement?
We started working with them in August 2020, and we are still working with them.
What evidence can you share that demonstrates the impact of the engagement?
In general, the feedback is positive. They obviously have the technical know-how. They aren’t permanently focused on the UX and UI because they aren’t a design firm, but when it comes to having the process work, it works. It was just an idea six months ago and now it's a reality. Obviously, that is something to shout about.
How did Digica perform from a project management standpoint?
They were exceptional. If there were any limitations, it was made known early. There were no rude surprises and timeline adherence was a strict priority. Three times a week we have a stand-up where we closely monitor the progress of the project.
What did you find most impressive about them?
Their deep knowledge and technical know-how impressed us. I think those qualities are very underrated. A lot of companies can claim to do certain things, but it is really the ability to really do what you say you can do.
When it comes to Digica, they have the experience and ability to get things done. They could always come up with a very elegant solution. When you engage with a vendor, the last thing that you want is for a ton of money to be spent and have a bunch of time dedicated but not have the results. I am very happy that we have been getting some results.
Are there any areas they could improve?
The project covers a very large canvas, everything from computer vision to engineering. We needed to assemble a team that could fill the gaps to provide the solutions, Their ability to do so shows that they have a large pool of talent so that they can piece people together. They also established a project lead so when they first start the project, they would understand the requirements and know how to assemble the team.
It’s more like an art rather than a science to understand the true requirements of a project, finding the right people, and putting the team together. I think that is really where they shine, and because of that, I don’t have any constructive criticism on how they can improve.
the project
Machine Learning Model Development for IoT Platform
"It is very clear that their work has shown us and our clients sufficient value."
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 an IoT software company providing end-to-end services for global customers.
What challenge were you trying to address with Enigma Pattern?
We were trying to take our data analysis to the next level for one of our larger clients. Our team was gathering a lot of data to make sudden reporting and value derivations for them. We knew there was more we could unpack with their data, so we hired Enigma Pattern to help us meet this challenge.
What was the scope of their involvement?
They provided hardcore Artificial Intelligence Markup Language (AIML) and data science expertise. Looking at the data, they would make decisions on what the data told us using different AIML models and techniques for pattern-seeking.
Our subject matter experts would work with them and request data to try to modify these models, looking to produce more relevant information for our customer’s business. Using this, we could then derive a set of very valuable reports for our client.
How did you come to work with Enigma Pattern?
I had an existing relationship with Rafal (CEO, Enigma Pattern). We knew each other in a previous life, and I knew he was very easy to work with and would find very high-caliber individuals for me to work with.
How much have you invested with them?
We invested somewhere in the £30,000–£50,000 range (approximately $39,000–$65,000 USD).
What is the status of this engagement?
The project lasted from September–December 2019, but we’re looking to start further projects with them.
What evidence can you share that demonstrates the impact of the engagement?
They provided us a set of valuable reports, graphs, and charts that described the trends, patterns, and information in our data. This information was all gleaned from the modeling they had done. It is very clear that their work has shown us and our clients sufficient value, so much so that we’re moving forward to a second and third phase of this project.
How did Enigma Pattern perform from a project management standpoint?
They performed well. I was slightly removed from the project, but the overall feedback I received was positive.
What did you find most impressive about them?
They were very flexible. They were ready to work with us regardless of the amount of work we had, and they were easy to work with in a way that many partners, unfortunately, are not.
Are there any areas they could improve?
No, not in any way I know. I was a step removed, but no problems were ever escalated to me. We’re very happy with Enigma Pattern.
the project
AI Services for Thermal Imaging Systems Company
"There aren’t that many people who have as good a knowledge base as the Enigma Pattern team."
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 technical lead of an international company that builds thermal imaging systems.
What challenge were you trying to address with Enigma Pattern?
We wanted their help in applying AI to thermal imaging systems.
What was the scope of their involvement?
Enigma Pattern provided data science services and neural networks system development. We were active in this project for six months. I can’t say anything in more detail than that. We’ve done more than one project with Enigma Pattern and are working on another one right now.
How did you come to work with Enigma Pattern?
My boss, who is the CTO, ran into Enigma Pattern at a trade show. There was interest in following up, so we had initial meetings with their team.
What is the status of this engagement?
Our work began a year and a couple of months ago. We’ve done more than one project with them and have a good working relationship with Enigma Pattern.
What evidence can you share that demonstrates the impact of the engagement?
This project was to replace conventional AI analytics with AI-based analytics. They were able to perform at about 30%, so there was a significant improvement in performance.
How did Enigma Pattern perform from a project management standpoint?
They provided a weekly report that we reviewed section by section. There were rocky moments at times but it was good in the end; they’re in Poland and we’re in the US but their project management was adequate.
What did you find most impressive about them?
There aren’t that many people who have as good a knowledge base as the Enigma Pattern team. They have several Ph.D. holders who are quite knowledgeable on their team. Their strength was their knowledge of neural networks, analytical and data science capabilities.
Are there any areas they could improve?
They could improve their project management skills. We didn’t encounter technical issues, rather issues with project management. They definitely made strides to improve it later on but there were definitely some growing pains.
the project
AI Development Services for Toy Company
“Enigma Pattern has delivered on time, within budget, and to our expectations.”
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 work for a toy company, and I’m responsible for sourcing external technologies to use in our products.
What challenge were you trying to address with Enigma Pattern?
We had some AI tasks to solve.
What was the scope of their involvement?
Enigma Pattern provides development for an AI product. I cannot disclose any details.
How did you come to work with Enigma Pattern?
We chose them because they had good insights into our problem. They also had some qualified people to solve that problem for us, and they made a good pitch.
What is the status of this engagement?
We started working with Enigma Pattern at the beginning of 2018. The project is ongoing.
What evidence can you share that demonstrates the impact of the engagement?
Enigma Pattern has delivered on time, within budget, and to our expectations.
How did Enigma Pattern perform from a project management standpoint?
They’re quite good at following up, and they’ve met the main and interim deadlines. They provide us with some Excel sheets for project management. We use tools like Asana and Jira internally, but not with Enigma Pattern.
What did you find most impressive about them?
They’re on par with other service providers we’ve worked with in the same field. They have a unique approach to solving our problem, which is quite good.
Are there any areas they could improve?
No, there’s nothing off the top of my mind.
The client was satisfied with Digica's ability to achieve their goals with good numbers. They lead a communicative and involved process to ensure a solid project management experience, which they took ownership of. The team also prases their ability to take care of all the processes.