Machine Learning for Asset Management

Machine Learning for Asset Management

DataArt published a new case study about using Machine Learning for asset management. The solution delivered significantly automated the image filtering process, making it possible to scale the business model as required. The Machine Learning approach facilitated a number of business benefits:
  • Reducing the human resources involved and automating the process;
  • Constantly improving image recognition models using the regression learning pipeline;
  • Ensuring that image recognition algorithms work on resource-limited devices, making it possible to use the solution in real time without cloud computation power;
  • Using cloud technologies to scale the solution.
The full case study is available here.
Read More »



DataArt on the Leading Edge of Food Recognition

DataArt on the Leading Edge of Food Recognition

The DataArt Orange initiative spent lots of development efforts for its food recognition R&D project. And finally it feels that the market is ready for the technology. Last week Google announced at the Rework Deep Learning Summit an artificial intelligence project to calculate the calories in pictures of food you have taken. According to The Guardian, “the prospective tool called Im2Calories, aims to identify food snapped and work out the calorie content”. There is not much information about the project and what algorithms are available at the moment, but what is available indicates that Im2Calories will utilize a similar approach used by DataArt’s Computer Vision Competence Centre researchers in their Eat’n’Click project.
Read More »


DataArt Orange to integrate its food recognition engine with Apple HealthKit and Voice Recognition

Eat’n’Click is an application developed by DataArt that helps people track the nutritional content of foods they consume. The app automatically tracks calorie information by scanning photographs of food.

Its prototype is available on the App Store and can recognize a number of fruits with more than an 85% success rate. Recently the application was demonstrated by the DataArt team during the Health 2.0 Europe 2014 event in London and was highly appreciated by its participants.

Following industry trends and the high attention Apple HealthKit is receiving, DataArt’s Research Lab decided to move forward by automating the tracking of users’ nutrition habits. DataArt is planning to build a PoC prototype to integrate with Apple HealthKit. Also, we plan to implement a voice recognition engine with it. The aim of DataArt’s Orange R&D initiative is to reduce the gap between humanity and computers. And we strongly believe that this step will be highly effective.

FoodR Slim to be integrated with Apple HealthKit and Voice Recognition
Read More »

DataArt Computer Vision Team To Develop Object Tracking PoC

Responding to a request from a potential customer, DataArt’s R&D department created a prototype application for object recognition and tracking within a video. The customer’s idea for the product was that an object, selected manually in a video for the first time, is then tracked automatically throughout the footage, with the object coordinates retrieved and stored as the video progresses. DataArt’s computer vision scientists and engineers timely conducted a feasibility study, which appeared to be positive, and created a prototype object tracking application. The application allows loading a video, pointing at an object at a specific frame (or again later if the automatic tracking fails), and runs an object tracking analysis over the loaded file. The object is located in the following frames, and the location of the object is stored along with the video as a key-value file, where the calculated coordinates of the object correspond to the current playback time. A commercial playback application could, using this information, then place an ad over the video at these specific coordinates during the playback, thus allowing for dynamic context advertising. film-5  
Read More »

Fruit recognition – some improvement

The quality of visual fruit recognition PoC was improved by adding texture and RGB color space features information to the feature vector. Same as in our previous experiment, we took the neural network as a classifier. The network learns with error of 0.155. The results are given below: fruit recognition In general, the quality of recognition was increased in 0.112%.
Read More »

How To: Integrate Your Heart Rate App with HealthKit API

At the Apple Worldwide Developer Conference earlier this month Apple introduced an app simply called “Health”that promises to become an all-embracing hub for healthcare and fitness applications and wearable devices. It will allow you to store all of your health data and vital signs in one place including your heart rate, blood pressure, blood sugar, sleep patterns, consumed and burnt calories and more. It will also give you control over all of your health apps through one interface. The news inspired our team to integrate our health apps with the HealthKit API to help bring the world one step closer to integrated health data. We started with our Heartbeat Rate application that processes the video stream from your iPhone/ iPod camera to measure heart rate. It analyzes the bluecomponent in the video stream providing reliable results, thus no physical contact is required. (Read more about Heartbeat Rate application.) Here is the recap of how our Heartbeat rate app was integrated with HealthKit API.
Read More »

DataArt Computer Vision Lab Released Football Clubs Recognizer

img_area_phantom
Event Image
DataArt Research Lab has released its application for football fans that visually identifies football clubs. Football Clubs Recognizer is available on the Apple App Store. In preparation for the 2014 Football World Cup, DataArt Computer Vision experts developed the first version of an application that provides full information about football teams including their place in the standings, roster, list of recent and upcoming matches, information about players, etc. To get information regarding a certain team just point the phone camera at a team logo wherever it may be displayed. The application can successfully recognize logos from screens, newspapers, etc.
Read More »

Fruit Recognition – Continuing Research

Fruit Recognition – Continuing Research

DataArt Research Lab continues to publish the results of fruit recognition using the Color Distance method. The Color Distance method showed good result as an engine for fruit recognition. Just for testing purposes, we took 15 classes of fruits (10 ‘ideal’ samples for each class) and a simple classifier of Euclidian distance. But such an approach has serious disadvantages:
  • in everyday life we do not deal with ideal pictures: the photos may contain different distortions, irregular brightness  etc.;
  • the classifier of Euclidian distance cannot provide us with real time work, particularly if we have a lot of classes and etalons.
So our next step is to use a more complicated real time working classifier and increase the sample set with new ‘real’ images.
Read More »


DataArt Announces ORANGE – the Missing Piece in Nutrition Tracking

New R&D initiative provides food recognition technology to calculate calorie intake NEW YORK – March 27, 2014DataArt, a leading custom software development company that builds advanced solutions for select industries, today announced the first results of DataArt ORANGE, a series of research and development projects that aim to automate the tracking of users’ nutrition habits. The DataArt ORANGE program automatically tracks calorie information by scanning photographs of food. DataArt ORANGE technology can currently recognize over 100 foods with an 85% success rate.
Read More »

DataArt Research Lab publishes Color distance method testing results

DataArt Research Lab publishes Color distance method testing results

The color distance method has been tested using 15 fruit types, each type having 10 photos. The following recognition score calculation algorithm has been used:

  • Three guesses (ordered best to worst) are considered.
  • A correct guess placed first obtains 10 points, placed second – 5, placed third has 1.
  • For all tests for a particular fruit type the obtained points are summed up and divided by the absolute maximum result 10 * N, where N – the number of tests for the class, thus yielding the classification quality for the type.
  • The overall classification quality for the whole fruit set, the individual classification qualities for every fruit type are averaged.
Read More »

DataArt Research Lab to experiment on finding and proofing feature extraction methods suitable for food recognition tasks

img_area_phantom
Event Image
Meals named the same rarely look similar. This is not only due to different people cook differently – in the computer vision sense, meals are combinations of areas (spots) with different color, texture, shape each. This makes typical image recognition principles less suitable for food image recognition, as we cannot rely on either form or relative position of the image parts. Typically, if local peculiarities of objects being detected cannot be caught, integration feature extraction methods take over differential one – e.g. in our current food image classification engine we mostly rely on combined histogram and texture parameters for the whole image. This approach shows relatively good results unless the meal we’re trying to classify appears to have no noticeable texture features.
Read More »

DataArt Has Started an R&D Project in Remote Human Pulse Detection, Based on Digital Signal Processing Principles

img_area_phantom
Event Image
Heartbeat Rate app allows to measure the pulse using video processing algorithm
Inspired by recent publication on a video processing algorithm, which is able to detect and magnify subtle periodic changes in color in the series of video frames, DataArt has started experiments on adding heartbeat measurement possibility to their Microsoft Kinect-based healthcare solution. The principle of detection is based on the fact that the human skin becomes more red when the blood pressure is at its maximum (systolic pressure), and less red when the pressure is at its minimum (diastolic pressure). For people not having arrhythmia, these changes are periodic, and therefore, its’ frequency can be caught and measured using spectrum analysis principles.
Read More »

DataArt is Building Face Recognition Application for iOS

img_area_phantom
Event Image
To broaden its professional horizons and get involved into something new, DataArt decided to dive into computer vision area, and to be more accurate, face recognition techniques. Our computer vision group created face recognition app that has access to DataArt employees’ database and could recognize them.
Read More »

iOS Sport Application For Football Fans

img_area_phantom
Event Image
DataArt has finished an experimental iOS-based application that visually recognizes UK football clubs by their emblems. The software identifies club emblems shown on a computer or TV screen, printed in a magazine or a newspaper, or even tattooed on a fan’s chest.
Read More »

Augmented Reality on a Gadget

What we typically call an Augmented Reality app on a smartphone or a touchpad device is built the following way: it captures the video stream provided by the built-in camera, transforms it, and delivers the output stream to the screen. The process of ‘transformation’ generally includes detection of a known object (marker) in the input stream, calculating its position in the 3D scene geometry, overlaying the scene with an artificial 3D model, placed at the right position and angles, and putting all this together. Depending on the application, the model can be static or dynamic, interactive or not, etc.
Read More »

DataArt Computer Vision Team has Created an All-custom Augmented Reality Engine Prototype

img_area_phantom
Event Image
Augmented reality example in Cactus.AR app
Following a CV-related inquiry, the computer vision team at Dataart created a custom solution for detecting, capturing, and tracking visual markers from a real time video stream. What is usually called Augmented Reality and typically associated with a 3rd party ‘black box’ which does all the complicated spatial job, is now modeled and implemented from scratch by DataArt, with all the 3D mathematics created by researches and ported and implemented by developers.
Read More »