Automatic document analysis and recognition is a hot topic in a modern computer vision. 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 like pictures, tables, text data, links, etc. There are several challenges in this case: geometric distortions of the paper, varying illumination, occlusions.
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 optical flow algorithm and then refines the residual warp using the optimized template matcher.
Object recognition is an important computer vision and machine learning problem. A particular case is automatic target recognition (ATR) on radar images. In the project, our team has developed a custom classification algorithm based on two different tools. We have been working with MSTAR dataset. This is a public dataset containing ten classes of vehicles with different orientations with 0.3mx0.3m.