In this work we describe an approach to real-time image search in large databases robust to variety of query distortions such as lighting alterations, projective distortions or digital noise. The approach is based on the extraction of keypoints and their descriptors, random hierarchical clustering trees for preliminary search and RANSAC for refining search and result scoring. The algorithm is implemented in Snapscreen system which allows determining a TV-channel and a TV-show from a picture acquired with mobile device. The implementation is enhanced using preceding localization of screen region. Results for the real-world data with different modifications of the system are presented.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Natalya Skoryukina ; Timofey Chernov ; Konstantin Bulatov ; Dmitry P. Nikolaev and Vladimir Arlazarov
Snapscreen: TV-stream frame search with projectively distorted and noisy query
", Proc. SPIE 10341, Ninth International Conference on Machine Vision (ICMV 2016), 103410Y (March 17, 2017); doi:10.1117/12.2268735; http://dx.doi.org/10.1117/12.2268735