Video Repeat Recognition and Mining by Visual Features

Repeat video clips such as program logos and commercials are widely used in video productions, and mining them is important for video content analysis and retrieval. In this chapter we present methods to identify known and unknown video repeats respectively. For known video repeat recognition, we focus on robust feature extraction and classifier learning problems. A clustering model of visual features (e.g. color, texture) is proposed to represent video clip and subspace discriminative analysis is adopted to improve classification accuracy, which results in good results for short video clip recognition. We also propose a novel method to explore statistics of video database to estimate nearest neighbor classification error rate and learn the optimal classification threshold. For unknown video repeat mining, we address robust detection, searching efficiency and learning issues. Two detectors in a cascade structure are employed to efficiently detect unknown video repeats of arbitrary length, and this approach combines video segmentation, color fingerprinting, self-similarity analysis and Locality-Sensitive Hashing (LSH) indexing. A reinforcement learning approach is also adopted to efficiently learn optimal parameters. Experiment results show that very short video repeats and long ones can be detected with high accuracy. Video structure analysis by short video repeats mining is also presented in results.