Rotation and flipping robust region binary patterns for video copy detection

Image-based coin recognition using rotation-invariant region binary patterns based on gradient magnitudes

“…Rotation and flipping robust region binary pattern (RFR) has been proposed to detect rotated or flipped copy videos [19]. It uses region binary pattern template, which consists of several rings, and each ring is divided into several sub-regions.…”

“…Fig. 2 shows all possible RFRs from 6 sub-regions [19]. The decimal numbers in RFRs denote their indexes, which are used to convert RBP to RFR.…”

“…In this paper, we propose a new coin feature based on the spatial structure of coin images by employing a rotation and flipping robust region binary patterns (RFR) [19]. Instead of luminance of RFR [19], we use gradient magnitudes in coin images to extract RBP because it is a more effective way to represent coin images [14].…”

“…Instead of luminance of RFR [19], we use gradient magnitudes in coin images to extract RBP because it is a more effective way to represent coin images [14]. Our gradient magnitude approach is different from the edge feature approaches [1,2].…”

Video Copy Detection based on Uniform Local Binary Pattern

“…Firstly, shot segmentation are performed, key frame features are extracted for video identification. Semin Kim [2] proposed two complementary region binary patterns from several rings in key frames are used as video fingerprint which is robust against rotation and flipping, but algorithm is more sensitive to sharpen. Teng Li [3] proposed video copy detection method jointly utilizing the characteristics of temporal continuity and multi-modality of video with high efficiency and robustness.…”