DOI: 10.3724/SP.J.1089.2010.11041

Journal of Computer-Aided Design & Computer Graphics (计算机辅助设计与图形学学报) 2010/22:9 PP.1483-1490

GPU-Based Fast Image Copy Detection

To speed up image copy detection by exploring the powerful computing capability of GPU, a novel GPU-based image copy detection scheme is proposed. Firstly, a new scale-invariant interest point detector-Harris-Hessian (H-H) is designed according to the architecture of GPU. The H-H extracts interest points in low scale and refines their location and scale in a series of scale-space with the determinant of Hessian matrix, which significantly reduces the pixel-level computation complexity and has better parallelism. Then, an image copy detection system based on the H-H is presented, the detection speed is significantly improved. The experimental results show that, compared to the existing CPU-based methods, the H-H achieves up to a speedup factor of 10~20 times and maintains a high detection accuracy. It only takes 19.8 ms for the system to detect a 640×480 image in a dataset of 11 250 images with 95% accuracy rate, which meets the demand of real-time applications under large scale data.

Key words:image copy detection,scale invariant,interest points,GPU,CUDA

ReleaseDate:2014-07-21 15:25:43

[1] Gao Ke, Lin Shouxun, Zhang Yongdong, et al. Object-based image retrieval using spatial context[J]. Journal of Computer-Aided Design & Computer Graphics, 2008, 20(11): 1452-1458 (in Chinese) (高 科, 林守勋, 张勇东, 等. 基于空间上下文的目标图像检[J]. 计算机辅助设计与图形学学报, 2008, 20(11): 1452-1458)

[2] Bay H, Tuytelaars T, Van Gool L. SURF: speeded up robust features[C]// Proceedings of European Conference on Computer Vision. Graz: Springer, 2006: 404-417

[3] Zheng Q F, Wang W Q, Gao W. Effective and efficient object-based image retrieval using visual phrases[C]// Proceedings of the 14th Annual ACM International Conference on Multimedia. Santa Barbara: ACM Press, 2006: 77-80

[4] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110

[5] Wu Enhua. State of the art and future challenge on general purpose computation by graphics processing unit[J]. Journal of Software, 2004, 15(10): 1493-1504 (in Chinese) (吴恩华. 图形处理器用于通用计算的技术、现状及其挑战[J]. 软件学报, 2004, 15(10): 1493-1504)

[6] NVIDIA. NVIDIA CUDA programming guide: Version2.0[OL]. [2009-09-21].

[7] Heymann S, Müller K. Sift implementation and optimization for general-purpose GPU[C]// Proceedings of the 15th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision. Plzen: Czech Republic, 2007: 1-3

[8] Sinha S N, Frahm J M, Pollefeys M, et al. GPU-based Video Feature Tracking and Matching[C]// Proceedings of workshop on Edge Computing Using New Commodity Architectures. Chapel Hill: UNC Republic, 2006: 6-12

[9] Cornelis N, Van Gool L, Leuven K U. Fast scale invariant feature detection and matching on programmable graphics hardware[C]// Proceedings of Computer Vision and Pattern Recognition. Alaska: IEEE Computer Society Press, 2008: 1-8

[10] Mikolajczyk K, Schmid C. Scale & affine invariant interest point detectors[J]. International Journal of Computer Vision, 2004, 60(1): 63-86

[11] Mount D M, Arya S. ANN: a library for approximate nearest neighbor searching [OL]. [2009-09-21]. http://

[12] Hua X S, Chen X, Zhang H J. Robust video signature based on ordinal measure[C]// Proceedings of International Conference on Image Processing. Singapore: IEEE Computer Society Press, 2004: 685-688

[13] Harris C, Stephens M. A combined corner and edge detector[C]// Proceedings of the 4th Alvey Vision Conference. Manchester: University of Sheffield Printing Unit, 1988: 147-151

[14] Mikolajczyk K, Tuytelaars T, Schmid C, et al. A comparison of affine region detectors[J]. International Journal of Computer Vision, 2006, 65(1): 43-72