Video learning based image classification method for object recognition

Abstract

Automatic image classification is the first step toward semantic understanding of an object in the computer vision area. The key challenge of problem for accurate object recognition is the ability to extract the robust features from various viewpoint images and rapidly calculate similarity between features in the image database or video stream. In order to solve these problems, an effective and rapid image classification method was presented for the object recognition based on the video learning technique. The optical-flow and RANSAC algorithm were used to acquire scene images from each video sequence. After the selection of scene images, the local maximum points on corner of object around local area were found using the Harris corner detection algorithm and the several attributes from local block around each feature point were calculated by using scale invariant feature transform (SIFT) for extracting local descriptor. Finally, the extracted local descriptor was learned to the three-dimensional pyramid match kernel. Experimental results show that our method can extract features in various multi-viewpoint images from query video and calculate a similarity between a query image and images in the database.

Keywords

image classification / multi-viewpoint image / feature extraction / video learning

References

[1] YanP, KhanS M, ShahM. Three-dimensional model based object recognition from arbitrary view [C]. International Conference of Computer Vision, 2007Rio de Janeiro, BrazilIEEE1-6

[2] FischlerM A, BollesR C. Random sample consensus: A Paradigm for model fitting with applications to image analysis and automated cartography [J]. Comm of the ACM, 1981, 24(6): 381-395

[3] HarrisC, StephensM. A combined corner and edge detector [C]. Proceedings of the 4th Alvey Vision Conference, 1988Manchester, UKThe Plessey Company147-151

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

[5] KeisterL H. User types and queries: Impact on image access systems [C]. Challenges in Indexing Electronic Text and Images, Learned Information, 1994Medford, NJASIS7-22

[6] FerrisM, MunsonT. Interior-point methods for massive support vector machines [J]. SIAM Journal on Optimization, 2002, 13(3): 783-804

[7] LazebnikS, SchmidC, PonceJ. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories [C]. Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, 2006New YorkIEEE Press2169-2178

[8] GraumanK, DarrellT. The pyramid match kernel: discriminative classification with sets of image features [C]. Tenth IEEE International Conference on Computer Vision (ICCV’05), 2005BeijingIEEE Press1458-1465

[9] PetersohnC. Logical unit and scene detection: A comparative survey [C]. Proceedings of SPIE, Multimedia Content Access: Algorithms and Systems II, 2008682002.1-682002.17

[10] RasheedZ, ShahM. Detection and representation of scenes in videos [J]. IEEE Trans Multimedia, 2005, 7(6): 1097-1105

[11] HanjalicA, LegendijkR J, BiemondJ. Automated high-level movie segmentation for advanced video-retrieval systems [J]. IEEE Tran on CSVT, 1999, 9(4): 580-588

[12] HanjalicA, LagendijkR L, BiemondJ. Automated high-level movie segmentation for advanced video-retrieval systems [J]. IEEE Trans Circuits Syst Video Technol, 1999, 9(4): 580-588

[13] YeungM, YeoB, LiuB. Segmentation of videos by clustering and graph analysis [J]. Comput Vis Image Understand, 1998, 71(1): 94-109

[14] SwainM J, BallardD H. Color indexing [J]. International Journal of Computer Vision, 1991, 7(1): 11-32