Journal Press India^®

Author Details ( * ) denotes Corresponding author

Spatial region hybrid matching (SRHM) is mainly used for comparing or computing the similarity of the both images in the computer vision and in the image processing also. By comparing the two images, SRHM implicitly assumes that: in the two images from the same Image category. Similar objects will appear in the same location. In the technique of Hybrid Spatial Matching (HSM) is well flexible similarity of the image by computing method to alleviate the problem of mismatching in SRHM. And the mismatching problem will be detected easily by HSM and the process is very faster for comparing of both images. In addition to that, the spatial matches between the corresponding regions, SRHM considers the relationship of the all spatial pairs in the both images. It will include more meaningful match than HSM. The technique propose two learning strategies for the learning of SVM models in the new technique of HSM Kernel in image, which are thousands of time faster than the general purpose method of SVM and also this technique is effective. The technique is used to compute the Hybrid Spatial Matching and Spatial Region Hybrid Matching on several challenging benchmarks and the technique is clearly shows that SRHM is more flexible and efficient than HSM by the way of computing each and every pixels of both images.

Keywords

Image Similarity; Region Classification; Image Comparison; Spatial Pyramid Matching; Flexible Image Similarity; Pixel Mismatch Detection; Spatial Pixel Coordinates Calculation

1. S. Lazebnik, C. Schmid, J. Ponce, Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories, in Proc. IEEE IntT Conf. on Computer Vision and Pattern Recognition, 2, 2006, 2169-2178.


2. T. Harada, Y. Ushiku, Y. Yamashita, Y. Kuniyoshi, Discriminative spatial pyramid," in Proc. IEEE IntT Conf. on Computer Vision and Pattern Recognition, 2011,1617-1624


3. G. Sharma, F. Jurie, C. Schmid, Discriminative spatial saliency for image classification, in Proc. IEEE IntT Conf. on Computer Vision and Pattern Recognition, 2012,3434-3441


4. Y. Jia, C. Huang, T. Darrell, Beyond spatial pyramids: Receptive field learning for pooled image features, in Proc. IEEE IntT Conf. on Computer Vision and Pattern Recognition, 2012, 3370-3377


5. Y.-L. Boureau, F. Bach, Y. LeCun, J. Ponce, Learning mid-level features for recognition, in Proc. IEEE IntT Conf. on Computer Vision and Pattern Recognition, 2010,2559-2566


6. J. Yang, K. Yu, Y. Gong, 1. Huang, Linear spatial pyramid matching using sparse coding for image classification, in Proc. IEEE IntT Conf. on Computer Vision and Pattern Recognition, 2009


7. J. Wang, J. Yang, K. Yu, F. Lv, T. Huang, Y. Gong, "Locality constrained linear coding for image classification," in Proc. IEEE IntT Conf. on Computer Vision and Pattern Recognition, 2010, 3360-3367


8. F. Perronnin, J. S'anchez, T. Mensink, Improving the Fisher kernel for large-scale image classification, in Proc. European Conf. Computer Vision, ser. LNCS 6314,2010,143-156


9. J. Wu, J. M. Rehg, Centrist: A visual descriptor for scene categorization, IEEE Trans, on Pattern Analysis and Machine Intelligence, 33(8), 2011, 1489-1501


10. F. Perronnin, C. Dance, Fisher kernels on visual vocabularies for image categorization, in Proc. IEEE IntT Conf. on Computer Vision and Pattern Recognition, 2007, 1-8.


11. R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, C-J. Lin, "Liblinear: A library for large linear classification, Journal of Machine Learning Research, 9,2008,1871-1874


12. J. Wu, Efficient HIK SVM learning for image classification, IEEE Trans, on Image Processing, 21(10), ,2012,4442-4453


13. A. Vedaldi, A. Zisserman, Efficient additive kernels via explicit feature maps, IEEE Trans, on Pattern Analysis and Machine Intelligence, 34(3), 2012, 480-492


14. J. Wu, Power Mean SVM for large scale visual classication, in Proc. IEEE IntT Conf. on Computer Vision and Pattern Recognition, 2012, 2344-2351


15. G. Sharma, F. Jurie, Learning discriminative spatial representation for image classification, in Proc. British Machine Vision Conference, 2011