Vol 3 , Issue 1 , January - March 2015 | Pages: 34-42 | Research Paper
Received: January 21, 2015 | Revised: February 15, 2015 | Accepted: February 28, 2015 | Published Online: March 15, 2015
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