Image Mosaicing using Harris, SIFT Feature Detection Algorithm
Hemlata Joshi, M. Tech · 2013
Image Mosaicing has wide applications in the field of 3D image reconstruction, medical imaging, military automatic target recognition, video conferencing, and data from satellites. An Image Mosaicing is a method of assembling multiple overlapping images of the same scene into a larger image. The input images are stitched together using image mosaicing algorithms i.e. Harris and SIFT (Scale Invariant Feature Transform). In this paper, a comparative study is done among the common stitching algorithms: Harris corner detection algorithm, SIFT algorithm. The principles of these algorithms are described in terms of computing time and stitching precision. Harris algorithm detects more features and is only rotationally invariant. SIFT is both rotationally and scale invariant, although it is slow. Harris corner detection algorithm (5) was proposed by Harris C and Stephens MJ in the year 1988. Harris algorithm is a point feature extracting algorithm based on Moravec algorithm. It is an algorithm based on still image used for combined corner and edge detector. Reasonable amount of corner features are extracted which gives a better quantitative measurement by using a stable operator. A local detecting window in image is designed. The average variation in intensity is determined by shifting the window by a small amount in different direction. The centre point of the window is extracted as corner point. The point can be recognized easily by looking at the intensity values within a small window. Shifting the window in any direction gives a large change in appearance. Harris corner detector is used for detecting corners. On shifting the window if it's a flat region than it will show no change of intensity in all direction. If an edge region is found than it will show no change of intensity along the edge direction. But if a corner is found than there will be a significant change of intensity in all directions. Harris corner detector gives a mathematical approach for determining the region is flat, edge or corner. Harris corner technique detects more features and it is rotational invariant and scale variant. Harris gave a formula that can be calculated out the change of the pixel values in any direction, rather than fixed in the 8 directions.