Rotation Invariant Histogram of Oriented Gradients
Minkyu Cheon, Wonju Lee, Chang‐Ho Hyun, Mignon Park · International Journal of Fuzzy Logic and Intelligent Systems · 2011
In this paper, we propose a new image descriptor, that is, a rotation invariant histogram of oriented gradients (RIHOG). RIHOG overcomes a disadvantage of the histogram of oriented gradients (HOG), which is very sensitive to image rotation. The HOG only uses magnitude values of a pixel without considering neighboring pixels. The RIHOG uses the accumulated relative magnitude values of corresponding relative orientation calculated with neighboring pixels, which has an effect on reducing the sensitivity to image rotation. The performance of RIHOG is verified via the index of classification and classification of Brodatz texture data.