Exploiting Oriented Gradient Histogram for Dorsal Vein Recognition

This paper discusses the combination of histogram of oriented gradients and dorsal vein images. Histogram of oriented gradients (HOG) is a feature descriptor used for dorsal hand vein images. Raw images of dorsal hand vein are taken from Bosphorus dataset and after pre-processing, region of interest is extracted. Interesting features are calculated by following the steps of HOG algorithm, which captures edge information inside the images. Edges are the important features containing valuable information even from the raw images. Nearest neighbor is used as a classifier. Bosphorus data is a collection of vein data from 100 subjects with lots of variations. By experimental work, our algorithm is proved to be better than all existing feature descriptors.