Efficient Descriptor of Histogram of Ridges Orientation Delineate for Fingernail

Fingernails structure are rich in orientation, ridges and edge features. Inspired by Edge Histogram Descriptor (EHD), this paper presents an efficient orientation-based local descriptor, named histogram of ridges orientation delineate (HROD). HROD is based on the fact that human vision is sensitive to edge features for image perception. For a given image, HROD algorithm first execute and perform a pre-process i.e., re-sizing, filtering, enhancement, segmentation, edge detection and feature extraction. Then, finds oriented edge maps according to predefined orientations using a well-known edge operator mask (2×2 sub block) and obtains a ridges orientation delineate map by choosing an orientation with the maximum edge magnitude for each pixel. In the experiment on this research, five oriented edge maps were used to generate and detect the maximum edge orientation construction of each block, namely vertical, horizontal, diagonal 45°, diagonal 135° and isotropic (non-orientation specific) orientation. Experimental results on fingernail images show that the performance of HROD comparable with the state-of-the-art orientation-based methods (e.g., Gabor filter, histogram of oriented gradients, and local directional code). Furthermore, the proposed HROD algorithm has advantages of low feature dimensionality and fast implementation for a real-time fingernails orientation recognition system.