The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Download
Citation
Articles | Volume XL-5/W6
https://doi.org/10.5194/isprsarchives-XL-5-W6-107-2015
https://doi.org/10.5194/isprsarchives-XL-5-W6-107-2015
18 May 2015
 | 18 May 2015

FACIAL FEATURES DETECTION USING TEXTURE HOUGH TRANSFORM

V. S. Gorbatsevich

Keywords: Local Binary Pattern, Object detection, facial features detection, Hough transform

Abstract. The paper presents an original method for object detection. The “texture” Hough transform is used as the main tool in the search. Unlike classical generalized Hough transform, this variation uses texture LBP descriptor as a primitive for voting. The voting weight of each primitive is assumed by learning at a training set. This paper gives an overview of an original method for weights learning, and a number of ways to get the maximum searching algorithm speed on practice.