Housdorff Distance 와 Hough Transform을 적용한 얼굴인식시스템의 분석

An Analysis on Face Recognition system of Housdorff Distance and Hough Transform

본 연구에서는 얼굴 영상을 캡쳐하여 전 처리한 후 얼굴영역을 분리하고, 분리된 얼굴 영역에서 미분 연산자와 최소 형태를 세선화하여 특징을 추출하였다. Hough Transform은 $r-\theta$ 평면에서 직선의 기울기와 절편으로 변환되며, 반면 Housdorff distance는 세선화된 영상에서 선분을 추출하여 길이, 회전, 천이 특징을 추출하였다. 사람마다 다른 특징들을 추출하여 Housdorff distance과 Hough Transform에 관하여 비교분석 결과 Hough변환의 복잡도가 더 적은 것으로 판단되었다. 인식율은 Housdorff Distance를 이용한 인식율이 Hough Transformation에 비해 조금 높게 나타났다.

In this paper, captured face-image was pre-processing, segmentation, and extracting features from thinning by differential operator and minute-delineation. A straight line in slope-intercept form was transformed at the $r-\theta$ domain using Hough Transform, instead of Housdorff distance are extract feature as length, rotation, displacement of lines from thinning line components by differentiation. This research proposed a new approach compare with Hough Transformation and Housdorff Distance for face recognition so that Hough transform is simple and fast processing of face recognition than processing by Housdorff Distance. Rcognition accuracy rate is that Housdorff method is higher than Hough transformation's method.