A Study on the Automatic Identification of HANGEUL Seal by using the Image Processing

영상처리에 의한 한글인장의 자동직별에 관한 연구

The proposed seal identification procedure consists of the smoothing, rotation, thinning, and matching techniques. The seal images which are scanned by CCTV are thresholded into the binary prctures of $256{\times}256$ pixels through A/D converter and 6502 microcomputer. After the sample and target images are ratated into an identical orientation, a thinning process is used to extract the skeletons of the character strobes. The wighted map is constructed by distance weight from which the distance weighted correlation C is computed. The C is compared with the dicision constant C or C for the purpose of seal indentification. The identification rate is 95% and the total CPU time is less than 3 minutes for each identification in the experiment.

印章識別은 平滑化, 回轉 및 移動, 細線化整合技法의 순서로 수행된다. CCTV카메라에 入力된 印章映像은 A/D變換機와 8bit microcomputer에 의하여 $256{\times}256$畵素의 2進映像으로 변환한다. 두 映像을 定位置로 回轉시킨 후, 細線化過程을 거쳐 文字의 골격선을 찾는다. 畵素거리에 따라 Weight.를 정하고 distance-weighted Correlation, C를 계산한다. 계산된 $C^K$와 결정상수 $C_YES$, $C_NO$를 비교하여 印章을 識別한 결과 95%의 높은 識別率을 얻었고 한 개의 對象印章을 識別하는데 걸린 시간은 3분 이내였다.