• 한국컴퓨터정보학회논문지
• /
• 제21권4호
• /
• pp.9-15
• /
• 2016

Symmetry is everywhere in the world around us from galaxy to microbes. From ancient times symmetry is considered to be a reflection of the harmony of universe. Symmetry is not only a significant clue for human cognitive process, but also useful information for computer vision such as image understanding system. Application areas include face detection and recognition, indexing of image database, image segmentation and detection, analysis of medical images, and so on. The technique used in this paper extracts edges, and the perpendicular bisector of any two edge points is considered to be a candidate axis of symmetry. The coefficients of candidate axis are accumulated in the coefficient space. Then the axis of symmetry is determined to be the line for which the coefficient histogram has maximum value. In this paper, an improved method is proposed that utilizes the directional information of edges, which is a byproduct of the edge detection process. Experiment on 20 test images shows that the proposed method performs 22.7 times faster than the original method. In another test on 5 images with 4% salt-and-pepper noise, the proposed method detects the symmetry successfully, while the original method fails. This result reveals that the proposed method enhances the speed and accuracy of detection process at the same time.

• 한국컴퓨터정보학회논문지
• /
• 제20권9호
• /
• pp.31-37
• /
• 2015

Symmetry is easily found in animals and plants as well as in artificial structures. It is useful not only for human cognitive process but also for image understanding by computer. Application areas include face detection and recognition, indexing of image database, image segmentation and detection, and analysis of medical images. The method used in this paper extracts edges, and the perpendicular bisector of any pair of selected edge points is considered to be a candidate axis of symmetry. The coefficients of the perpendicular bisectors are accumulated in the coefficient space. Axis of symmetry is determined to be the line for which the histogram has maximum value. This method shows good results, but the usefulness of the method is restricted because the amount of computation increases proportional to the square of the number of edges. In this paper, an acceleration method is proposed which performs $2^{2n}$ times faster than the original one. Experiment on 20 test images shows that the proposed method using level-3 image segmentation performs 63.9 times faster than the original method.

• 대한전자공학회논문지SP
• /
• 제38권4호
• /
• pp.411-421
• /
• 2001

일반화 대칭 변환 (generalized symmetry transform, GST)은 주어진 영상에서 사전 분할이 없이 국부성과 반사 대칭성을 결합하여 대칭을 측정하고 관심 영역을 추출한다. GST의 거리 가중치 함수에서 국부적인 대칭성이 반영되며 이 함수의 표준 편차 u에 의해 GST의 수행 범위가 조절된다. 넓은 관심영역을 추출하기 위해 반지름 r이 큰 검색영역 내에서의 대칭성이 추출될 필요가 있다. 이에 따라서 GST의 수행시간은 r에 따라 2차적으로 증가하게 된 본 논문에서는 이를 개선하기 위해 선택적 방향 주의를 가지는 수정된 스캔라인 GST를 제안한다. 제안된 GST는 기존의 GST와 유사한 대칭 특성을 추출하지만 선택적 방향의 기울기만을 고려한 스캔라인 위의 에지 화소쌍에서 GST를 수행함으로써 r에 따라서 이의 수행시간이 선형적으로 증가된다 특히 r이 큰 경우에 선택적 방향에 대해서만 적용하면 기존의 GST의 계산량이 비대해지는 단점을 보완해 줄 수 있다. 제안된 GST가 기존의 GST보다 시간적으로 효과적이며 유용하다는 것이 여러 종류의 영상에 대한 실험으로 확인되었다.