High Performance Object Recognition with Application of the Size and Rotational Invariant Feature of the Fourier Descriptor to the 3D Information of Edges = 푸리에 표현자의 크기와 회전 불변 특징을 에지에 대한 3 차원 정보에 응용한 고효율의 물체 인식

국문 초록 (Abstract)

3차원 정보로부터 정확한 에지를 추출하고 푸리 변환하여 물체를 인식할 수 있는 고 효율의 물체 인식방법을 제안하였다. 물체의 윤곽은 인식에 유용한 많은 정보를 포함하고 있지만, 정확한 윤곽정보를 얻기가 어려우며, 정확한 윤곽정보를 얻었다고 하더라도 물체의 크기나 방향 마다 윤곽이 달라지기 때문에 물체 인식에 획기적 대안으로 활용되지 못하고 있다. 제안한 물체 인식 알고리즘은 1) 레이저 스캔 디바이스를 사용하여 얻는 3 차원 물체정보로부터 정밀한 물체 윤곽을 획득하고 2) 크기 및 회전 불변한 푸리에 표시 자를 이용하여 윤곽을 표현함으로써, 필요 데이터 베이스의 크기를 대폭 줄인다. 이렇게 얻어진 물체에 대한 푸리에 표식자 정보는 미리 준비된 푸리에 표식자 데이터 베이스로부터 최적 정합되는 물체를 찾아 인식한다. 이 알고리즘은 MPEG7 Part B의 방대한 영상 데이터 베이스를 대상으로 실험하였으며, 그에 대한 결과를 논문에 포함시켰다.

다국어 초록 (Multilingual Abstract)

A high performance object recognition algorithm using Fourier description of the 3D information of the objects is proposed. Object boundaries contain sufficient information for recognition in most of objects. Howeveer, it is not well utilized as the key solution of the object recognition since obtaining the accurate boundary information is not easy. Also, object boundaries vary highly depending on the size or orientation of object. The proposed object recognition algorithm is based on 1) the accurate object boundaries extracted from the 3D shape which is obtained by the laser scan device, and 2) reduction of the required database using the size and rotational invariant feature of the Fourier Descriptor. Such Fourier information is compared with the database and the recognition is done by selecting the best matching object. The experiments have been done on the rich database of MPEG 7 Part B.

목차 (Table of Contents)

• 요약
• Abstract
• Ⅰ. Introduction
• Ⅱ. Relevant Technologies
• Ⅲ. Proposed Depth-based Shape Retrieval
• Ⅳ. Experimental Results
• Ⅴ. Conclusions
• References
• 저자소개

참고문헌 (Reference)

1 W. Niblack, "The QBIC project: querying image by content using color, texture and shape" 173-187, 1993

2 K. L. Kashyap, "Stochastic models for closed boundary analysis: representation and reconstruction" 27 : 627-637, 1981

3 Eric Persoon, "Shape Discrimination Using Fourier Descriptors" 170-179, 1977

4 Q.M. Tieng, "Recognition of 2D object contours using the wavelet transform zero-crossing representation" 19 : 1997

5 Quang Minh Tieng, "Recognition of 2D Object Contours Using the Wavelet Transform Zero-Crossing Representation" 19 (19): 1997

6 Hee Soo Yang, "Recognition of 2D Object Contours Using Starting-Point-Independent Wavelet Coefficient Matching" 9 (9): 171-181, 1998

7 Kindratenko V.V, "On Using Functions to Describe the Shape" 18 (18): 225-245, 2003

8 E.R. Davies, "Machine Vision : Theory, Algorithms, Practicalities" Academic Press 1997

9 B. Dorner, "Hand Shape Identification and Tracking for Sign Language Interpretation" 1993

10 C.T. Zahn, "Fourier descriptors for plane closed curves" c-21 : 269-281, 1972

11 Charles T. Zahn, "Fourier Descriptors for Plane closed Curves" 21 : 269-281, 1972

12 I. Kunttu, "Efficient Fourier shape descriptor for industrial defect images using wavelets" 44 : 2005

13 김형석, "Distance Measurement Using a Single Camera with a Rotating Mirror" 제어ㆍ로봇ㆍ시스템학회 3 (3): 542-551, 2005

14 Hannu Kauppinen, "An Experimental Comparison of Autoregressive and Fourier-Based Descriptors in 2D Shape Classification" 17 (17): 201-207, 1995

15 W.Y.Kim and Y, "A region-based shape descriptor using Zernike moments" 16 : 95-102`, 2000

16 Atul Sajjanhar, "A Technique for Similarity Retrieval of Shapes" Monash University 1997

17 Bin Wang, "A Novel Fourier Descriptor for Shape Retrieval" 4223 : 822-825, 2006

18 Hyongsuk Kim, "A Depth Measurement System with the Active Vision of the Striped Lighting and Rotating Mirror" 108-115, 2004

19 P.J. van Otterloo, "A Contour-Oriented Approach to Shape Analysis" Prentice-Hall International Ltd 1991

20 Chung-Lin Huang, "A Content-based image retrieval system" 16 (16): 149-163, 1998