Journal of the Korea Computer Graphics Society (한국컴퓨터그래픽스학회논문지)

Korea Computer Graphics Society (한국컴퓨터그래픽스학회)
권호 표지

Person Identification based on Clothing Feature

의상 특징 기반의 동일인 식별

  • Choi, Yoo-Joo (Dept. of Newmedia, Korean German Institute of Technology) ;
  • Park, Sun-Mi (School of EECS, Kyungpook National University Division of Electrical) ;
  • Cho, We-Duke (Division of Electrical & Computer Engineering, Ajou University) ;
  • Kim, Ku-Jin (Dept. of Computer Engineering, Kyungpook National University)
  • 최유주 (한독미디어대학원대학교 뉴미디어학부) ;
  • 박선미 (경북대학교 전자전기컴퓨터학부) ;
  • 조위덕 (아주대학교 전자공학부) ;
  • 김구진 (경북대학교 컴퓨터공학과)
  • Received : 2009.08.06
  • Accepted : 2010.02.09
  • Published : 2010.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

With the widespread use of vision-based surveillance systems, the capability for person identification is now an essential component. However, the CCTV cameras used in surveillance systems tend to produce relatively low-resolution images, making it difficult to use face recognition techniques for person identification. Therefore, an algorithm is proposed for person identification in CCTV camera images based on the clothing. Whenever a person is authenticated at the main entrance of a building, the clothing feature of that person is extracted and added to the database. Using a given image, the clothing area is detected using background subtraction and skin color detection techniques. The clothing feature vector is then composed of textural and color features of the clothing region, where the textural feature is extracted based on a local edge histogram, while the color feature is extracted using octree-based quantization of a color map. When given a query image, the person can then be identified by finding the most similar clothing feature from the database, where the Euclidean distance is used as the similarity measure. Experimental results show an 80% success rate for person identification with the proposed algorithm, and only a 43% success rate when using face recognition.

비전 기반의 감시 시스템에서 동일인의 식별은 매우 중요하다. 감시 시스템에서 주로 사용되는 CCTV 카메라의 영상은 상대적으로 낮은 해상도를 가지므로 얼굴 인식 기법을 이용하여 동일인을 식별하기는 어렵다. 본 논문에서는 CCTV 카메라 영상에서 의상 특징을 이용하여 동일인을 식별하는 알고리즘을 제안한다. 건물의 주출입구에서 출입자가 인증을 받을 때, 의상 특징이 데이터베이스에 저장된다. 그 후, 건물 내에서 촬영한 영상에 대해 배경 차감 및 피부색 발견 기법을 이용하여 의상 영역을 발견한다. 의상의 특징 벡터는 텍스처와 색상 특징을 이용하여 구성한다. 텍스처 특징은 지역적 에지 히스토그램을 이용하여 추출된다. 색상 특징은 색상 지도의 옥트리 기반 양자화(octree-based quantization)를 이용하여 추출된다. 건물 내의 촬영 영상이 주어질 때, 데이터베이스에서 의상 특징이 가장 유사한 사람을 발견함으로써 동일인을 식별하며, 의상 특징 벡터 간의 유사도 측정을 위해서는 유클리디안 거리(Euclidean distance)를 사용한다. 실험 결과, 얼굴인식 기법이 최대 43%의 성공률을 보인 데 비해, 의상 특징을 이용하여 80%의 성공률로 동일인을 식별하였다.

Keywords

References

  1. D. Anguelov, K. Lec, S. B. Gokturk and B. Sumengen, "Contextual Identity Recognition in Personal Photo Albums," In Proc. of IEEE CVPR, pp. 1-7, 2007.
  2. Y. J. Choi, K. J. Kim and W. D. Cho. "Grid-based Approach for Detecting Head and Hand Regions," In Proc. of ICIC 2007, CClS 2. pp. 1126-1132, 2007.
  3. Y. Freund and R. E. Schapire. "Decision-theoretic Generalization of Online Learning and an Application to Boosting, " In Computational Learning Theory: Eurocolt'95, pp. 23-37, 1995.
  4. M. Gervautz and W. Purgathofer. "A Simple Method for Color Quantization: Octree Quantization," Graphics Gems, Morgan Kaufmann, 1990.
  5. A, Gorras, F. Tous, J. Llads and M. Vanrell. "High-level Clothes Description Based on Color-texture and Structural Features," Lecture Notes in Computer Science, 2652, pp. 108-116, 2003
  6. X. Hongli, X. De and G. Yong. "Region-based Image Retrieval Using Color Coherence Region Vectors," In Proc. of the 7th International Conference on Signal Processing, pp. 761-764, 2004.
  7. K. J. Kim, S. M. Park and Y. J. Choi, "Clothing Identification Based on Edge Information," In Proc. of APSCC, IEEE Asia-Pacific Services Computing Conference, pp.876-880, 2008.
  8. N. W. Kim, T. Y. Kim and J. S. Choi. "Edge-based Spatial Descriptor for Content-based Image Retrieval," Lecture Notes in Computer Science, 3568, pp. 454-464, 2005.
  9. M. S. Lew, N. Sebe, C. Djeraba and R. Jain. "Content-based Multimedia Information Retrieval: State of the Art and Challenges," ACM Transactions on Multimedia Computing, Communications & Applications, 2(1), pp. 1-19,2006. https://doi.org/10.1145/1126004.1126005
  10. D. Ramanan, D. A, Forsyth and A, Zisserman. 'Tracking People by Learning Their Appearance," IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(1), pp. 65-81, 2007. https://doi.org/10.1109/TPAMI.2007.250600
  11. M. J. Swain and D. H. Ballard. "Color Indexing," International Journal of Computer Vision, 7(1), pp. 11-32, 1991. https://doi.org/10.1007/BF00130487
  12. F. Tous, A. Borras, R. Benavente, R. Baldrich, M. Vanrel and J. Llads. "Textual Descriptors for Browsing People by Visual Appearance," Lecture Notes in Computer Science, 2504, pp. 419-429, 2002.
  13. J. Z. Wang, J. Li and G. Wiederhold. "Simplicity: Semantics-sensitive Integrated Matching for Picture Libraries," IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(9), pp. 947-963, 2001. https://doi.org/10.1109/34.955109
  14. J. Yang, D. Zhang, A. F. Frangi and J. Y. Yang, 'Two-Dimensional PCA:A New Approach to Appearance-Based Face Representation and Recognition," IEEE Trans. on PAMl, 26(1), pp. 131-137,2004. https://doi.org/10.1109/TPAMI.2004.1261097
  15. W. Zhao, R. Chellappa, P. j. Phillips and A. Rosenfeld. "Face Recognition: A Literature Survey," ACM Computing Survey, 35(4), pp. 399-458, 2003. https://doi.org/10.1145/954339.954342
  16. S. Zhou, V. Krueger and R. Chellappa. "Probabilistic Recognition of Human Faces from Video," Computer Vision and Image Understanding, 91(1-2), pp. 214-245, 2003. https://doi.org/10.1016/S1077-3142(03)00080-8