얼굴인식기술은 컴퓨터비전 분야에서 중요한 역할을 담당하고 있다. 본 논문에서는, PCA와 SVM 기술을 사용하는 빠른 얼굴인식기술을 제안한다. 제안한 시스템에서는, 먼저 지역 히스토그램 분포를 분석하여 생성한 통계적 특성을 사용함으로써 얼굴가능영역을 필터링한다. 이 과정에서 대부분의 비얼굴 영역이 제거되기 때문에 탐지 과정의 처리속도가 향상된다. 다음으로는 PCA 특징 벡터가 생성되고, SVM 분류기를 사용하여 테스트 영상 내에 얼굴이 존재하는지를 탐지한다. 본 논문에서의 테스트 영상은 CMU 얼굴 데이터베이스를 사용하였으며, SVM의 학습을 위한 얼굴과 비얼굴 샘플들은 MIT 데이터 세트로부터 선택하였다. 얼굴탐지 실험결과, 제안한 방법에서 좋은 성능을 나타내었다.
얼굴인식기술은 컴퓨터비전 분야에서 중요한 역할을 담당하고 있다. 본 논문에서는, PCA와 SVM 기술을 사용하는 빠른 얼굴인식기술을 제안한다. 제안한 시스템에서는, 먼저 지역 히스토그램 분포를 분석하여 생성한 통계적 특성을 사용함으로써 얼굴가능영역을 필터링한다. 이 과정에서 대부분의 비얼굴 영역이 제거되기 때문에 탐지 과정의 처리속도가 향상된다. 다음으로는 PCA 특징 벡터가 생성되고, SVM 분류기를 사용하여 테스트 영상 내에 얼굴이 존재하는지를 탐지한다. 본 논문에서의 테스트 영상은 CMU 얼굴 데이터베이스를 사용하였으며, SVM의 학습을 위한 얼굴과 비얼굴 샘플들은 MIT 데이터 세트로부터 선택하였다. 얼굴탐지 실험결과, 제안한 방법에서 좋은 성능을 나타내었다.
Human face detection technique plays an important role in computer vision area. It has lots of applications such as face recognition, video surveillance, human computer interface, face image database management, and querying image databases. In this paper, a fast face detection approach using Princi...
Human face detection technique plays an important role in computer vision area. It has lots of applications such as face recognition, video surveillance, human computer interface, face image database management, and querying image databases. In this paper, a fast face detection approach using Principal Component Analysis (PCA) and Support Vector Machines (SVM) is proposed based on the previous study on face detection technique. In the proposed detection system, firstly it filter the face potential area using statistical feature which is generated by analyzing the local histogram distribution the detection process is speeded up by eliminating most of the non-face area in this step. In the next step, PCA feature vectors are generated, and then detect whether there are faces present in the test image using SVM classifier. Finally, store the detection results and output the results on the test image. The test images in this paper are from CMU face database. The face and non-face samples are selected from the MIT data set. The experimental results indicate the proposed method has good performance for face detection.
Human face detection technique plays an important role in computer vision area. It has lots of applications such as face recognition, video surveillance, human computer interface, face image database management, and querying image databases. In this paper, a fast face detection approach using Principal Component Analysis (PCA) and Support Vector Machines (SVM) is proposed based on the previous study on face detection technique. In the proposed detection system, firstly it filter the face potential area using statistical feature which is generated by analyzing the local histogram distribution the detection process is speeded up by eliminating most of the non-face area in this step. In the next step, PCA feature vectors are generated, and then detect whether there are faces present in the test image using SVM classifier. Finally, store the detection results and output the results on the test image. The test images in this paper are from CMU face database. The face and non-face samples are selected from the MIT data set. The experimental results indicate the proposed method has good performance for face detection.
* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.
제안 방법
In this paper, we propose a method for eliminating most of the non-face area in gray images, that it can save more detecting time and reduce the misclassification ratio. Face area has different statistical character with most of the non-face area.
This paper proposed a fast face detection method based on PCA and SVM. Combining PCA and SVM has high performance in face detection task In addition, the proposed method filters the face potential areas to save the detecting time and reduce the wrong detection results.
PCA and SVM. Combining PCA and SVM has high performance in face detection task In addition, the proposed method filters the face potential areas to save the detecting time and reduce the wrong detection results. It can be seen from the results, most of the non-face areas have been eliminated.
성능/효과
Obviously, the proposed method works faster than the face detection that only combined PCA and SVM. The experimental results indicated a high detection ratio and low misclassified ratio. In the future works, the performance of classifier and the face potential area selection method are also could be improved.
참고문헌 (8)
Ming-Hsuan Yang, David J. Kriegman, Narendra Ahuja 'Detecting Faces in Images: A Survey', IEEE Transactions on Pattern Analysis and Machine Intelligence, Jan. 2002
Clyde Shavers, Robert Li, Gary Lebby 'An SVM-based Approach to Face Detection', Proceedings of the 38th Southeastern Symposium on System Theory Tennessee Technological University, Mar. 2006
Lindsay I Smith 'A tutorial on Principal Components Analysis', http://www.cs.otago.ac.nz/cosc453/student_tutorials/principal_components.pdf, Feb. 2002
E. Osuna, R. Freund, F. Girosi 'Training Support Vector Machines: An Application to Face Detection,' Proceedings IEEE Conference Computer Vision and Pattern Recognition, 1997
Christopher J.C. Burges, A Tutorial on Support Vector Machines for Pattern Recognition, 1998
B. Heisele, T. Poggio, Massimiliano Pontil 'Face Detection in Still Gray Images', AI Memo 1687, Massachusetts Institute of Technology, 2000
Rafael C. Gonzalez, Richard E. Woods 'Digital Image Processing (Second Edition)', Prentice Hall, 2002
C. Papageorgiou, T. Poggio 'A Trainable System for Object Detection', International Journal of Computer Vision, Volume 38, Issue 1, Jun. 2000
이 논문을 인용한 문헌
저자의 다른 논문 :
활용도 분석정보
상세보기
다운로드
내보내기
활용도 Top5 논문
해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다. 더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.