상세정보
학술지
Facial Feature Extraction Based on Private Energy Map in DCT Domain
- 발행일
- 200704
- 출처
- ETRI Journal, v.29 no.2, pp.243-245
- ISSN
- 1225-6463
- 출판사
- 한국전자통신연구원 (ETRI)
- 협약과제
- 06MK1500, 고인식 다중생체인식 전용칩셋 기술, 정교일
- 초록
- This letter presents a new feature extraction method based on the private energy map (PEM) technique to utilize the energy characteristics of a facial image. Compared with a non-facial image, a facial image shows large energy congestion in special regions of discrete cosine transform (DCT) coefficients. The PEM is generated by energy probability of the DCT coefficients of facial images. In experiments, higher face recognition performance figures of 100% for the ORL database and 98.8% for the ETRI database have been achieved.
- KSP 제안 키워드
- DCT coefficients, DCT domain, Discrete cosine Transform, Energy congestion, Energy map, Energy probability, Facial image, ORL database, Special regions, energy characteristics, face recognition