Facial Data Field

Expressional face recognition is a challenge in computer vision for complex expressions. Facial data field is proposed to recognize expression. Fundamentals are presented in the methodology of face recognition upon data field and subsequently, technical algorithms including normalizing faces, generating facial data field, extracting feature points in partitions, assigning weights and recognizing faces. A case is studied with JAFFE database for its verification. Result indicates that the proposed method is suitable and effective in expressional face recognition considering the whole average recognition rate is up to 94.3%. In conclusion, data field is considered as a valuable alternative to pattern recognition.

Ҳали таржима қилинмаган