人類與生具備著許多種生活的能力,辨識與偵測人臉是視覺能力的一部份。近幾年來關於人臉應用的相關研究不斷的被提出來,例如犯罪判定及安全監控,但這些技術卻遲遲不能達到普及化的應用,其中一很重要的因素是,沒有一有效方法能夠精準的定位出在複雜環境下人臉的位置,因此,就算是辨識率再高,若不能先精準的偵測出人臉的位置,這些應用也都只能紙上談兵。 本研究以類神經網路系統中的「倒傳遞類神經網路」做為人臉偵測的模式,而最佳化類神經網路架構之特徵決定實際上是有點難度的,因為人臉特徵的組合方式是相當多元的,該如何在最有效率的時間裡決定最佳化人臉特徵是值得研究的主題,於是本論文採用「基因演算法」來進行快速地搜尋,期望能在最短的時間將可能的組合方式都運算過,以期搜尋出適合的類神經網路架構的人臉特徵。最後再經由人臉膚色予以再確認,以提升偵測正確率。經由實驗結果顯示所提方法確有相當不錯的效能。
Human face represents one of the most common patterns in our vision. Therefore, automatic recognition of human faces is an essential task in many applications such as criminal identification and security checks. The first important step of automatic human face recognition is to detect face in a given unknown picture. However, the task of automatic face detection in a complex background is difficult to cope with. In this thesis, discriminating features are selected by genetic algorithm with neural network so as to design an accurate face detector. Moreover, verification on face skin has been involved to increase the accuracy of face detection. Experimental results prove the effectiveness of the proposed text detection method.