即時人臉辨識在KIOSK上之應用

Real-Time Face Identification for KIOSK Application

廖威傑(Wei-Jie Liao)

指導教授 ： 林道通

國立臺北大學/電機資訊學院/資通科技產業碩士專班/碩士(2014年)

摘要

本文使用了一套基於資料分群概念的系統SVM訓練來做人臉辨識系統。辨識人臉首先必須先偵測到人臉影像，利用一種迭代演算法AdaBoost來偵測眼睛，得到眼睛中心坐標後，將兩眼坐標帶入設計好的橢圓遮罩去切割出人臉部位，由於原圖的五官對比不夠明顯，為了增加人臉五官的對比強度，使用了Retinex這個演算法，過去此演算法常用於數位相機自動白平衡中，它除了具有色彩恆常性，亦包含了強化影像的效果，對於光線對影像所造成的影響，具有良好的處理效果，接著就是使用擷取可辨識的臉部特徵，我們使用對紋理特徵有良好效果的LBP 特徵，只在灰階上的運算， 速度較快可應用於即時系統上，最後使用SVM 分類器去訓練LBP所擷取的特徵來做辨識。

關鍵字

人臉辨識、支持向量機

並列摘要

Face identification for security systems has become an important research subject. This thesis proposes a face identification system for application in area access control systems. Support vector machine (SVM) was employed to conduct face identification based on a data clustering method. Initially, the face was detected using the AdaBoost algorithm. An elliptical mask was then used to remove the non-face area of the image. If the contrast was insufficient to produce a full-featured image of the face, the image was enhanced using the Retinex algorithm. This algorithm corrects lighting condition and maintains color constancy. A local binary pattern (LBP) was used to capture the facial features because it positively affects the characteristics of the texture. Employing an LBP is simple and fast; therefore it can be appropriately applied in real-time systems. An SVM classifier was used to train LBP features to accomplish identification. The proposed system is proven to be applicable for access control with satisfactory correct identification accuracy.

並列關鍵字

face identification、retinex、support vecator machine、local binary pattern

參考文獻

[1] Karl Pearson. Liii. on lines and planes of closest fit to systems of points in space. The

559–572, 1901.

[2] Ronald A Fisher. The use of multiple measurements in taxonomic problems. Annals of

eugenics, 7(2):179–188, 1936.

[3] AS Tolba, AH El-Baz, and AA El-Harby. Face recognition: A literature review. International