【正文】 最后，在與國家的最先進的一些方法相比，我們的FLBP方法所能達到的眼科中心的定位精度最高。新LRBT方法有助于與其他特征像素提取方法相比提高了FLBP眼檢測性能。特別是，首先，F(xiàn)LBP方法顯著于LBP方法提高了在這兩個眼檢測率和眼中心定位精度方面。該FLBP可以在鄰域，與其他鄰居像素點比較。基于距離矢量場和FLBP參數(shù)，可以形成給定圖像的FLBP特征值。這個特征是由廣義的，例如，邊緣，Gabor小波特征，色彩特征，等。proposed a method for detecting eye and mouth using distance vector field. Recently, Chen and Liu[33]and[34],proposed an approach that uses a morphological method for extracting an eye strip, where the iris is located through template matching by means of an adaptive half circle template.The photometric appearancebased approaches usually collect a large amount of training data representing the eyes of different subjects, with different face orientations and under different illumination conditions. A classifier or regression model is then constructed for eye detection. The Eigen analysis has been applied in eye detectionfirst extract the intensity valleys as the potential eyeanalog segments. A pair of eyeanalog segments is then detected as eyes if its placement is most consistent with the anthropological characteristic of human eyes. Khosravi and Safabakhshandproposed a method for locating the iris of an eye using both intensity and edge information. Other methodss sclera, and a Gaussian filter for detecting the dark circle of the iris. The nonlinear filter is used to detect the left and right corners of an eye in a color image. Kawaguchi and Rizon[28]proposed a method that extracts the center point between the two eyes. Based on the observation that the betweeneye area is dark on its left and right (eyes and eyebrows) and bright on the upper side (forehead) and the lower side (nose bridge), they proposed a circlefrequency filter to locate the candidate points. Sirohey et al.[27]and Kawato and Tetsutaniextended the VPF to a generalized projection function (GPF). Their experiments show that the hybrid projection function, which is a special case of GPF, is better than VPF, while VPF is better than the integral projection function. Kawato and Ohyadescribed an eye model that consists of six landmarks corresponding to the eye corner points, which are located based on a variance projection function or VPF. Zhou and Gengand[21].The mon features in the distinctive featurebased approaches include edge, intensity of iris, as well as color distribution. Feng and Yuen[20][19][18]introduced Local Ternary Patterns (LTP), for face recognition. Liu and Liuintroduced Local Quantized Patterns (LQP), a generalization that uses lookuptable based vector quantization to code larger or deeper patterns. Tan and Triggsproposed a highorder local pattern descriptor, Local Derivative Pattern (LDP), for face recognition. Hussain and Triggsface recognition. In particular, a face image is divided into several regions where the LBP feature distributions are extracted and concatenated to form an enhanced feature vector, which serves as a face descriptor. Zhang and Gao[13][12]pattern recognitionLBP (iii) the FLBP method displays superior representational power and flexibility to the LBP method due to the introduction of feature pixels as well as its parameters。Section ). The contributions of the paper are as follows:?A new FLBP method is presented. The FLBP encodes both local and feature information. In contrast to the original LBP that only pares a pixel with the pixels in its own neighborhood, the FLBP can pare a pixel with the pixels in its own neighborhood as well as in other neighborhoods. The FLBP generalize the LBP which can be considered as a special case of the FLBP. The FLBP is expected to perform better than the LBP approach for texture description and pattern recognition.?As the FLBP method encodes both local and feature information, the performance of FLBP depends on the extraction of the feature pixels. To improve FLBP performance, we present a new feature pixel extraction method, the LBP with Relative Bias Thresholding (LRBT) method.?For the application of FLBP on eye detection, experimental results using the BioID and FERET databases show that: (i) the FLBP method significantly improves upon the LBP method in terms of both eye detection rate and eye center localization accuracy。and[9],[7], the color features[6]pattern recognitionproposed a method that applies two relationships: “l(fā)ess than or equal to” or “greater than” that are represented by two possible values: 0 or 1. The method thus reduces the total number of texture units from 6561 to 256, which can be represented by eight binary numbers. The two relationship version of texture units is named as Local Binary Patterns or LBPand Gong et al.introduced the concept of texture unit and texture spectrum. A texture unit of a pixel is represented by eight elements, which correspond to the eight neighbors in a 33 neighborhood with three possible values: 0, 1, 2. The three values represent three possible relationships between the center pixel and its neighbors: “l(fā)ess than”, “equal to”, or “greater than”. As a result, there are 38=6561 possible texture units in total. A texture spectrum of a region is defined by the histogram of the texture units over the region. The large number of possible texture units, however, poses a putational challenge. To reduce the putational burden, Ojala et al.[3]. At an earlier stage for texture analysis, Wang and He[2] The LBP with Relative Bias Thresholding (LRBT)1. IntroductionThe Local Binary Patterns (LBP) method, which defines a grayscale invariant texture description by paring a center pixel with its neighbors, is a popular method for texture analysis Eye detection。 Feature Local Binary Pattern (FLBP)。that only pares a pixel with the pixels in its own neighborhood。參考文獻 [1] E. Newham. The Biometric Report[R]. SJB Services, New York, 1995.[2] Biometrics Market and Industry Report 20072012[R]. International Biometric Group, 2007.[3] H. Chan and . A manmachine facial recognition system: some prel