【正文】 過不斷地查找資料后總結(jié)，我們都很好的按老師的要求完成了畢業(yè)論文的寫作，這種收獲的喜悅相信每個(gè)人都能夠體會(huì)到。 在這次畢業(yè)論文中同學(xué)之間互相幫助，共同商量相關(guān)專業(yè)問題,這種交流對(duì)于即將面臨畢業(yè)的我們來說是一次很有意義的經(jīng)歷,大學(xué)四年都一起走過了,在最后我們可以聚在一起討論學(xué)習(xí),研究專業(yè)問題,進(jìn)而更好的了解我們每個(gè)人的興趣之所在,明確我們的人生理想,進(jìn)而在今后的生活和工作中更好的發(fā)揮自己的優(yōu)勢(shì),學(xué)好自己的專業(yè),成為一個(gè)對(duì)于社會(huì)有用的人. 在此更要感謝我的專業(yè)老師，是你們的細(xì)心指導(dǎo)和關(guān)懷，使我能夠順利的完成畢業(yè)論文。老師的檢查總是很仔細(xì)的，可以認(rèn)真的看論文的每一個(gè)細(xì)小的格式要求，認(rèn)真的讀每一個(gè)同學(xué)的論文，然后提出最中肯的意見，這是很難得的。LBP the FLBP can pare a pixel with the pixels in its own neighborhood as well as in other neighborhoods. The experimental results on eye detection using the BioID and FERET databases show the feasibility of our FLBP method. In particular, first, the FLBP method significantly improves upon the LBP method in terms of both eye detection rate and eye center localization accuracy. Second, we present a new feature pixel extraction method—the LBP with Relative Bias Thresholding (LRBT) method. The new LRBT method helps improve the FLBP eye detection performance when pared with other feature pixel extraction methods. Third, the FLBP method displays superior representational power and flexibility to the LBP method due to the introduction of the feature pixels as well as the FLBP parameters. Finally, in parison with some stateoftheart methods, our FLBP method achieves the highest accuracy of eye center localization.Keywords Local Binary Pattern (LBP)。 Distance vector。[1],and[4][1][5][1].The LBP method has been applied in manytasks. While we are inspired by the achievement of LBP, two problems occurred to us. First, LBP only pares a pixel with the pixels in its own neighborhood. We believe that more information could be revealed if we can pare a pixel with the pixels in other neighborhoods. However arbitrarily paring a pixel with any other neighborhoods might not provide useful information. Our first problem is how to locate a pixel and a neighborhood which will provide useful information after paring them each other. Second, LBPs encodes a little information about the relationship of local texture with the features, such as edges, peaks and valleys. Our second problem is how to design a texture descriptor which encodes more information of the relationship of local texture with the features. These two problems motivated us to this study. The goal of our study is to find a new texture descriptor which can solve the two problems.We present in this paper a new Feature Local Binary Patterns (FLBP) method that encodes the information of both local texture and features. The features are broadly defined by any features which meet the requirements of specific applications, such as the edges, the intensity peaks or valleys, the Gabor wavelet featuresand[8],[10][11], as well as the LBP with Relative Bias Thresholding (LRBT) features (see (ii) the new LRBT feature pixel extraction method helps improve the FLBP eye detection performance when pared with other feature pixel extraction methods。 and (iv) in parison with the state of the art methods, the FLBP method achieves the highest accuracy of eye center localization.2. BackgroundIn recent years, themethod has been applied in manytasks, such as face detection and recognition, scene and image texture classification. Many extensions of the original LBP have been proposed to improve the performance. Ahonen et al.andpresented a facial image representation based on the LBP texture features for[14][15][16][17]presented a method that fuses local LBP features, global frequency features, as well as color features for improving face recognition performance. Banerji et al.proposed novel color LBP descriptors for scene and image texture classification.Eye detection, an example of facial landmark detection, plays an important role in designing an automatic face recognition system. Eyes have some unique geometric and photometric characteristics, which provide important and reliable information for their localization. Even though a lot of research has been carried out and some progress has been reported, eye detection remains a challenging research topic due to the difficult factors caused by occlusion, closed eye, illumination variation, eye size and orientations, etc. Three major types of approaches for eye detection are templatebased, distinctive featurebased and photometric appearancebased approaches. Yuille et al.proposed a deformable template for face features, where an eye is described by a parameterized template. Specifically, an energy function is first defined to link the edges, peaks, and valleys in an image to the properties of the template. The template then interacts dynamically with the image by altering its parameter values to minimize the energy function, and by doing so deforms itself for the best fit. The method, however, is not only time consuming, but critically relies on the initial position of the template. If the initial position of the template is above the eyebrow, for example, the method fails to detect the eye. Further improvement of the method by applying some eye features in the initialization stage is reported inand[22][23][24][25][26]andpresented methods for eye detection using linear and nonlinear filters. The linear filter contains the Gabor wavelets with four orientations for detecting the edges of an eye39。[29][30][31][32][33],[35][36]. Pentland et al.extended the eigenfaces technique to the description and coding of facial features, yielding eigeneyes, eigennoses, and eigenmouths. Asteriadis et al.[37][38]presented an eye detection method using color information and wavelet features together with a new efficient Support Vector Machine (eSVM). 英文翻譯：特征的局部二元模式與眼檢測(cè)中的應(yīng)用摘要本文提出了一種新的基于紋理特征和功能的信息的特征局部二進(jìn)制模式（FLBP）方法。具體地說，二進(jìn)制圖象首先被從給定圖像中提取特征點(diǎn)導(dǎo)出，然后形成一個(gè)距離矢量場(chǎng)通過獲得數(shù)值計(jì)算在所述二進(jìn)制圖像中定義的每個(gè)像素及其最接近的特征像素之間的距離矢量。與此相反，以原來的LBP相比，在其自己的鄰域的像素的像素。使用BioID和FERET數(shù)據(jù)庫上的人眼檢測(cè)實(shí)驗(yàn)結(jié)果表明我們的FLBP方法的可行性。其次，我們提出了一個(gè)新的特征像素提取方法，用在相對(duì)偏閾值（LRBT）方法LBP。第三，F(xiàn)LBP方法由于引入??了特征的像素以及FLBP參數(shù)，表現(xiàn)出了出了優(yōu)越表達(dá)能力和靈活性的LBP方法。關(guān)鍵詞 特征局部二進(jìn)制模式；局部二進(jìn)制模式（LBP）；人眼檢測(cè)；距離矢量；相對(duì)偏差閾值的LBP何為局部二元模式（LBP）方法，該方法通過比較中心與其鄰居像素得到限定灰度不變紋理的描述值，