عنوان مقاله
الگوهای دودویی محلی و کاربردش در تحلیل تصویر چهره: بررسی
فهرست مطالب
مقدمه
الگوهای دودویی محلی
تغییرات اخیر الگوی دودویی محلی
انتخاب ویژگی بر مبنای الگوی دودویی محلی
تحلیل تصویر چهره مبتنی بر الگوی دودویی محلی
ملاحظات پایانی
بخشی از مقاله
تحلیل تصویر چهره مبتنی بر الگوی دودویی محلی
شناسایی چهره مبتنی برماشین شامل دو بعد حساس یعنی نمایش چهره و طراحی رده بند یا طبقه بند می باشد. نمایش چهره از نیل به مجموعه ویژگیهای وابسته از تصاویر اصلی برای وصف چهره ها به منظور تسهیل روند شناسایی موثر مبتنی بر ماشین تشکیل می شود.
کلمات کلیدی:
Local Binary Patterns and Its Application to Facial Image Analysis: A Survey Di Huang, Student Member, IEEE, Caifeng Shan, Member, IEEE, Mohsen Ardabilian, Yunhong Wang, Member, IEEE, and Liming Chen, Member, IEEE Abstract—Local binary pattern (LBP) is a nonparametric descriptor, which efficiently summarizes the local structures of images. In recent years, it has aroused increasing interest in many areas of image processing and computer vision and has shown its effectiveness in a number of applications, in particular for facial image analysis, including tasks as diverse as face detection, face recognition, facial expression analysis, and demographic classification. This paper presents a comprehensive survey of LBP methodology, including several more recent variations. As a typical application of the LBP approach, LBP-based facial image analysis is extensively reviewed, while its successful extensions, which deal with various tasks of facial image analysis, are also highlighted. Index Terms—Face detection, face recognition, facial expression analysis, local binary patterns (LBPs), local features. I. INTRODUCTION DURING the past few years, local binary patterns (LBPs) [1] have aroused increasing interest in image processing and computer vision. As a nonparametric method, LBP summarizes local structures of images efficiently by comparing each pixel with its neighboring pixels. The most important properties of LBP are its tolerance regarding monotonic illumination changes and its computational simplicity. LBP was originally proposed for texture analysis [2], and has proved a simple yet powerful approach to describe local structures. It has been extensively exploited in many applications, for instance, face image analysis [3], [4], image and video retrieval [5], [6], environment modeling [7], [8], visual inspection [9], [10], motion analysis [11], [12], biomedical and aerial image analysis [13], [14], and remote sensing [15] (see a comprehensive bibliography of LBP methodology online [16]). LBP-based facial image analysis has been one of the most popular and successful applications in recent years. Facial image analysis is an active research topic in computer vision, with Manuscript received May 12, 2010; revised November 24, 2010; accepted February 7, 2011. Date of publication March 28, 2011; date of current version October 19, 2011. This work was supported in part by the French Research Agency (ANR) project ANR Face Analysis and Recognition using 3D under Grant ANR-07-SESU-004–03. This paper was recommended by Associate Editor X. Li. D. Huang, M. Ardabilian, and L. Chen are with the Universite de Lyon, Lab- ´ oratoire d’InfoRmatique en Image et Systemes d’information, Centre National ` de Recherche Scientifique 5205, Ecole Centrale de Lyon, 69134 Lyon, France (e-mail: di.huang@ec-lyon.fr). C. Shan is with the Philips Research, 5656 AE Eindhoven, The Netherlands (e-mail: caifeng.shan@philips.com). Y. Wang is with Beijing Key Laboratory of Digital Media, State Key Laboratory of Virtual Reality Technology and Systems, and School of Computer Science and Engineering, Beihang University, 100191, Beijing, China. Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org. Digital Object Identifier 10.1109/TSMCC.2011.2118750 a wide range of important applications, e.g., human–computer interaction, biometric identification, surveillance and security, and computer animation. LBP has been exploited for facial representation in different tasks, which include face detection [4], [17]–[19], face recognition [20]–[26], facial expression analysis [27]–[31], demographic (gender, race, age, etc.) classification [32], [33], and other related applications [34], [35]. The development of LBP methodology can be well illustrated in facial image analysis, and most of its recent variations are proposed in this area. Some brief surveys on image analysis [36] or face analysis [37]–[39], which use LBP, were given, but all these studies discussed limited papers of the literature, and many new related methods have appeared in more recent years. In this paper, we present a comprehensive survey of the LBP methodology, including its recent variations and LBP-based feature selection, as well as the application to facial image analysis. To the best of our knowledge, this paper is the first survey that extensively reviews LBP methodology and its application to facial image analysis, with more than 100 related reviewed literatures. The remainder of this paper is organized as follows. The LBP methodology is introduced in Section II. Section III presents the recent variations of LBP. LBP-based feature-selection methods are discussed in Section IV. Section V describes different facets of its applications on facial image analysis. Finally, Section VI concludes the paper. II. LOCAL BINARY PATTERNS The original LBP operator labels the pixels of an image with decimal numbers, which are called LBPs or LBP codes that encode the local structure around each pixel. It proceeds thus, as illustrated in Fig. 1: Each pixel is compared with its eight neighbors in a 3 × 3 neighborhood by subtracting the center pixel value; the resulting strictly negative values are encoded with 0, and the others with 1. For each given pixel, a binary number is obtained by concatenating all these binary values in a clockwise direction, which starts from the one of its top-left neighbor. The corresponding decimal value of the generated binary number is then used for labeling the given pixel. The derived binary numbers are referred to be the LBPs or LBP codes. One limitation of the basic LBP operator is that its small 3 × 3 neighborhood cannot capture dominant features with large-scale structures. To deal with the texture at different scales, the operator was later generalized to use neighborhoods of different sizes [1]. A local neighborhood is defined as a set of sampling points evenly spaced on a circle, which is centered at the pixel to be labeled, and the sampling points that do not fall
