Published on

IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit

  • Be the first to comment

  • Be the first to like this

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide


  1. 1. Einstein.J, DivyaBaskaran / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 Vol. 3, Issue 2, March -April 2013, pp.351-355 Face-Name Graph Matching For The Personalities In Movie Screen Einstein.J*, DivyaBaskaran** *(Asst. Professor, Dept. of IT, VelTech HighTech Dr. Rangarajan Dr.Sakunthala Engineering College, Chennai.) ** (Final Year Student, M.Tech IT, Vel Tech Dr. RR &Dr. SR Technical University, Chennai.)Abstract In image processing, various biometric computer vision research community over past twoapplications, name identification from facial decades.images plays an important role, Weber’s Local There are 2 main steps involved inDescriptor (WLD) will be used for face recognizing names of humans presented in an imagerecognition for name identification.WLD is a .These are face detection and name classificationtexture descriptor that performs better than ,which are applied consecutively. In order to exploitother similar descriptors but it is holistic due to uniqueness of faces in name recognition, the firstits very construction. We divide an image into a step is to detect and localize those faces in thenumber of blocks, calculate WLD descriptor for images. This is the task achieved by face detectioneach block and concatenate them. This spatial systems.WLD descriptor has better discriminatory As face detection is one of popular researchpower. It is used to represent the image in terms areas, many algorithms have been proposed for it.of differential excitations and gradient Most of them are based on the same ideaorientation histogram for texture analysis.WLD considering the face detection as a binaryis based on Weber’s law and it is robust to classification task. That is, given a part of image, theillumination change, noise and other distortions. task is to decide whether it is a face or not .This isSo it effectively analyzes the face features to achieved by first transforming the given region intoaccurate matching and name identification. The features and then using classifier trained on examplefeature extraction approach will be used for both images to decide if these features represent a humantest and database images to recognize for name face. faces can appear in various locations and canidentification. The face will be recognized by also show themselves in various sizes, often afinding Euclidean distance between them. The window-sliding technique is also employed .Theproposed spatial WLD descriptor with simplest idea is to have the classifier classifying the portionsclassifier gives much better accuracy with lesser of an image, at all location and scales, as face oralgorithmic complexity than face recognition non-face.approaches. 2. RELATED WORKSKeywords- Normalization, Orientation, This section discuss about the literatureDifferential excitation, Euclidean Distance. survey done on various issues are Cast list discovery problem: In the “cast list1. INTRODUCTION discovery “problem the faces are clustered by There are number of applications where appearance and faces of a particular character areface recognition can play an important role expected to be collected in a few pure clusters.including biometric authentication, high technology Names for the clusters are then manually selectedsurveillance and security systems image retrieval from the cast list. Ramanan et al. Proposed toand passive demographical data collections .it is manually label an initial set of face clusters andobservable that our behaviour and social interaction further cluster the rest face instances based onare face recognition system could have great impact clothing within scenes the authors have addressedin improving human computer interaction systems the problem of finding particular characters byin such a way as to make them be more user- building a model/classifier of the character’sfriendly and acting more human-like. It is appearance from user-provided training data.unarguable that face is one the most important Multiple learning problems: Multiple instancesfeature that characterizes human beings. By only learning (MIL) is proposed for problems withlooking ones faces, we are not only able to tell who incomplete knowledge on data labels. Instead ofthey are but also perceive a lot of information such receiving labelled instances as a conventionalas their emotions, ages and names. This is why face supervised method does, a MIL method receives arecognition by face has received much interest in set of labelled bags, where each bag contains a number of unlabelled instances. Thus ,a label can be 351 | P a g e
  2. 2. Einstein.J, DivyaBaskaran / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 Vol. 3, Issue 2, March -April 2013, pp.351-355regarded as a constraint in the form of logical-orrelationship with the labels of the instances in thebag.Retrieval problem (AFR) in video: Recent yearshave seen a development of algorithms that useAFR for the analysis of media content. Most ofthese deal with the retrieval problem in video.Arandjelovi’c and zisserman use signature images,obtained by a cascade of transformations of thedetected faces. These are matched using a robustdistance measure in an image to -image or image –to-set fashion to retrieve film shots based on the Figure 1: Block diagram for identifying face andpresence of specific actors. sivic et al. Match face namesets, representing individual faces using SIFTdescriptors corresponding to salient facial features.Everingham and Zisserman employ a quasi3D 3.2WLDmodel of the head to correct for varying pose and In this part, we describe the two components of WLD. Differential excitation ((ξ)enrich the training corpus via shot tracking. and orientation (θ).After that we present how to compute a WLD histogram for an input image (or3. PROPOSED SYSTEM image region). The paper proposes a simple, yet verypowerful and robust local descriptor, called theWeber’s Local Descriptor (WLD).It is based on thefact that human perception of a pattern depends notonly on the change of a stimulus (such as sound.lightening)but also on the original intensity of thestimulus specifically.WLD consists of twocomponents differential excitation component is afunction of the ratio between two terms. One is therelative intensity differences of a current pixelagainst its neighbours. The other is the intensity of Fig 2.WLD applied Imagethe current pixel. For a given image, we use the twocomponents to construct a concatenated WLD 3.2.1 DIFFERENTIAL EXCITATIONhistogram .Experimental results on the Brodatz and We use the intensity differences betweenKTH-TIPS2-a texture databases show that WLD its neighbours and a current pixel as the changes ofimpressively outperforms the other widely used the current pixel. By this means, we hope to find thedescriptors (e.g. ,Gabor and SIFT).In addition, salient variations within an image to simulate theexperimental results on human face detection also pattern perception of human beings. Specifically ,ashow a promising performance comparable to the differential excitationξ (xc) of a current pixel xc isbest known results on the MIT+CMU frontal face computed. We first calculate the differencestest set, the AR face dataset and the CMU profile between its neighbours and the centre point usingtest set. the filter f003.1CLASSIFICATION With all necessary features have been extracted, Where xi(i=0,1...p-1)denotes the i-th neighbours ofthe final task is to decide whether or not those xc and p is the number of neighbours. Followingfeatures represent female or male face .As there are hints in Weber’s Law, we then compute the ratio ofobviously two decisions to make this essentially the differences to the intensity of the current pointbinary classification task, that is the classifier is by combining the outputs of the two filters f00 andtrained on the female and male example face images f01(whose output 01 s v is the original image inso that it learns the decision boundary between these fact).two classes. After that it uses what it learn to make adecision on the given face images. We then employ the arctangent function on Gratio(٠): Combining (2), (3) and (4), we have: 352 | P a g e
  3. 3. Einstein.J, DivyaBaskaran / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 Vol. 3, Issue 2, March -April 2013, pp.351-355 the weber’s fraction. Weber’s Law, more simply stated, says that the size of a just noticeable difference(i.e., ΔI) is a constant proportion of theSo, the differential excitation of the current pixel original stimulus value. So ,for example, in a noisyξ(xc) is computed as: environment one must shout to be heard while a whisper works in a quiet room.Note that ξ(x) may take a minus value if theneighbour intensities are smaller than that of thecurrent pixel. By this means, we attempt to preservemore discriminating information in comparison tousing the absolute value of ξ(x).Intuitively, if ξ(x) ispositive; it simulates the case that the surroundingsare lighter than the current pixel. In contrast, if ξ(x)is negative, it simulates the case that thesurroundings are darker than the current pixel.3.2.2 ORIENTATION The orientation component of WLD is thegradient orientation as in, which is computed asWhere 10 s v and 11 s v are the outputs of the filtersf10 and f11 Fig 3: Illustration of computation of the WLDFor simplicity, θ is further quantized into T Descriptor.dominant orientations. Before the quantization, weperform the mapping f :θaθ ′ : 4. IMPLEMENTATION After faces are detected by face detection algorithm, they need to be decided his or her names .This is the task achieved by name identification based on face recognition. Similar to the face detection task, the name identification task is also considered as a binary classification problem and it will be done by recognizing the faces to identify theWhereθ∈ [-π/2, π/2] and θ ′ ∈ [0, 2π]. This mapping name though the database. Essentially, Nameconsiders the value of θ and the sign of 10 s v and identification through face recognition consists of 411 s v. The quantization functions is then as follows main steps (1)Pre-processing, (2) Feature Detection,(3) Euclidean Distance and(4) Name Classification. 4.1PRE-PROCESSING3.3WEBER’S LAW Since, in real-life, it is unlikely that people Ernst Weber, an experimental psychologist will face directly and frontally towards the camera,in the 19th century, observed that the ratio of the face images often consist of some in-plane and out-increment threshold to the background intensity is a of-plane Rotations. Moreover, it is also unlikely thatconstant. This relationship, known since as weber’s the light condition will be the same for all images.Law, can be expressed as These variations greatly affect an accuracy of name classifiers. The purpose of pre-processing step is thus to remove these variations as much as possible. As with other computer vision applications, there is Where ΔI represents the increment no unique solution to this problem. The commonthreshold(just noticeable difference for techniques involved in pre-processing step are facediscrimination).I represents the initial stimulus alignment, and light normalization. Face alignmentintensity and K signifies that the proportion on the tries to align faces such that they are closed to aleft side of the equation remains constant despite common or specified pose of face as much asvariations in the term. The fraction ΔI/I is known as 353 | P a g e
  4. 4. Einstein.J, DivyaBaskaran / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 Vol. 3, Issue 2, March -April 2013, pp.351-355possible, whereas light normalization tries to get rid 5. CONCLUSIONof the variation in illumination. one of the common The proposed schemes are useful toemployed normalization techniques in the name improve results for identification of the face tracksclassification field is histogram equalization. extracted from uncontrolled movie videos from the sensitivity analysis. It is shown that to some degree4.1.1NORMALIZATION such schemes have better robustness to the noises in Normalization is a process that changes the constructing affinity graphs than the traditionalrange of pixel intensity values. The linear methods. It gives best results in noise fullnormalization of a grey scale digital image is environment also. Future scenario will extend theperformed according to the formula work to investigate that the optimal functions for different movie genres. REFERENCES For example, if the intensity range of the [1] J. Sang, C. Liang, C. Xu, and J. Cheng,image is 50 to 180 and the desired range is 0 to 255 “Robust movie character identification andthe process entails subtracting 50 from each of pixel the sensitivity analysis,” in Proc. ICME,intensity, making the range 0 to 130.Then each pixel 2011.intensity is multiplied by 255/130,making the range [2] S. Satoh and T. Kanade, “Name-it:0 to 255. Association of face and name in video,” in Proc. Comput.Vis. Pattern Recognit., 1997.4.2FEATURE DETECTION [3] T. L. Berg, A. C. Berg, J. Edwards, M. Working directly on raw pixel values can Maire, R.White, Y. W. Teh, E. G. Learned-be very slow as one small face image can contain a Miller, and D. A. Forsyth, “Names andthousand of pixels. Furthermore, not all the pixels faces in the news,” in Proc. Comput. Vis.will be useful. There can be an underlying structure Pattern. Recognit., 2004.that describes the differences between male and [4] J. Yang and A. Hauptmann, “Multiplefemale faces better. Thus the feature detection instance learning for labeling faces inmodule is employed here. broadcasting news video,” in Proc. ACM Int. Conf. Multimedia, 2005.4.3EUCLIDEAN DISTANCE [5] M. Everingham and A. Zisserman, The Euclidean distance or Euclidean metric “Identifying individuals in video byis the ordinary distance between two points that one combining “generative” and discriminativewould measure with a ruler, and is given by the head models,” in Proc. Int. Conf. Comput.Pythagorean formula. By using this formula as Vis., 2005.distance, Euclidean space(or even any inner product [6] O. Arandjelovic and R. Cipolla,space)becomes a metric space. The associated norm “Automatic cast listing in feature lengthis called the Euclidean norm. Older literature refers films with anisotropic manifold space,” into the metric as Pythagorean metric Proc. Comput. Vis. Pattern Recognit., 2006. [7] M. Everingham, J. Sivic, and A. Zissserman, “Hello! my name is buffy automatic naming of characters in tvWhere, D-Database image, Ii-Input image video,” in Proc. BMVC, 2006. [8] T. Cour, B. Sapp, C. Jordan, and B. Taskar,4.4 NAME CLASSIFICATION “Learning from ambiguously labeled Generally there are two types of features images,” in Proc. Comput. Vis. Pattern.presented in the name classification context, Recognit., 2009.geometric-based features and appearance-based [9] J. Stallkamp, H. K. Ekenel, and R.features. Stiefelhagen, “Video-based face a)Geometric-based features(also called local recognition on real-world data,” in Proc.features)came from psychophysical explorations. Int. Conf. Comput. Vis., 2007, pp. 1–8.They represent high-level face descriptions such as [10] S. Satoh and T. Kanade, “Name-it:distances between nose ,eyes and mouth, face width, Association of face and name in video,” inface length, eyebrow thickness and so on. Proc. Comput. Vis. Pattern Recognit.,b)Appearance-based features(also called global 1997, pp. 368–373.features)use low –level information about face [11] J. Yang and A. Hauptmann, “Multipleimage areas based on pixel values. instance learning for labelling faces in broadcasting news video,” in Proc. ACM Int. Conf. Multimedia, 2005, pp. 31–40. 354 | P a g e
  5. 5. Einstein.J, DivyaBaskaran / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 Vol. 3, Issue 2, March -April 2013, pp.351-355 [12] A. W. Fitzgibbon and A. Zisserman, “On affine invariant clustering and automatic cast listing in movies,” in Proc. ECCV, 2002, pp. 304–320.*Author: Einstein.J, received B.Tech degree inInformation Technology from Anna University in2005, M.Tech degree from Anna University in2008.His current research interest includeCryptography, Image processing, Computernetworks, Cloud computing etc. He is a Asst.Professor in the Department of InformationTechnology in VelTech HighTech Dr. Rangarajan &Dr. Sakunthala Engineering College, Avadi,Chennai, India. Einstein.J has published Eightinternational publications and presented Six researchpapers in international and national conferences,having 4 years of teaching experience in variousinstitutions in India.**Author: Divya Baskaran received B.Tech degreein Information Technology from PeriyarManiammai University, Thanjavur, India in2011,Currrently pursuing M.Tech degree inInformation Technology from VelTech Dr . RR &Dr. SR Technical University, Avadi, Chennai, India.Divya Baskaran has published one internationalpublication. 355 | P a g e