Special Issue Article
Novel Approach in Face Recognition Using Hieratical Multiscale Local Binary Pattern with Elm Classifier
This paper presents a efficient facial image recognition based on multi scale local binary pattern (LBP) texture features .It’s a fast and simple for implementation, has shown its superiority in face recognition. To extract representative features, “uniform” LBP was proposed and its effectiveness has been validated. However, all “non-uniform” patterns are clustered into one pattern, so lot of useful information is lost. In this study, propose to build a hieratical multiscale LBP histogram for an image. The face image is divided into several regions from which the LBP feature distributions are extracted and concatenated into an enhanced feature vector to be used as a face descriptor. The useful information of “non-uniform” patterns at large scale is dug out from its counterpart of small scale, The performance of the proposed method is that it can fully utilize LBP information while it does not need any training step, That classification we introduce ELM classifier with LBP, and then Performance of the feature extraction method to be evaluated by Elm classifier. Which may be sensitive to training samples assessed in the face recognition problem under different challenges, other applications and several extensions are also discussed. The main advantage of the proposed scheme is that it can fully utilize LBP information while it does not need any training steps for extract the features, which may be sensitive to training samples. Experiments on ORL face database data base show the effectiveness of the proposed method. KEYWORDS— Facial image representation, local binary pattern, multiscale, component based face recognition, texture feature, Extreme Learning machine.