Fingerprint Detection Technique Using SURF, PHOG & PCA Feature Extraction Process

The biometric way of identifying a person are wildly spared around many industries and organizations. The identification techniques followed for the biometric are mostly common in using fingerprint detection for individual identification. Basically password based security systems are cracked through many techniques, which makes many problem to the organization using password for security purpose. The spoof fingerprint way of identifying a person is becoming very famous in providing security to the users. The research work focuses on proposing a novel approach in merging fingerprint features all together in one static software approach. The features identified from the fingerprints are extracted using histogram equations in initial step of fingerprint security system. The Gabor wavelet transformation techniques is one of the images processing technique used for identifying features. The features are maintained carefully with applying dynamic score level integration. The efficiency of proposed work is checked with LivDet 2011 dataset. The rate of classification shows 9.625% and error rate is 2.27%.

A Gabor Wavelet Based Approach for Off-Line Recognition of ODIA Handwritten Numerals

Optical Character Recognition is one of the most interesting and highly motivated areas of research, which has been very much ap-preciated in different aspect to the area of digitations world. Here in this paper we have suggested a probabilistic approach for develop-ing recognition system for handwritten Odia numerals. To report a good level of recognition of Odia scripts is quite challenging with respect to other Indian scripts .All the procedure are sequentially enclosed to develop an recognition model and report a successful recognition accuracy. Here we have performed the analysis over to standard handwritten numeral database named as IITBBS Odia Numeral Database, which is collected from IIT Bhubaneswar. In the suggestive recognition system we have adopted a 2D-Gabor wavelet transformation approach for selection of feature vector. Apart from it we have also noted down the dimensional reduction to the obtained feature vector by sustaining to PCA. In order to predict high recognition rate we have followed up by RBF Neural Network classifier. In addition to it we have also evaluate different version of RBF like Gaussian and Polynomial. Performing over 400 samples each of 10 categories (400*10) number of Odia numeral images, we have maintained a well-defined training and testing ratio in the clas-sifier and achieved 98.02%, 96.8%.recognition rate for the reported classifiers.

An Image Classification Algorithm Based on SVM

Image classification is a image processing method which to distinguish between different categories of objectives according to the different features of images. It is widely used in pattern recognition and computer vision. Support Vector Machine (SVM) is a new machine learning method base on statistical learning theory, it has a rigorous mathematical foundation, builts on the structural risk minimization criterion. We design an image classification algorithm based on SVM in this paper, use Gabor wavelet transformation to extract the image feature, use Principal Component Analysis (PCA) to reduce the dimension of feature matrix. We use orange images and LIBSVM software package in our experiments, select RBF as kernel function. The experimetal results demonstrate that the classification accuracy rate of our algorithm beyond 95%.

A Gabor Wavelet Transformation-Based Texture Images Classification Algorithm

In this paper, we introduce a texture image classification algorithm based on Gabor wavelet transform. Using Gabor wavelet transform, image is decomposed into sub-bands images in multiresolution and multi-direction, and we extract texture feature from all sub-bands images. Then the algorithm groups feature image into clusters by the k near neighbor algorithm. The experimental results on dataset Brodatz showed that the proposed algorithm can achieve an ideal accuracy rate and excellent classification effect.

High Performance Human Face Recognition using Gabor Based Pseudo Hidden Markov Model

This paper introduces a novel methodology that combines the multi-resolution feature of the Gabor wavelet transformation (GWT) with the local interactions of the facial structures expressed through the Pseudo Hidden Markov Model (PHMM). Unlike the traditional zigzag scanning method for feature extraction a continuous scanning method from top-left corner to right then top-down and right to left and so on until right-bottom of the image i.e., a spiral scanning technique has been proposed for better feature selection. Unlike traditional HMMs, the proposed PHMM does not perform the state conditional independence of the visible observation sequence assumption. This is achieved via the concept of local structures introduced by the PHMM used to extract facial bands and automatically select the most informative features of a face image. Thus, the long-range dependency problem inherent to traditional HMMs has been drastically reduced. Again with the use of most informative pixels rather than the whole image makes the proposed method reasonably faster for face recognition. This method has been successfully tested on frontal face images from the ORL, FRAV2D, and FERET face databases where the images vary in pose, illumination, expression, and scale. The FERET data set contains 2200 frontal face images of 200 subjects, while the FRAV2D data set consists of 1100 images of 100 subjects and the full ORL database is considered. The results reported in this application are far better than the recent and most referred systems.