Description

The identification of a person using anyone of the human body part is called as the biometric authentication. The main advantage of the dental biometric is that it cannot be faked. The identification of persons through biometric uses several human biometrics for the identification of the persons. The dental biometric is employed for this process. The dental regions were unique for the persons and hence the persons can be identified more effectively. The dental images were segmented and features were extracted from the segmented portions. The extracted features were then classified inorder to recognize the persons. The performance of the process is measured. The input dental images were initially preprocessed inorder to obtain the more accurate dental images. The images were then segmented based on the thresholding operations. The box segmentation process is done by using morphological operations. The morphological operations employed were open operation and close operation. The structuring element is a small binary image, i.e. a small matrix of pixels, each with a value of zero or one. The pattern of ones and zeros specifies the shape of the structuring element. The closing of an image by a structuring element is a dilation followed by an erosion. The opening of an image by a structuring element is an erosion followed by a dilation. The features were then extracted from the images based on the statistical features extracted from the image. The features extracted were mean, median, minimum, maximum distance between binary regions, entropy, gradient and standard deviation. The extracted features were then classified using distance metrics. In addition to the statistical features texture features were extracted from the images based on XCSLBP process. The extracted features were classified based on the SVM classification process. The performance measures were then calculated based on the performance metrics like accuracy, sensitivity and specificity.