Indexing Scheme for Iris Using Discrete Cosine and Discrete Wavelet Transform

In this paper, we proposed indexing scheme for Iris image database. We used Discrete Cosine Transformation (DCT) and Discrete Wavelet Transformation (DWT) successively on the normalized Iris image to compute the feature vector of Iris image. DCT and DWT are performed block wise on the normalized Iris image. Based on feature vector of Iris image, we constructed adaptive sized bin, so that each bin consist equal number of images. Interval of the bin is computed using Gaussian distribution approximation. The use of these type of bins improve the penetration rate. The bin number for each index of the feature vector is obtained to form the global key for each image. During database preparation the key is used to traverse the B-tree. The images with same key are stored in the same leaf node. For a given query image, the key is generated and tree is traversed to end up to a leaf node. The templates stored at the leaf node are retrieved and compared with the query template to find the best match. The proposed indexing scheme is showing considerably low penetration rate of 0.0006%, for UBIris.v1.