Abstract: Reliable feature extraction from poor quality fingerprint images is still the most challenging problem in fingerprint recognition system. It needs a lot of pre-processing steps to improve the quality of images, then it needs a reliable feature extractor to extract some distinctive features. Segmentation is one of the most important pre-processing steps in fingerprint identification followed by alignment, and enhancement. We improved the segmentation technique which based on thresholding the energy map, with another one based on morphological operation. Recently, Multiresolution techniques have been widely used as a feature extractor in the field of biometric recognition. We use modern multiresolution techniques; Curvelet, Wave Atoms, Shearlet transforms in extracting distinctive features from the enhanced fingerprint images in a new methodology. The selected features are matched throw K-Nearest neighbor classifier technique. We test our methodology in 114 subjects selected from a very challenges database; CASIA; we achieved a high recognition rate of about 99.5%.

Keywords: Fingerprint Recognition, Multiresolution Feature Extraction, Wave Atom, Shearlet, Curvelet, Real Noisy Database, Fingerprint Image Enhancement.