Abstract: In order to authenticate a user of an electronic device, an image of the user's fingerprint is captured. Before feature information is extracted, the fingerprint image is enhanced via localized normalization thereby increasing contrast within the fingerprint image. Thereafter, feature information, such as key point data, is extracted from the image and compared to a predefined template to determine whether the feature information matches the template. If so, the user is authenticated. By enhancing the quality of the fingerprint image through localized normalization and other techniques, the reliability of the matching operation is significantly enhanced. In addition, using key point comparisons for assessing similarity between the feature information and the template helps to address inconsistencies relating to finger rotation, scale, and translation during capture.