No abstract

Moments can be viewed as powerful image descriptors that capture global characteristics of an image. The magnitude of the moment coefficients is said to be invariant under geometrical transformations like rotation which makes them suitable for most of the recognition applications. But in practice, the invariance of moment coefficients is compromised due to the errors in computation. This paper presents an empirical study of some popularly used moment functions to find out the robust coefficients under rotation. The selected robust coefficients are used in face recognition under in-plane rotation. Experimental results demonstrate that the performance of the proposed method comes at par with the performance of the traditional method by using lesser number of moment coefficients and thus results in significant saving in the feature extraction time.

Information security is the process of securing the information or data from unauthorized access. Fingerprint authentication is proven to be more secure because it authorizes the unique feature of on finger. Fingerprint recognition system has been suffering through Positive and Negative classifications. In positive classification, the physical access control systems and user should negotiate for self-identification. The false case classification broadly talks about low quality of images in case of user identification may authenticate malicious user. Distortion detection can be categorized in two classification problems, which can be solved using the registered ridge orientation map and period map of a fingerprint which is used as the feature vector and CNN is trained to perform the classification and rectification (or equivalently distortion field estimation) task which can be viewed as a regression problem, where the input is a distorted fingerprint and the output is a distortion field. For such problem, Detection and Rectification of the distorted fingerprint is must. Distortion rectification is used to transform a distorted fingerprint into a normal one so as to increase the recognition rate of existing fingerprint recognition algorithms for distorted fingerprints. CNN is an efficient distortion rectification method and the processing speed is significantly faster than other methods.

No abstract