Signature recognition

About: Signature recognition is a research topic. Over the lifetime, 2138 publications have been published within this topic receiving 37605 citations.

A Non-uniform Quantizing Approach to Protect Biometric Templates

Abstract: In this paper, a novel methodology to achieve the security of the biometric templates in biometric systems is proposed. An adaptive non-uniform quantization (ANUQ) algorithm is introduced to eliminate the contradiction between the fuzziness of the biometric information and the sensitive of the Hash function. The ANUQ algorithm maps different biometric feature vectors from the same individual to a unique quantized feature vector. Then the quantized feature vector can be saved and identified by its hash. A biometric template protection scheme is designed which avoids the storage of users? biometric templates, and further reduce the risk of losing of users? sensitive information. Simulations on an iris recognition algorithm show the feasibility of this method.

Protecting DCT Templates for a Face Verification System by Means of Pseudo-random Permutations

Abstract: Biometric template security and privacy are a great concern of biometric systems, because unlike passwords and tokens, compromised biometric templates cannot be revoked and reissued. In this paper we present a protection scheme for an identity verification system through biometrical face recognition based on a user dependent pseudo-random ordering of the DCT template coefficients and MPL and RBF Neural Networks for classification. In addition to privacy enhancement, because a hacker can hardly match a fake biometric sample without knowing the pseudo-random ordering this scheme, it also increases the biometric recognition performance.

Signature envelope curvature descriptor for offline signature verification

Abstract: This paper presents an algorithm for feature descriptor extraction of signature using signature envelope curvature sequences which are rotation invariant. The envelope curvature reflects both the direction change pattern of the envelope sequence and smoothness of the envelope that are usually employed for signature verification by human experts. A polygon matching technique is applied to eliminate the shift effect which results from the arbitrary start point selection for calculation of the proposed envelope curvature features. To make the method robust to be size invariant, a normalization process is done with additional benefit of feature dimension reduction. Finally, experimental results show comparable performance of the proposed method aiming at simple and skill forgery detection for offline signature verification.

Wavelet Transform Based Global Features for Online Signature Recognition

Abstract: This paper presents an efficient algorithm for an online signature verification system that is based on the extraction of global features from the spatial coordinates obtained during the online acquisition of a signature using one dimensional wavelet transform. A k-NN classifier is used for classification purposes. Low error rates obtained for both random and skilled forgeries datasets illustrate the feasibility of the algorithm for an online signature verification system

A facial expression recognition model based on HMM

Abstract: The most expressive way humans display emotions is through facial expressions, and the facial expression recognition has been widely used. Although so many researches are done, it is hard to find a practical application in the real world. The motion of the face is modeled by HMM as follows, first, according to the function of HMM in processing continuous dynamic signal and model recognition, and for the sample's overlap and similarity in the sample space, Code-HMM was made up respectively; then, inducted KNN and some discrimination rules by analyzing the output result. A method based on code HMM+KNN is proposed to recognize the facial expression. The experimental results show that this method is better than traditional HMM.