Signature recognition

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

Automatic face recognition

Abstract: A review of competing facial recognition techniques is presented. The authors then go on to introduce a new method of feature-based facial codeing allowing an entire face to be represented in less than two hundred bytes of information. Crucial to this coding process is the use of an a priori model of the face, which helps to guide the location and storage of the most important facial parts. The data reduction is thus achieved while still preserving many of the intrinsic facial recognition features. The algorithm used to perform the data reduction of the face is described. Results, for verification and recognition trials, are presented for a software implementation of the algorithm. >

A simple and effective method for online signature verification

Abstract: This paper presents a simple and efficient method for online signature verification. The technique is based on a feature set comprising of several histograms that can be computed efficiently given a raw data sequence of an online signature. The features which are represented by a fixed-length vector can not be used to reconstruct the original signature, thereby providing privacy to the user's biometric trait in case the stored template is compromised. To test the verification performance of the proposed technique, several experiments were conducted on the well known MCYT-100 and SUSIG datasets including both skilled forgeries and random forgeries. Experimental results demonstrate that the performance of the proposed technique is comparable to state-of-art algorithms despite its simplicity and efficiency.

A new scheme for off-line handwritten connected digit recognition

Abstract: A scheme is proposed for off-line handwritten connected digit recognition, which uses a sequence of segmentation and recognition algorithms. First, the connected digits are segmented by employing both the gray scale and binary information. Then, a new set of features is extracted from the segments. The parameters of the feature set are adjusted during the training stage of the hidden Markov model (HMM) where the potential digits are recognized. Finally, in order to confirm the preliminary segmentation and recognition results, a recognition based segmentation method is presented.

VSig: Hand-gestured signature recognition and authentication with wearable camera

Abstract: Wearable camera is gaining popularity not only as a recording device for law enforcement and hobbyists, but also as a human-computer interface for the next generation wearable technology. It provides a more convenient and portable platform for gesture input than stationary camera, but poses unique challenges due to user movement and scene variation. In this paper, we describe a robust wearable camera based system called VSig for hand-gestured signature recognition and authentication. The proposed method asks the user to virtually sign within the field of the view of the wearable camera. Fingertip is segmented out and tracked to reconstruct the signature. This is followed by signature matching for authentication with the pre-stored signatures of the individual. A dataset named SIGAIR comprising of hand-gestured signatures from 10 individuals has been created and used for testing. An average accuracy of 97.5% is achieved by the proposed method.

Recognition of chain-coded handwritten character images with scanning n-tuple method

Abstract: A method of applying n-tuple recognition techniques to handwritten OCR, which involves scanning an n-tuple classifier over a chain-code of the image, is described. The traditional advantages of n-tuple recognition, i.e. training and recognition speed, are retained, while offering superior recognition accuracy, as demonstrated by results on three widely used data sets.