Topic
Signature recognition
About: Signature recognition is a research topic. Over the lifetime, 2138 publications have been published within this topic receiving 37605 citations.
Papers published on a yearly basis
Papers
More filters
Patent•
26 Feb 2014
TL;DR: In this paper, the analysis of characteristics of audio and/or video signals for the generation of audio-visual content signatures is presented, where a region of interest for example of high entropy is identified in audio signature data.
Abstract: The invention relates to the analysis of characteristics of audio and/or video signals for the generation of audio-visual content signatures. To determine an audio signature a region of interest for example of high entropy—is identified in audio signature data. This region of interest is then provided as an audio signature with offset information. A video signature is also provided.
TL;DR: The proposed online handwritten signature verification system consists mainly of three phases: Signal preprocessing, feature extraction, and feature matching, which is helpful in improving the results.
Abstract: Handwritten signature is the most widely accepted biometric to identity verification. The proposed online handwritten signature verification system consists mainly of three phases: Signal preprocessing, feature extraction, and feature matching. Steps for verifying online handwritten signature in this system start with extracting dynamic data (x and y positions) of points that forming the signature. Pen-movement angles and speed are then derived from pen position data. To reduce variations in pen-position and pen-movement angles dimensionality, data is normalized. After that all the parameters are to be put in a single vector. Here in the proposed system five parameters are taken in to account. Features of the signature can be extracted using proposed feature extraction method. Corresponding to every signature a unique feature will be extracted and this will be quantized using quantization step size vector. Both the feature vector and quantization vector are to be stored using template generator. Further, during the matching phase, a different distance measuring algorithm has been implemented known as Minkowski distance which is helpful in improving the results.
31 Aug 1992
TL;DR: The authors present a theorem for self-structuring neural models stating that these models are universal approximators and thus relevant to real-world pattern recognition.
Abstract: The authors propose a self-structuring hidden control (SHC) neural model for pattern recognition which establishes a near-optimal architecture during training. A significant network architecture reduction in terms of the number of hidden processing elements (PEs) is typically achieved. The SHC model combines self-structuring architecture generation with nonlinear prediction and hidden Markov modelling. The authors present a theorem for self-structuring neural models stating that these models are universal approximators and thus relevant to real-world pattern recognition. Using SHC models containing as few as five hidden PEs each for an isolated word recognition task resulted in a recognition rate of 98.4%. SHC models can also be applied to continuous speech recognition. >
01 Jan 2015
TL;DR: Using feature selection technique it is shown that recognition rate improves and the number of features generated is high leading to higher computation time.
Abstract: This study investigates various feature selection techniques for face recognition. Biometric based authentication system protects access to resources and has gained importance, because of their reliable, invariant and discriminating features. An automated biometric system is based on physiological or behavioral human characteristics for protected access. Biometric trait such as palmprint, iris, hand, voice, face fingerprint, or signature is used to authenticate a person's claim. Of the biometrics, face recognition is gaining popularity due to its simple method of capturing the image using cameras. However the number of features generated is high leading to higher computation time. Using feature selection technique it is shown that recognition rate improves.
14 Sep 2017
TL;DR: A cryptographic algorithm based on behavior analysis is presented, which has a better recognition rate with less resource occupation, and can identify the program variants accurately, so it has a good application prospects.
Abstract: Due to the abuse of cryptography technology and the difficulty to break encryption algorithm, ransomware has a huge threat to cyberspace. So how to detect the cryptographic algorithm in the recognition program plays an important role in the protection of information security. However, existing cryptographic algorithm identification and analysis technology has the disadvantages of low recognition efficiency, single analysis strategy, and they cannot identify program variants effectively. In view of these problems, this paper presents a cryptographic algorithm based on behavior analysis. Based on the behavior analysis, combined with the static structure and dynamic statistical characteristics of the key data, the subroutine of the target program is gradually screened, and the execution logic of the subroutine is analyzed. Finally, the cryptographic algorithm in the binary code of the program is obtained. Compared with the traditional signature-based technology, our technology has a better recognition rate with less resource occupation. What’s more, this technology can identify the program variants accurately, so it has a good application prospects.