Signature recognition

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

FPGA hardware for speech recognition using hidden Markov models.

Abstract: Some speech recognition applications, like speaker verification, dialog recognition or the speech to text transcription could require real time processing and a good precision. Other applications such as toys, automotive vehicles or portable machines still could aggregate the portability and low-power requirements, in addition to physical compactness. These requirements could require a hardware solution for the speech recognition problem. The current work proposes an architecture using hardware based in FPGAs, optimizing the pre-processing and parameter extraction for performing efficient speech recognition.

An Implementation of Optical Image Fingerprint Recognition System

Abstract: Although there have been abundant research examining fingerprint recognition systems in the biometric recognition domain, recognition rate and speed remain significant problems. In order to achieve high recognition rates and real-time processing, a high-resolution image capturing device coupled with high speed processing is needed. As a potential solution, we propose a fuzzy identification method to get a higher recognition rate and increase recognition speed while avoiding deletion of necessary fingerprint features and removing unnecessary fingerprint features that do not affect recognition results. The images are cut into many small blocks, statistics pixels, and thresholds are set to judge the angles as eigenvalues. The FAR (False Acceptance Rate) and FRR (False Rejected Rate) are then tested by using multiple pieces of fingerprints on different people interactively. The results not only show a certain degree of recognition rate on low-quality fingerprint images, but also reduce the computational complexity on recognition rate. Additionally, there is a high requirement to request the accuracy of finger location, which indicates that there is still much space for system improvement.

Novel facial image recognition techniques employing principal component analysis

Abstract: Recently, pattern recognition/classification has received considerable attention in diverse engineering fields such as biomedical imaging, speaker identification, fingerprint recognition, and face recognition, etc. This study contributes novel techniques for facial image recognition based on the Two dimensional principal component analysis in the transform domain. These algorithms reduce the storage requirements by an order of magnitude and the computational complexity by a factor of 2 while maintaining the excellent recognition accuracy of the recently reported methods. The proposed recognition systems employ different structures, multicriteria and multitransform. In addition, principal component analysis in the transform domain in conjunction with vector quantization is developed which result in further improvement in the recognition accuracy and dimensionality reduction. Experimental results confirm the excellent properties of the proposed algorithms.

Gesture Recognition Using Pseudo 3D Hidden Markov Models

Abstract: We introduce a novel approach to gesture recognition, based on Pseudo 3D Hidden Markov Models. This technique is capable of integrating spatially and temporally derived features in an elegant way, thus making possible the recognition of static gestures such as standing in a special posture, as well as dynamic gestures such as hand waving. Pseudo 2D Hidden Markov Models have been utilized for two dimensional Problems such as face recognition. P3DHMMs can be considered as an extension of 2D case, where the so-called superstates in P3DHMM encapsulate P2DHMMs. By the means of this structure, image sequences can be generated by the model. The Performance of our approach is demonstrated in this paper by a number of experiments on a gesture database of nine different predefined gestures.