The Experts below are selected from a list of 3276 Experts worldwide ranked by ideXlab platform
R. Balan - One of the best experts on this subject based on the ideXlab platform.
-
AutoID - Speaker verification with combined threshold, identification front-end, and UBM
Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID'05), 2005Co-Authors: J. Rosca, R. BalanAbstract:This paper presents a novel approach to improve accuracy performance of a speaker verification system through combination or cascading three different verification methods using an identification "front-end", a universal background model, and an individual matching score threshold. The performance of a speaker verification system can be determined in terms of false rejection rate and false acceptance rate using a standard benchmark speech corpus, which represents fixed common populations in testing voice and claimed identities. By further assuming uniform distributions, it can show analytically that the false acceptance rate of a standalone system either using the threshold or the universal background model can be significantly reduced when combined with the identification ''front-end''. Experiments have provided clear evidence, and even more gains to combine all three methods together. The results show 60% reduction in the false acceptance rate for combining with the identification "front-end" alone, and 80% reduction for combining all three methods without adding penalty in the false rejection rate.
-
Speaker verification with combined threshold, identification front-end, and UBM
Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID'05), 2005Co-Authors: J. Rosca, R. BalanAbstract:This paper presents a novel approach to improve accuracy performance of a speaker verification system through combination or cascading three different verification methods using an identification "front-end", a universal background model, and an individual matching score threshold. The performance of a speaker verification system can be determined in terms of false rejection rate and false acceptance rate using a standard benchmark speech corpus, which represents fixed common populations in testing voice and claimed identities. By further assuming uniform distributions, it can show analytically that the false acceptance rate of a standalone system either using the threshold or the universal background model can be significantly reduced when combined with the identification ''front-end''. Experiments have provided clear evidence, and even more gains to combine all three methods together. The results show 60% reduction in the false acceptance rate for combining with the identification "front-end" alone, and 80% reduction for combining all three methods without adding penalty in the false rejection rate.
John J. Weng - One of the best experts on this subject based on the ideXlab platform.
-
A learning-based prediction-and-verification segmentation scheme for hand sign image sequence
IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999Co-Authors: John J. WengAbstract:We present a prediction-and-verification segmentation scheme using attention images from multiple fixations. A major advantage of this scheme is that it can handle a large number of different deformable objects presented in complex backgrounds. The scheme is also relatively efficient. The system was tested to segment hands in sequences of intensity images, where each sequence represents a hand sign in American Sign Language. The experimental result showed a 95 percent correct segmentation rate with a 3 percent false rejection rate.
-
ICPR - View-based hand segmentation and hand-sequence recognition with complex backgrounds
Proceedings of 13th International Conference on Pattern Recognition, 1996Co-Authors: John J. WengAbstract:In this paper, we presents a three-stage framework to analyze time-varying image sequences. The focus of this paper is the second stage: segmentation. We propose a prediction-and-verification segmentation scheme which efficiently utilizes the attention images from the multiple fixations. The experimental results show 95% correct segmentation rate with 3% false rejection rate of 805 testing images. The recognition of hand sign based on the segmentation results has shown that the system has achieved a good performance for this very difficult vision task.
-
Hand segmentation using learning-based prediction and verification for hand sign recognition
Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1996Co-Authors: John J. WengAbstract:This paper presents a prediction-and-verification segmentation scheme wing attention images from multiple fixations. A major advantage of this scheme is that it can handle a large number of different deformable objects presented in complex backgrounds. The scheme is also relatively efficient since the segmentation is guided by the past knowledge through a prediction-and-verification scheme. The system has been tested to segment hands in the sequences of intensity images, where each sequence represents a hand sign. The experimental result showed a 95% correct segmentation rate with a 3% false rejection rate.
J. Rosca - One of the best experts on this subject based on the ideXlab platform.
-
AutoID - Speaker verification with combined threshold, identification front-end, and UBM
Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID'05), 2005Co-Authors: J. Rosca, R. BalanAbstract:This paper presents a novel approach to improve accuracy performance of a speaker verification system through combination or cascading three different verification methods using an identification "front-end", a universal background model, and an individual matching score threshold. The performance of a speaker verification system can be determined in terms of false rejection rate and false acceptance rate using a standard benchmark speech corpus, which represents fixed common populations in testing voice and claimed identities. By further assuming uniform distributions, it can show analytically that the false acceptance rate of a standalone system either using the threshold or the universal background model can be significantly reduced when combined with the identification ''front-end''. Experiments have provided clear evidence, and even more gains to combine all three methods together. The results show 60% reduction in the false acceptance rate for combining with the identification "front-end" alone, and 80% reduction for combining all three methods without adding penalty in the false rejection rate.
-
Speaker verification with combined threshold, identification front-end, and UBM
Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID'05), 2005Co-Authors: J. Rosca, R. BalanAbstract:This paper presents a novel approach to improve accuracy performance of a speaker verification system through combination or cascading three different verification methods using an identification "front-end", a universal background model, and an individual matching score threshold. The performance of a speaker verification system can be determined in terms of false rejection rate and false acceptance rate using a standard benchmark speech corpus, which represents fixed common populations in testing voice and claimed identities. By further assuming uniform distributions, it can show analytically that the false acceptance rate of a standalone system either using the threshold or the universal background model can be significantly reduced when combined with the identification ''front-end''. Experiments have provided clear evidence, and even more gains to combine all three methods together. The results show 60% reduction in the false acceptance rate for combining with the identification "front-end" alone, and 80% reduction for combining all three methods without adding penalty in the false rejection rate.
Manesh Kokare - One of the best experts on this subject based on the ideXlab platform.
-
COMPARISON OF COLOR AND TEXTURE FOR IRIS RECOGNITION
International Journal of Pattern Recognition and Artificial Intelligence, 2012Co-Authors: Lenina Birgale, Manesh KokareAbstract:This paper proposes the utility of texture and color for iris recognition systems. It contributes for improvement of system accuracy with reduced feature vector size of just 1 × 3 and reduction of false acceptance rate (FAR) and false rejection rate (FRR). It avoids the iris normalization process used traditionally in iris recognition systems. Proposed method is compared with the existing methods. Experimental results indicate that the proposed method using only color achieves 99.9993 accuracy, 0.0160 FAR, and 0.0813 FRR. Computational time efficiency achieved is of 947.7 ms.
-
Iris Recognition Using Discrete Wavelet Transform
2009 International Conference on Digital Image Processing, 2009Co-Authors: Lenina Vithalrao Birgale, Manesh KokareAbstract:We propose a novel approach for improved iris recognition system with reduced false acceptance rate (FAR) and false rejection rate (FRR). The technique developed here uses all the frequency resolution planes of discrete wavelet transform (DWT). These frequency planes provide abundant texture information present in an iris at different resolutions. The accuracy is improved up to 98.98%. With proposed method FAR and FRR is reduced up to 0.0071% and 1.0439% respectively.
-
ICDIP - Iris Recognition Using Discrete Wavelet Transform
2009 International Conference on Digital Image Processing, 2009Co-Authors: Lenina Vithalrao Birgale, Manesh KokareAbstract:We propose a novel approach for improved iris recognition system with reduced false acceptance rate (FAR) and false rejection rate (FRR). The technique developed here uses all the frequency resolution planes of Discrete Wavelet Transform (DWT). These frequency planes provide abundant texture information present in an iris at different resolutions. The accuracy is improved up to 98.98%. With proposed method FAR and FRR is reduced up to 0.0071% and 1.0439% respectively.
J.a. Du Preez - One of the best experts on this subject based on the ideXlab platform.
-
A comparison between hidden Markov models and vector quantization for speech independent speaker recognition
1993 IEEE South African Symposium on Communications and Signal Processing, 1993Co-Authors: D. M. Weber, J.a. Du PreezAbstract:We compare Vector Quantization and Hidden Markov Models for speaker recognition for real time recognition. A scheme to reject speakers not known to the system is described and tested. Results show that the HMM algorithm outperforms the VQ algorithm. Using a 64 state HMM, a speaker recognition accuracy of 96.1% was achieved. The rejection option generated 25.7% false rejections for a 95% confidence of a correct decision. VQ best results were 93.1% with a 61% false rejection rate for codebooks of size 128. >