The Experts below are selected from a list of 107418 Experts worldwide ranked by ideXlab platform
Kaisheng Hsieh - One of the best experts on this subject based on the ideXlab platform.
-
ultrasonic liver tissues classification by fractal Feature Vector based on m band wavelet transform
IEEE Transactions on Medical Imaging, 2003Co-Authors: Wenli Lee, Yungchang Chen, Kaisheng HsiehAbstract:Describes the feasibility of selecting a fractal Feature Vector based on M-band wavelet transform to classify ultrasonic liver images - normal liver, cirrhosis, and hepatoma. The proposed Feature extraction algorithm is based on the spatial-frequency decomposition and fractal geometry. Various classification algorithms based on respective texture measurements and filter banks are presented and tested. Classifications for the three sets of ultrasonic liver images reveal that the fractal Feature Vector based on M-band wavelet transform is trustworthy. A hierarchical classifier, which is based on the proposed Feature extraction algorithm is at least 96.7% accurate in the distinction between normal and abnormal liver images and is at least 93.6% accurate in the distinction between cirrhosis and hepatoma liver images. Additionally, the criterion for Feature selection is specified and employed for performance comparisons herein.
-
ultrasonic liver tissues classification by fractal Feature Vector based on m band wavelet transform
International Symposium on Circuits and Systems, 2001Co-Authors: Wenli Lee, Yungchang Chen, Kaisheng HsiehAbstract:This paper proposes a new fractal Feature Vector based on M-band wavelet transform for classification of ultrasonic liver images-normal liver, cirrhosis, and hepatoma. Classifications for liver images have revealed that the fractal Feature Vector is trustworthy. A hierarchical classifier produces 97.27% correct classification for the distinction of normal and abnormal liver image and 93.6% correct classification for the distinction of cirrhosis and hepatoma liver image.
K. Laurila - One of the best experts on this subject based on the ideXlab platform.
-
cepstral domain segmental Feature Vector normalization for noise robust speech recognition
Speech Communication, 1998Co-Authors: O. Viikki, K. LaurilaAbstract:Abstract To date, speech recognition systems have been applied in real world applications in which they must be able to provide a satisfactory recognition performance under various noise conditions. However, a mismatch between the training and testing conditions often causes a drastic decrease in the performance of the systems. In this paper, we propose a segmental Feature Vector normalization technique which makes an automatic speech recognition system more robust to environmental changes by normalizing the output of the signal-processing front-end to have similar segmental parameter statistics in all noise conditions. The viability of the suggested technique was verified in various experiments using different background noises and microphones. In an isolated word recognition task, the proposed normalization technique reduced the error rates by over 70% in noisy conditions with respect to the baseline tests, and in a microphone mismatch case, over 75% error rate reduction was achieved. In a multi-environment speaker-independent connected digit recognition task, the proposed method reduced the error rates by over 16%.
-
ICASSP - A recursive Feature Vector normalization approach for robust speech recognition in noise
Proceedings of the 1998 IEEE International Conference on Acoustics Speech and Signal Processing ICASSP '98 (Cat. No.98CH36181), 1Co-Authors: O. Viikki, D.k. Bye, K. LaurilaAbstract:The acoustic mismatch between testing and training conditions is known to severely degrade the performance of speech recognition systems. Segmental Feature Vector normalization was found to improve the noise robustness of mel-frequency cepstral coefficients (MFCC) Feature Vectors and to outperform other state-of-the-art noise compensation techniques in speaker-dependent recognition. The objective of Feature Vector normalization is to provide environment-independent parameter statistics in all noise conditions. We propose a more efficient implementation approach for Feature Vector normalization where the normalization coefficients are computed in a recursive way. Speaker-dependent recognition experiments show that the recursive normalization approach obtains over 60%, the segmental method approximately 50%, and parallel model combination a 14% overall error rate reduction, respectively. Moreover, in the recursive case, this performance gain is obtained with the smallest implementation costs. Also in speaker-independent connected digit recognition, over a 16% error rate reduction is obtained with the proposed Feature Vector normalization approach.
Luiz S Oliveira - One of the best experts on this subject based on the ideXlab platform.
-
a multiple Feature Vector framework for forest species recognition
ACM Symposium on Applied Computing, 2013Co-Authors: Paulo R Cavalin, Marcelo N Kapp, J G Martins, Luiz S OliveiraAbstract:In this work we focus on investigating the use of multiple Feature Vectors for forest species recognition. As consequence, we propose a framework to deal with the extraction of multiple Feature Vectors based on two approaches: image segmentation and multiple Feature sets. Experiments conducted on a 112 species database containing microscopic images of wood demonstrate that with the proposed framework we can increase the recognition rates of the system from about 55.7% (with a single Feature Vector) to about 93.2%.
-
SAC - A multiple Feature Vector framework for forest species recognition
Proceedings of the 28th Annual ACM Symposium on Applied Computing - SAC '13, 2013Co-Authors: Paulo R Cavalin, Marcelo N Kapp, J G Martins, Luiz S OliveiraAbstract:In this work we focus on investigating the use of multiple Feature Vectors for forest species recognition. As consequence, we propose a framework to deal with the extraction of multiple Feature Vectors based on two approaches: image segmentation and multiple Feature sets. Experiments conducted on a 112 species database containing microscopic images of wood demonstrate that with the proposed framework we can increase the recognition rates of the system from about 55.7% (with a single Feature Vector) to about 93.2%.
Wenli Lee - One of the best experts on this subject based on the ideXlab platform.
-
ultrasonic liver tissues classification by fractal Feature Vector based on m band wavelet transform
IEEE Transactions on Medical Imaging, 2003Co-Authors: Wenli Lee, Yungchang Chen, Kaisheng HsiehAbstract:Describes the feasibility of selecting a fractal Feature Vector based on M-band wavelet transform to classify ultrasonic liver images - normal liver, cirrhosis, and hepatoma. The proposed Feature extraction algorithm is based on the spatial-frequency decomposition and fractal geometry. Various classification algorithms based on respective texture measurements and filter banks are presented and tested. Classifications for the three sets of ultrasonic liver images reveal that the fractal Feature Vector based on M-band wavelet transform is trustworthy. A hierarchical classifier, which is based on the proposed Feature extraction algorithm is at least 96.7% accurate in the distinction between normal and abnormal liver images and is at least 93.6% accurate in the distinction between cirrhosis and hepatoma liver images. Additionally, the criterion for Feature selection is specified and employed for performance comparisons herein.
-
ultrasonic liver tissues classification by fractal Feature Vector based on m band wavelet transform
International Symposium on Circuits and Systems, 2001Co-Authors: Wenli Lee, Yungchang Chen, Kaisheng HsiehAbstract:This paper proposes a new fractal Feature Vector based on M-band wavelet transform for classification of ultrasonic liver images-normal liver, cirrhosis, and hepatoma. Classifications for liver images have revealed that the fractal Feature Vector is trustworthy. A hierarchical classifier produces 97.27% correct classification for the distinction of normal and abnormal liver image and 93.6% correct classification for the distinction of cirrhosis and hepatoma liver image.
O. Viikki - One of the best experts on this subject based on the ideXlab platform.
-
cepstral domain segmental Feature Vector normalization for noise robust speech recognition
Speech Communication, 1998Co-Authors: O. Viikki, K. LaurilaAbstract:Abstract To date, speech recognition systems have been applied in real world applications in which they must be able to provide a satisfactory recognition performance under various noise conditions. However, a mismatch between the training and testing conditions often causes a drastic decrease in the performance of the systems. In this paper, we propose a segmental Feature Vector normalization technique which makes an automatic speech recognition system more robust to environmental changes by normalizing the output of the signal-processing front-end to have similar segmental parameter statistics in all noise conditions. The viability of the suggested technique was verified in various experiments using different background noises and microphones. In an isolated word recognition task, the proposed normalization technique reduced the error rates by over 70% in noisy conditions with respect to the baseline tests, and in a microphone mismatch case, over 75% error rate reduction was achieved. In a multi-environment speaker-independent connected digit recognition task, the proposed method reduced the error rates by over 16%.
-
ICASSP - A recursive Feature Vector normalization approach for robust speech recognition in noise
Proceedings of the 1998 IEEE International Conference on Acoustics Speech and Signal Processing ICASSP '98 (Cat. No.98CH36181), 1Co-Authors: O. Viikki, D.k. Bye, K. LaurilaAbstract:The acoustic mismatch between testing and training conditions is known to severely degrade the performance of speech recognition systems. Segmental Feature Vector normalization was found to improve the noise robustness of mel-frequency cepstral coefficients (MFCC) Feature Vectors and to outperform other state-of-the-art noise compensation techniques in speaker-dependent recognition. The objective of Feature Vector normalization is to provide environment-independent parameter statistics in all noise conditions. We propose a more efficient implementation approach for Feature Vector normalization where the normalization coefficients are computed in a recursive way. Speaker-dependent recognition experiments show that the recursive normalization approach obtains over 60%, the segmental method approximately 50%, and parallel model combination a 14% overall error rate reduction, respectively. Moreover, in the recursive case, this performance gain is obtained with the smallest implementation costs. Also in speaker-independent connected digit recognition, over a 16% error rate reduction is obtained with the proposed Feature Vector normalization approach.
