Pub Date : 1998-10-12DOI: 10.1109/ICOSP.1998.770246
Peng Hua, Le Zhongxin
A blind equalization algorithm based on the unsupervised Gaussian cluster formation technique with a robust adaptive step-size to update the equalizer coefficients is proposed. In order to guarantee the convergence of the algorithm, the algorithm runs in a "stop-and-go" operation mode in such a way that a Godard class of algorithm controls its "stop-and-go" operation. In order to achieve faster convergence speed, the algorithm is switched to a Godard class of algorithm when adaptation is stopped. Simulation results confirm the effectiveness of the proposed algorithm on high-order QAM signals.
{"title":"A new blind equalizer for high-order QAM system","authors":"Peng Hua, Le Zhongxin","doi":"10.1109/ICOSP.1998.770246","DOIUrl":"https://doi.org/10.1109/ICOSP.1998.770246","url":null,"abstract":"A blind equalization algorithm based on the unsupervised Gaussian cluster formation technique with a robust adaptive step-size to update the equalizer coefficients is proposed. In order to guarantee the convergence of the algorithm, the algorithm runs in a \"stop-and-go\" operation mode in such a way that a Godard class of algorithm controls its \"stop-and-go\" operation. In order to achieve faster convergence speed, the algorithm is switched to a Godard class of algorithm when adaptation is stopped. Simulation results confirm the effectiveness of the proposed algorithm on high-order QAM signals.","PeriodicalId":145700,"journal":{"name":"ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116279217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-10-12DOI: 10.1109/ICOSP.1998.770303
Wen-Rong Wu, Po-Chen Chen, Hwai-Tsu Chang, Chun-Hung Kuo
Kalman filtering is an effective speech enhancement technique, in which speech and noise signals are usually modeled as autoregressive (AR) processes and represented in the state-space domain. Since AR coefficient identification and Kalman filtering require extensive computations, practical implementation of this approach is difficult. This paper proposes a simple and practical scheme that overcomes these problems. Speech signals are first decomposed into subbands. Subband speech signals are then modeled as low-order AR processes, such that low-order Kalman filters can be applied. Enhanced fullband speech signals are finally obtained by combining the enhanced subband speech signals. Using a frame-based algorithm, autocorrelation functions of subband speech are calculated and the Yuler-Walker equations are solved to obtain the AR parameters. Simulation results show that Kalman filtering in the subband domain not only greatly reduces the computational complexity, but also achieves better performance compared to that in the fullband domain.
{"title":"Frame-based subband Kalman filtering for speech enhancement","authors":"Wen-Rong Wu, Po-Chen Chen, Hwai-Tsu Chang, Chun-Hung Kuo","doi":"10.1109/ICOSP.1998.770303","DOIUrl":"https://doi.org/10.1109/ICOSP.1998.770303","url":null,"abstract":"Kalman filtering is an effective speech enhancement technique, in which speech and noise signals are usually modeled as autoregressive (AR) processes and represented in the state-space domain. Since AR coefficient identification and Kalman filtering require extensive computations, practical implementation of this approach is difficult. This paper proposes a simple and practical scheme that overcomes these problems. Speech signals are first decomposed into subbands. Subband speech signals are then modeled as low-order AR processes, such that low-order Kalman filters can be applied. Enhanced fullband speech signals are finally obtained by combining the enhanced subband speech signals. Using a frame-based algorithm, autocorrelation functions of subband speech are calculated and the Yuler-Walker equations are solved to obtain the AR parameters. Simulation results show that Kalman filtering in the subband domain not only greatly reduces the computational complexity, but also achieves better performance compared to that in the fullband domain.","PeriodicalId":145700,"journal":{"name":"ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116615549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-10-12DOI: 10.1109/ICOSP.1998.770275
H.R.S. Mohammadi
Sorted codebook vector quantization (SCVQ) is shown to be a very efficient vector quantization method. Generalization of SCVQ is suggested and its application to the spectral coding of speech using the quantization of line spectral frequencies (LSF), which are the most popular parameters to represent the linear prediction model for spectrum quantization in speech coders, is described. Computer simulations are conducted to evaluate the performance of the new method. We demonstrate that the new method achieves superior quality and has low implementation costs.
{"title":"Spectral coding of speech based on generalized sorted codebook vector quantization","authors":"H.R.S. Mohammadi","doi":"10.1109/ICOSP.1998.770275","DOIUrl":"https://doi.org/10.1109/ICOSP.1998.770275","url":null,"abstract":"Sorted codebook vector quantization (SCVQ) is shown to be a very efficient vector quantization method. Generalization of SCVQ is suggested and its application to the spectral coding of speech using the quantization of line spectral frequencies (LSF), which are the most popular parameters to represent the linear prediction model for spectrum quantization in speech coders, is described. Computer simulations are conducted to evaluate the performance of the new method. We demonstrate that the new method achieves superior quality and has low implementation costs.","PeriodicalId":145700,"journal":{"name":"ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115260751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-10-12DOI: 10.1109/ICOSP.1998.770335
P. Skocir, B. Marusic, J. Tasic
We present the results of a preliminary study of enhancement of images that have been degraded by lossy wavelet coding algorithms. In this preliminary study we tested a large set of (nonlinear) image enhancement algorithms. The results have been evaluated using a simple objective criterion, which has been found to have reasonable correlation to subjective quality estimation for wavelet-degraded images. We first discuss some of the aspects of lossy wavelet coding and the associated degradation. Then we briefly outline the proposed quality measure. Finally we present the postprocessing algorithm which was found to be optimal for image enhancement after the abovementioned kind of degradation.
{"title":"Evaluation of postprocessing stages for wavelet-compressed image enhancement based on a simple perceptual criteria","authors":"P. Skocir, B. Marusic, J. Tasic","doi":"10.1109/ICOSP.1998.770335","DOIUrl":"https://doi.org/10.1109/ICOSP.1998.770335","url":null,"abstract":"We present the results of a preliminary study of enhancement of images that have been degraded by lossy wavelet coding algorithms. In this preliminary study we tested a large set of (nonlinear) image enhancement algorithms. The results have been evaluated using a simple objective criterion, which has been found to have reasonable correlation to subjective quality estimation for wavelet-degraded images. We first discuss some of the aspects of lossy wavelet coding and the associated degradation. Then we briefly outline the proposed quality measure. Finally we present the postprocessing algorithm which was found to be optimal for image enhancement after the abovementioned kind of degradation.","PeriodicalId":145700,"journal":{"name":"ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115595828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-10-12DOI: 10.1109/ICOSP.1998.770871
Zhang Qing, Wang Shu
The ART-2 neural network is a self-organized artificial network that operates according to adaptive resonance theory. A neuro-fuzzy network, which combines ART-2 and the fuzzy system in series, is presented and applied to fire detection. The results of experiments show that this system has a stronger ability to adapt to the environment than the backpropagation (BP) neural network. It can detect various standard test fires more rapidly and accurately, and has strong anti-interference capability.
{"title":"A fire detection system based on ART-2 neuro-fuzzy network","authors":"Zhang Qing, Wang Shu","doi":"10.1109/ICOSP.1998.770871","DOIUrl":"https://doi.org/10.1109/ICOSP.1998.770871","url":null,"abstract":"The ART-2 neural network is a self-organized artificial network that operates according to adaptive resonance theory. A neuro-fuzzy network, which combines ART-2 and the fuzzy system in series, is presented and applied to fire detection. The results of experiments show that this system has a stronger ability to adapt to the environment than the backpropagation (BP) neural network. It can detect various standard test fires more rapidly and accurately, and has strong anti-interference capability.","PeriodicalId":145700,"journal":{"name":"ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116159744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-10-12DOI: 10.1109/ICOSP.1998.770326
Lin Wenjing, Li Wangchao
Fractal coding is a very promising technique for image compression. However, it has not been widely used because of its long encoding time and high computational complexity. This paper presents a fast fractal image coding technique and its algorithm. Experimental results show that the proposed method is both effective and efficient.
{"title":"A fast fractal image coding technique","authors":"Lin Wenjing, Li Wangchao","doi":"10.1109/ICOSP.1998.770326","DOIUrl":"https://doi.org/10.1109/ICOSP.1998.770326","url":null,"abstract":"Fractal coding is a very promising technique for image compression. However, it has not been widely used because of its long encoding time and high computational complexity. This paper presents a fast fractal image coding technique and its algorithm. Experimental results show that the proposed method is both effective and efficient.","PeriodicalId":145700,"journal":{"name":"ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116575096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-10-12DOI: 10.1109/ICOSP.1998.770829
Z. Chi, Jun Kong
Image content classification is a very important step in document image analysis and understanding, and page-segmentation-based document image compression. In this paper, we present an new approach to classifying image content using block Kolmogorov complexity (KC) measures. A binarized two-dimensional image is first partitioned into blocks and each block image is converted into a one-dimensional binary sequence using either horizontal or vertical scanning. The block complexities are then computed over the obtained binary sequences. An image is classified into one of two categories, textual or pictorial images, using two fuzzy rules with the mean value and the standard deviation of block complexities. Experimental results on eight Chinese/English textual images of different fonts and eight different pictorial images show that our approach is reliable in discriminating these two types of images. Moreover, the performance of our method, where a training process is not required, is comparable to that of a neural network technique.
{"title":"Image content classification using a block Kolmogorov complexity measure","authors":"Z. Chi, Jun Kong","doi":"10.1109/ICOSP.1998.770829","DOIUrl":"https://doi.org/10.1109/ICOSP.1998.770829","url":null,"abstract":"Image content classification is a very important step in document image analysis and understanding, and page-segmentation-based document image compression. In this paper, we present an new approach to classifying image content using block Kolmogorov complexity (KC) measures. A binarized two-dimensional image is first partitioned into blocks and each block image is converted into a one-dimensional binary sequence using either horizontal or vertical scanning. The block complexities are then computed over the obtained binary sequences. An image is classified into one of two categories, textual or pictorial images, using two fuzzy rules with the mean value and the standard deviation of block complexities. Experimental results on eight Chinese/English textual images of different fonts and eight different pictorial images show that our approach is reliable in discriminating these two types of images. Moreover, the performance of our method, where a training process is not required, is comparable to that of a neural network technique.","PeriodicalId":145700,"journal":{"name":"ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115616110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-10-12DOI: 10.1109/ICOSP.1998.770203
Su Cheol Kang, Sang Min Lee, S. Hong
In this paper we proposed a new wavelet filtering technique to reduce the speckle noise in ultrasound images. The advantages of this approach are demonstrated in echocardiographic image enhancement and in comparison with other techniques. Wavelet signal processing provides a multiresolution decomposition. The fact that wavelet approaches tend to concentrate energy near edge features makes the result rather different than that found in standard Fourier based approaches. For speckle noise, the time and frequency localization capabilities of wavelets provide better noise reduction and less signal distortion than direct filtering of data. A technical method of noise filtering for reducing speckle noise in ultrasound images is presented. Experimental results are presented to illustrate the application of these techniques to echocardiographic images. Application of the proposed method to echocardiographic images has demonstrated that the results produced have high potential for use as inputs for a further automated interpretation stage.
{"title":"Noise reduction of echocardiographic images using wavelet filtering","authors":"Su Cheol Kang, Sang Min Lee, S. Hong","doi":"10.1109/ICOSP.1998.770203","DOIUrl":"https://doi.org/10.1109/ICOSP.1998.770203","url":null,"abstract":"In this paper we proposed a new wavelet filtering technique to reduce the speckle noise in ultrasound images. The advantages of this approach are demonstrated in echocardiographic image enhancement and in comparison with other techniques. Wavelet signal processing provides a multiresolution decomposition. The fact that wavelet approaches tend to concentrate energy near edge features makes the result rather different than that found in standard Fourier based approaches. For speckle noise, the time and frequency localization capabilities of wavelets provide better noise reduction and less signal distortion than direct filtering of data. A technical method of noise filtering for reducing speckle noise in ultrasound images is presented. Experimental results are presented to illustrate the application of these techniques to echocardiographic images. Application of the proposed method to echocardiographic images has demonstrated that the results produced have high potential for use as inputs for a further automated interpretation stage.","PeriodicalId":145700,"journal":{"name":"ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121521917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-10-12DOI: 10.1109/ICOSP.1998.770820
Guojun Lu, J. Phillips
In common colour-based image retrieval, colour histograms for images in the database and queries are calculated. The distance between a query and each of the database images is calculated as the sum of the absolute values of bin-to-bin differences between their histograms. The method ignores colour similarity between bins, leading to cases where perceptually similar images have very large histogram distances. In this paper, we propose to use perceptually weighted histograms (PWH) to overcome the problem. In PWH, a pixel contributes weights to a number of perceptually similar bins instead of a single bin. The contributing weights are inversely proportional to the distance between the pixel and bins.
{"title":"Using perceptually weighted histograms for colour-based image retrieval","authors":"Guojun Lu, J. Phillips","doi":"10.1109/ICOSP.1998.770820","DOIUrl":"https://doi.org/10.1109/ICOSP.1998.770820","url":null,"abstract":"In common colour-based image retrieval, colour histograms for images in the database and queries are calculated. The distance between a query and each of the database images is calculated as the sum of the absolute values of bin-to-bin differences between their histograms. The method ignores colour similarity between bins, leading to cases where perceptually similar images have very large histogram distances. In this paper, we propose to use perceptually weighted histograms (PWH) to overcome the problem. In PWH, a pixel contributes weights to a number of perceptually similar bins instead of a single bin. The contributing weights are inversely proportional to the distance between the pixel and bins.","PeriodicalId":145700,"journal":{"name":"ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121899348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-10-12DOI: 10.1109/ICOSP.1998.770145
Wang Chengyi, Wang Hongyu
Conventional estimation methods for the cyclic spectra of cyclostationary processes are the temporally smoothed cyclic periodogram and the spectrally smoothed cyclic periodogram. In the case of short data records, both methods have low resolution and bad reliability. This paper uses maximum likelihood filters with modified analysis effective bandwidth to estimate cyclic spectra. Good performance in terms of resolution and reliability can be obtained using this method.
{"title":"Estimation of cyclic spectra using maximum likelihood filters","authors":"Wang Chengyi, Wang Hongyu","doi":"10.1109/ICOSP.1998.770145","DOIUrl":"https://doi.org/10.1109/ICOSP.1998.770145","url":null,"abstract":"Conventional estimation methods for the cyclic spectra of cyclostationary processes are the temporally smoothed cyclic periodogram and the spectrally smoothed cyclic periodogram. In the case of short data records, both methods have low resolution and bad reliability. This paper uses maximum likelihood filters with modified analysis effective bandwidth to estimate cyclic spectra. Good performance in terms of resolution and reliability can be obtained using this method.","PeriodicalId":145700,"journal":{"name":"ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123711309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：