3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the最新文献

筛选
英文 中文
Probabilistic neural network analysis of quantitative nuclear features in predicting the risk of cancer recurrence at different follow-up times 定量核特征的概率神经网络分析在预测不同随访时间肿瘤复发风险中的应用
P. Petalas, P. Spyridonos, D. Glotsos, Dionisis A. Cavouras, P. Ravazoula, G. Nikiforidis
{"title":"Probabilistic neural network analysis of quantitative nuclear features in predicting the risk of cancer recurrence at different follow-up times","authors":"P. Petalas, P. Spyridonos, D. Glotsos, Dionisis A. Cavouras, P. Ravazoula, G. Nikiforidis","doi":"10.1109/ISPA.2003.1296438","DOIUrl":"https://doi.org/10.1109/ISPA.2003.1296438","url":null,"abstract":"This paper explores the prognostic significance of automatically generated features from biopsies of superficial transitional cell carcinomas (TCCs) of urinary bladder in predicting the time interval in which the tumor is more likely to recur. Clinical material comprised 73 patients diagnosed with superficial TCC and followed-up for at least 60 months. Patients' data set was separated into three prognostic groups in respect to time interval in which the tumor may recur. For each case, 40 descriptive quantitative features related to nuclear characteristics were generated. The prognostic value of the estimated features was analyzed by means of a probabilistic neural network (PNN) classifier. To find best vector combination leading to the smallest classification error, an exhaustive search procedure in feature space was utilized. Classifier performance was evaluated by means of the leave-one-out method. Throughout the analysis of the prognostic feature combinations, four features, two describing nuclear texture, and two related to shape distribution of nuclei in the sample, were identified as the important markers for patients' outcome prediction. The overall predictive accuracy was 73%. Intermediate and long-term recurrent cases were identified with an accuracy of 76%. For the short-term group the predictive accuracy was 63%. The detection of recurrences in certain future time seems feasible by analyzing the prognostic information of nuclear features and incorporating the PNN model. The improvement in prognostic ability may be clinically important for patient follow-up, and therapeutic treatment.","PeriodicalId":218932,"journal":{"name":"3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121085947","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}
引用次数: 6
Directional analysis of image textures for feature extraction and segmentation 用于特征提取和分割的图像纹理方向分析
I. Kontaxakis, E. Sangriotis, D. Martakos
{"title":"Directional analysis of image textures for feature extraction and segmentation","authors":"I. Kontaxakis, E. Sangriotis, D. Martakos","doi":"10.1109/ISPA.2003.1296872","DOIUrl":"https://doi.org/10.1109/ISPA.2003.1296872","url":null,"abstract":"This paper describes a new approach for texture feature extraction, appropriate for unsupervised image segmentation applications. The pixel features are obtained by using directional filters to analyze the given image to a set of subimages, each one containing an isolated angular section of the initial image spectrum, and estimating the pixel local energy in them. By incorporating the proposed feature extraction technique into a single multicomponent texture segmentation procedure, some experiments with texture separation have been implemented and the effectiveness of the presented method has been tested. The results are presented and a comparison with feature extraction techniques, based on the discrete wavelet decomposition of the image, is made.","PeriodicalId":218932,"journal":{"name":"3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127367260","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}
引用次数: 4
A novel morphological subband decomposition scheme for 2D+t wavelet video coding 一种新的二维+t小波视频编码形态学子带分解方案
G. Abhayaratne, H. Heijmans
{"title":"A novel morphological subband decomposition scheme for 2D+t wavelet video coding","authors":"G. Abhayaratne, H. Heijmans","doi":"10.1109/ISPA.2003.1296901","DOIUrl":"https://doi.org/10.1109/ISPA.2003.1296901","url":null,"abstract":"Interframe or 2D+t wavelet video coding leads to a scalable video coding framework with all three scalabilities: quality (PSNR), spatial and temporal. One of the major challenges in the 2D+t frame work is the spatial (2D) decomposition of detail frames produced by the temporal decomposition process (t). Detail frames are different from still images so that better coding performance can be achieved by using nonlinear spatial decomposition techniques. In this paper, a wavelet transform based on a novel morphological operator, the complete inf-semilattice (or cist-) erosion, is presented and its coding performances for detail frames are compared with the existing nonlinear transforms based on the median operator and linear wavelet transforms used in still image coding. The simulation results show that the cisl-erosion based wavelet decomposition outperforms the median based wavelet decomposition for all temporal subbands and performs better or comparably with the 5/3 biorthogonal wavelet transform in most cases.","PeriodicalId":218932,"journal":{"name":"3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127506670","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}
引用次数: 9
A coding method for UVLC targeting efficient decoder architecture 一种针对高效解码器结构的UVLC编码方法
Shang Xue, B. Oelmann
{"title":"A coding method for UVLC targeting efficient decoder architecture","authors":"Shang Xue, B. Oelmann","doi":"10.1109/ISPA.2003.1296935","DOIUrl":"https://doi.org/10.1109/ISPA.2003.1296935","url":null,"abstract":"Variable length code (VLC) is used in a large variety of lossless compression applications. A specially designed VLC, called \"universal variable length code\" (UVLC), is utilized in the latest video coding standard H.26L under development. In this work we propose a coding method that we call \"alternating coding\" (ALT coding) for UVLC. An efficient UVLC decoder is designed (ALT decoder) on the basis of it. ALT coding facilitates a much easier decoding scheme for UVLC. It frees the decoder from codeword tables and the sizes of the barrel shifters are reduced. The codeword tables and barrel shifters usually occupy the largest portion of the area in the traditional VLC decoders and they are also performance limiting in terms of speed and power consumption. We compare the ALT decoder with one of the most efficient VLC decoders called \"VLC decoder using plane separation\" (PLS). Our results show that the ALT decoder increases 257% in speed, decreases 41% in size, and consumes 45% power of the PLS decoder.","PeriodicalId":218932,"journal":{"name":"3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125862074","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}
引用次数: 5
A hybrid fingerprint matcher in memory constrained environments 内存受限环境下的混合指纹匹配器
V. Krivec, J. Birchbauer, W. Marius, H. Bischof
{"title":"A hybrid fingerprint matcher in memory constrained environments","authors":"V. Krivec, J. Birchbauer, W. Marius, H. Bischof","doi":"10.1109/ISPA.2003.1296350","DOIUrl":"https://doi.org/10.1109/ISPA.2003.1296350","url":null,"abstract":"Hybrid fingerprint matchers are well known as a powerful tool for high security applications where the reliability of a single fingerprint characteristic is not high enough for the intended application. In this paper, we propose a novel method, which due to its compressibility can be applied in memory constrained environments. This is important for application in smart cards and independent identification modules, which recently gained popularity. The proposed method uses minutia point matcher as the first stage of matching, and, after successfully completing this stage, the second stage of matching is based on comparing the homogeneity of a direction map. The direction map is compressed using a quad tree.","PeriodicalId":218932,"journal":{"name":"3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123283843","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}
引用次数: 8
A new sinusoidal modelling approach for parametric speech and audio coding 一种新的正弦建模方法用于参数化语音和音频编码
P. Vera-Candeas, N. Ruiz-Reyes, J. Curpián-Alonso, M. Rosa-Zurera
{"title":"A new sinusoidal modelling approach for parametric speech and audio coding","authors":"P. Vera-Candeas, N. Ruiz-Reyes, J. Curpián-Alonso, M. Rosa-Zurera","doi":"10.1109/ISPA.2003.1296882","DOIUrl":"https://doi.org/10.1109/ISPA.2003.1296882","url":null,"abstract":"In this paper we propose a new approach based on energy-adaptive matching pursuits to improve sinusoidal modelling for parametric speech and audio coding. To reduce the complexity of the algorithm, an over-complete dictionary composed of complex exponentials is used. An analysis-synthesis windows scheme that avoids overlapping is proposed. For efficient quantization of sinusoidal model parameters, a new algorithm that largely reduces the side information required by the decoder is described. Experimental results show evidence of the advantages of the proposed method to be integrated into multi-pans models for parametric speech/audio coding.","PeriodicalId":218932,"journal":{"name":"3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125278231","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}
引用次数: 0
Video coding rate control strategy based on the characteristics of picture 基于图像特性的视频编码速率控制策略
L. Xiaohui, Wu Xiaopei
{"title":"Video coding rate control strategy based on the characteristics of picture","authors":"L. Xiaohui, Wu Xiaopei","doi":"10.1109/ISPA.2003.1296913","DOIUrl":"https://doi.org/10.1109/ISPA.2003.1296913","url":null,"abstract":"An improved rate control strategy is proposed, which allocates the target number of bits at first on picture layer. And then different types of pictures respectively are processed on the basis of picture characteristics when each frame is coded. Finally, a quantization parameter is selected for each macroblock with different characteristics in a coded frame. As a result, the number of bits for each frame picture is allocated more reasonably, and the subjective and objective quality of the picture constructed at the decoding end can be raised, especially in some important detailed parts. The experiment shows that this rate control strategy can effectively avoid the overflow and underflow of the encoder buffer, and the output bit rates incline to stabilization.","PeriodicalId":218932,"journal":{"name":"3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125366272","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}
引用次数: 0
Single chip FPGA realization of a 2D multicomponent wavelet transform 单片机FPGA实现二维多分量小波变换
O. Venard, R. Lionti, L. Chra
{"title":"Single chip FPGA realization of a 2D multicomponent wavelet transform","authors":"O. Venard, R. Lionti, L. Chra","doi":"10.1109/ISPA.2003.1296946","DOIUrl":"https://doi.org/10.1109/ISPA.2003.1296946","url":null,"abstract":"In this paper we describe a 2D wavelet transform (WT) implementation intended for color image compression. The proposed implementation handles the data stream on the YUV color space thanks to a multicomponent approach of the wavelet transform. The 2D WT is conducted in a separable manner by means of the 5-3 biorthogonal filters. This leads to a multiplier-less and low-latency on-line running computation, realization of a 2D multicomponent forward and inverse discrete wavelet transform (DWT) on a single FPGA chip.","PeriodicalId":218932,"journal":{"name":"3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125517101","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}
引用次数: 0
Design of optimum recursive digital filters with double zeros on the unit circle leading to symmetric ladder wave digital filter structures 单位圆上双零的最佳递归数字滤波器的设计导致对称阶梯波数字滤波器结构
B. Soltanian, T. Saramaki, H. Johansson
{"title":"Design of optimum recursive digital filters with double zeros on the unit circle leading to symmetric ladder wave digital filter structures","authors":"B. Soltanian, T. Saramaki, H. Johansson","doi":"10.1109/ISPA.2003.1296865","DOIUrl":"https://doi.org/10.1109/ISPA.2003.1296865","url":null,"abstract":"A class of odd-order low-pass recursive digital filters leading to symmetric ladder wave digital (LWD) filter implementations is introduced. In the pass-band, these filters have the same equiripple performance as elliptic filters of the same order, whereas in the stop-band there are the maximum numbers of double zeros. This implies that if the odd filter order is 2M+1, then, in addition to a single zero at z = 1, the proposed filter has M/2 complex-conjugate double zero pairs [(M-1)/2 double and one single complex-conjugate zero pair] on the unit circle for M even [odd]. By slightly modifying an algorithm proposed earlier by the second author, a very fast iterative technique is developed for designing these filters to exhibit also an equiripple stop-band performance. When implemented using LWD filter structures, the proposed filters have the following two benefits compared to elliptic filters. First, the resulting structure becomes symmetric, which reduces the number of distinct multipliers by a factor of two. Second, the maximum amplitude value remains to be unity as well as the two outputs of the LWD structure remain power complementary also after quantizing the coefficient values (without additional scaling operations being needed when implementing elliptic filters.) Examples are included illustrating that the price to be paid for these attractive properties is only a 3- to 5-dB reduction in the stop-band attenuation.","PeriodicalId":218932,"journal":{"name":"3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115589552","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}
引用次数: 1
Versatile analogue motion estimator architecture 通用模拟运动估计器架构
M. Panovic, A. Demosthenous
{"title":"Versatile analogue motion estimator architecture","authors":"M. Panovic, A. Demosthenous","doi":"10.1109/ISPA.2003.1296423","DOIUrl":"https://doi.org/10.1109/ISPA.2003.1296423","url":null,"abstract":"A motion estimator architecture based on analogue subsystems is presented which meets the requirements of several different video coding standards. The proposed architecture allows motion estimation parameters to be changed to meet various video standards without redesigning the hardware. Moreover, it offers reductions in size, power dissipation and consequently cost, over digital implementations, while maintaining the versatility of the digital approach. Simulated results indicate that the architecture is not sensitive to errors usually associated with the use of analogue circuits.","PeriodicalId":218932,"journal":{"name":"3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122092625","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}
引用次数: 3
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信