Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing最新文献_第3页

A speech recognizer with low complexity based on RNN 基于RNN的低复杂度语音识别器

Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514901

K. Kasper, H. Reininger, D. Wolf, H. Wust

引用次数: 4

A neural network approach to face/palm recognition 人脸/手掌识别的神经网络方法

Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514906

S. Kung, Shang-Hung Lin, M. Fang

{"title":"A neural network approach to face/palm recognition","authors":"S. Kung, Shang-Hung Lin, M. Fang","doi":"10.1109/NNSP.1995.514906","DOIUrl":"https://doi.org/10.1109/NNSP.1995.514906","url":null,"abstract":"This paper proposes a face/palm recognition system based on decision-based neural networks (DBNN). The face recognition system consists of three modules. First, the face detector finds the location of a human face in an image. The eye localizer determines the positions of both eyes in order to generate meaningful feature vectors. The facial region proposed contains eyebrows, eyes, and nose, but excluding mouth. (Eye-glasses will be permissible.) Lastly, the third module is a face recognizer. The DBNN can be effectively applied to all the three modules. It adopts a hierarchical network structures with nonlinear basis functions and a competitive credit-assignment scheme. The paper demonstrates its successful application to face recognition applications on both the public (FERET) and in-house (SCR) databases. In terms of speed, given the extracted features, the training phase for 100-200 persons would take less than one hour on Sparc10. The whole recognition process (including eye localization, feature extraction, and classification using DBNN) may consume only a fraction of a second on Sparc10. Experiments on three different databases all demonstrated high recognition accuracies. A preliminary study also confirms that a similar DBNN recognizer can effectively recognize palms, which could potentially offer a much more reliable biometric feature.","PeriodicalId":403144,"journal":{"name":"Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing","volume":"270 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127547357","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: 58

An error diffusion neural network for digital image halftoning 数字图像半调误差扩散神经网络

Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514917

B. Shoop, E. Ressler

引用次数: 11

Neural network-based image segmentation for image interpolation 基于神经网络的图像分割图像插值

Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514913

N. Marsi, Sergio Carrato

引用次数: 7

Design and evaluation of neural classifiers application to skin lesion classification 神经分类器在皮肤病变分类中的设计与评价

Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514923

Mads I-Iintz-hladsen, Lars Kai Hansen, Jan Larsen, Eric Olesen, Icrzysztof T. Drzewiecki

引用次数: 24

Intelligent network monitoring 智能网络监控

Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514927

C. Hood, C. Ji

引用次数: 5

Hierarchical mixtures of experts methodology applied to continuous speech recognition 层次混合专家方法在连续语音识别中的应用

Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514900

Ying Zhao, R. Schwartz, J. Sroka, J. Makhoul

引用次数: 4

A study of the application of the CMAC artificial neural network to the problem of gas sensor array calibration CMAC人工神经网络在气体传感器阵列标定问题中的应用研究

Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514924

P.M. Bajaria, B. Segee

引用次数: 0

Estimating image velocity with convected activation profiles: analysis and improvements for special cases 用对流激活剖面估计图像速度:特殊情况的分析与改进

Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514909

R. Cunningham, A. Waxman

{"title":"Estimating image velocity with convected activation profiles: analysis and improvements for special cases","authors":"R. Cunningham, A. Waxman","doi":"10.1109/NNSP.1995.514909","DOIUrl":"https://doi.org/10.1109/NNSP.1995.514909","url":null,"abstract":"The method of convected activation profiles was developed to measure short-range visual motion of edge and point features in time-varying imagery. Each feature is assumed to generate a spatiotemporal Gaussian activation profile that results in a shape-preserved activity wave that is convected along with that feature, and the phase velocity of the wave provides a velocity estimate of the feature. By this method, both explicit feature tracking (a complex and computationally expensive operation) and the assumption that intensity is convected (which is rarely justified) are avoided. The method is suitable for real-time implementations and can be described in terms of shunting dynamics of neural systems. Spatiotemporal filters that measure the velocity of lines and points were described and demonstrated in the earlier work: this paper presents a detailed analysis of the accuracy of the method in scenes consisting of highly textured objects with fixed projections onto the image plane. We also describe how to accurately measure the velocity of short lines and line ends; in the past the velocity of short lines was severely underestimated, and the velocity of line ends could only be measured by recognizing line end features and evaluating the speed of these \"point\" features in isolation. This new method simplifies velocity extraction yet requires no additional computation. Finally, we clarify our earlier suggestion for selecting a velocity estimate from among several filters of different scales.","PeriodicalId":403144,"journal":{"name":"Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133030412","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

Channel equalization by finite mixtures and the EM algorithm 有限混合信道均衡与EM算法

Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514935

L. Xu

引用次数: 5