检索结果-内蒙古大学图书馆

4th workshop on artificial neural networks in pattern recognition

作者： Sohail, Abu Sayeed Md Bhattacharya, Prabir Mudur, Sudhir P. Krishnamurthy, Srinivasan Gilbert, Lucy Concordia Univ Dept Comp Sci & Software Engn Montreal PQ Canada Univ Cincinnati Dept Comp Sci Cincinnati OH 45221 USA Royal Victoria Hosp Dept Obstet & Gynaecol Montreal PQ H3A 1A1 Canada

ISBN: (纸本)9783642121586

This paper presents a combined method of content-based retrieval and classification of ultrasound medical images representing three types of ovarian cysts: Simple Cyst, Endometrioma, and Teratoma. Combination of histogram moments and Gray Level Co-Occurrence Matrix (GLCM) based statistical texture descriptors has been proposed as the features for retrieving and classifying ultrasound images. To retrieve images, relevance between the query image and the target images has been measured using a similarity model based on Gower's similarity coefficient. Image classification has been performed applying Fuzzy k-Nearest Neighbour (k-NN) classification technique. A database of 478 ultrasound ovarian images has been used to verify the retrieval and classification accuracy of the proposed system. In retrieving ultrasound images, the proposed method has demonstrated above 79% and 75% of average precision considering the first 20 and 40 retrieved images respectively. Further, 88.12% of average classification accuracy has been achieved in classifying ultrasound images using the proposed method.

关键词： Ultrasound Medical Image Retrieval Ovarian Cyst Classification Texture Feature Histogram Moments Fuzzy k-NN

来源：评论

学校读者我要写书评

暂无评论

Part-based high accuracy recognition of serial numbers in bank notes 6

引用

6th iapr TC3 International workshop on artificial neural networks for pattern recognition, ANNPR 2014

作者： Feng, Bo-Yuan Ren, Mingwu Zhang, Xu-Yao Suen, Ching Y. School of Computer Science Nanjing University of Science and Technology Nanjing210094 China National Laboratory of Pattern Recognition Institute of Automation of Chinese Academy of Sciences Beijing100190 China Centre for Pattern Recognition and Machine Intelligence Concordia University MontrealH3G 1M8 Canada

ISBN: (纸本)9783319116556

This paper proposes a novel part-based character recognition method for a new topic of RMB (renminbi bank note, the paper currency used in China) serial number recognition, which is important for reducing financial crime and improving financial market stability and social security. Given an input sample, we first generate a set of local image parts using the Difference-of-Gaussians (DoG) keypoint detector. Then, all of the local parts are classified by an SVM classifier to provide a confidence vector for each part. Finally, three methods are introduced to combine the recognition results of all parts. Since the serial number samples suffer from complex background, occlusion, and degradation, our part-based method takes advantage of both global and local character structure features, and offers an overall increase in robustness and reliability to the entire recognition system. Experiments conducted on a RMB serial number character database show that the test accuracy boosted from 98.90% to 99.33% by utilizing the proposed method with multiple voting based combination strategy. The part-based recognition method can also be extended to other types of banknotes, such as Euro, U.S. and Canadian dollars, or in character recognition applications with complex backgrounds. © Springer International Publishing Switzerland 2014.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

The effect of fuzzy training targets on voice quality classification

The effect of fuzzy training targets on voice quality classi...

引用

1st iapr TC3 workshop on Multimodal pattern recognition of Social Signals in Human-Computer-Interaction, MPRSS 2012

作者： Scherer, Stefan Kane, John Gobl, Christer Schwenker, Friedhelm Institute of Creative Technologies University of Southern California United States Phonetics and Speech Laboratory Trinity College Dublin Ireland Institute of Neural Information Processing Ulm University Germany

ISBN: (纸本)9783642370809

The dynamic use of voice qualities in spoken language can reveal useful information on a speaker's attitude, mood and affective states. This information may be desirable for a range of speech technology applications. However, annotation of voice quality may frequently be inconsistent across raters. But whom should one trust or is the truth somewhere in between? The current study looks first to describe a voice quality feature set that is suitable for differentiating voice qualities on a tense to breathy dimension. These features are used as inputs to a fuzzy-input fuzzy-output support vector machine (F 2SVM) algorithm, to automatically classify the voice qualities. The F2SVM is compared to standard approaches and shows promising results. Performances for cross validation, leave one speaker out, and cross corpus experiments of around 90% are achieved. © 2013 Springer-Verlag.

关键词： artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Unsupervised spatial pattern classification of electrical-wafer-sorting maps in semiconductor manufacturing

引用

pattern recognition LETTERS 2005年第12期26卷 1857-1865页

作者： Di Palma, F De Nicolao, G Miraglia, G Pasquinetti, E Piccinini, F Univ Pavia Dipartimento Informat & Sistemist I-27100 Pavia Italy STMicroelect I-20041 Agrate Brianza Italy

in semiconductor manufacturing, the spatial pattern of failed devices in a wafer can give precious hints on which step of the process is responsible for the failures. In the literature, Kohonen's Self Organizing Feature Maps (SOM) and Adaptive Resonance Theory 1 (ART1) architectures have been compared, concluding that the latter are to be preferred. However, both the simulated and the real data sets used for validation and comparison were very limited. In this paper, the use of ART1 and SOM as wafer classifiers is re-assessed on much more extensive simulated and real data sets. We conclude that ART1 is not adequate, whereas SOM provide completely satisfactory results including visually effective representation of spatial failure probability of the pattern classes. (c) 2005 Elsevier B.V. All rights reserved.

关键词： semiconductor manufacturing wafer maps self organizing feature maps adaptive resonance theory

来源：评论

学校读者我要写书评

暂无评论

Quasi-optimum combination of multilayer perceptrons for adaptive multiclass pattern recognition 3rd

引用

3rd International workshop on artificial neural networks, IWANN 1995

作者： García, Alberto Ruiz Areas Túnez, Francisco J. Departamento de Informática y Sistemas Universidad de Murcia Spain

ISBN: (纸本)3540594973

Standard multiclass pattern recognition requires frequent re-learning stages when the set of categories of interest evolves in time. In order to minimize the computation costs of class incorporation and removal, we divide the global multiclass recognizer into a collection of class pairwise neural dichotomizers. When a new class appears, an adequate set of dichotomizers is created and trained to discriminate the new class from the rest. If a class disappears, its associated diehotomizers are eliminated In both cases previously learned knowledge is not disturbed. The properties of neural recognizers and pairwise modularization allow an analytic quasi-optimum method for combining network outputs to obtain the global multiclass response. An incremental and distributed pattern recognition architecture is presented and its performance experimentally evaluated, obtaining better error rates and learning times than conventional multiclass recognizers using similar resources. The design is highly parallel and asyncronous, adequate for dynamic real time applications. © 1995, Springer Verlag. All rights reserved.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Creating Emotion recognition Algorithms Based on a Convolutional neural Network for Sentiment Analysis 3rd

Creating Emotion Recognition Algorithms Based on a Convoluti...

引用

3rd International workshop on Reproducible Research in pattern recognition, RRPR 2021

作者： Ivanyuk, Vera Tsapina, Ekaterina Financial University under the Government of the Russian Federation Moscow Russia Bauman Moscow State Technical University Moscow Russia

ISBN: (纸本)9783030764227

The objective of the research is the development and evaluation testing of a speed-optimized «Dual-trained Lazy CNN» neural network model for language-dependent sentiment analysis in Slavic languages in specific cultural context, as well as the software implementation of the resulting network. Convolutional neural networks are easy to train and implement. To train them, a standard error back propagation algorithm is used, and because the filter weights are evenly distributed the number of parameters in the convolutional neural network is small. From the viewpoint of computational linguistics, convolutional neural networks are a powerful tool for classification, that, however, does not have any language intuition, which significantly complicates the analysis of algorithm errors. However, it is convolutional networks that are widely used in text data analysis tasks. neural networks always work with big data and often require a lot of processing power. Therefore, to simplify computations, it makes sense to use «lazy» NNs. A «lazy» neural network is a network, which, if it receives input data that repeats the patterns that were previously processed by it, returns a result that was obtained earlier. © 2021, Springer Nature Switzerland AG.

关键词： Emotion recognition

来源：评论

学校读者我要写书评

暂无评论

Improving Audio-Visual Speech recognition Using Gabor Recurrent neural networks 1

引用

5th iapr TC 9 workshop on pattern recognition of Social Signals in Human-Computer-Interaction (MPRSS)

作者： Saudi, Ali S. Khalil, Mahmoud I. Abbas, Hazem M. German Univ Cairo Fac Media Engn & Technol New Cairo Egypt Ain Shams Univ Fac Engn Cairo Egypt

ISBN: (数字)9783030209841

ISBN: (纸本)9783030209841;9783030209834

The performance of speech recognition systems can be significantly improved when visual information is used in conjunction with the audio ones, especially in noisy environments. Prompted by the great achievements of deep learning in solving Audio-Visual Speech recognition (AVSR) problems, we propose a deep AVSR model based on Long Short-Term Memory Bidirectional Recurrent neural Network (LSTM-BRNN). The proposed deep AVSR model utilizes the Gabor filters in both the audio and visual front-ends with Early Integration (EI) scheme. This model is termed as BRNNav model. The Gabor features simulate the underlying spatiotemporal processing chain that occurs in the Primary Audio Cortex (PAC) in conjunction with Primary Visual Cortex (PVC). We named it Gabor Audio Features (GAF) and Gabor Visual Features (GVF). The experimental results show that the deep Gabor (LSTM-BRNNs)-based model achieves superior performance when compared to the (GMM-HMM)-based models which utilize the same front-ends. Furthermore, the use of GAF and GVF in both audio and visual front-ends attain significant improvement in the performance compared to the traditional audio and visual features.

关键词： Audio-Visual Speech recognition Bidirectional Recurrent neural Network Gabor filters

来源：评论

学校读者我要写书评

暂无评论

Linear contrast classifiers in high-dimensional spaces 6

引用

6th iapr TC3 International workshop on artificial neural networks for pattern recognition, ANNPR 2014

作者： Schmid, Florian Lausser, Ludwig Kestler, Hans A. Medical Systems Biology and Institute of Neural Information Processing Ulm University Ulm89069 Germany

ISBN: (纸本)9783319116556

Linear classifiers are mainly discussed in terms of training algorithms that try to find an optimal hyperplane according to a data dependent objective. Such objectives might be the induction of a large margin or the reduction of the number of involved features. The underlying concept class of linear classifiers is analyzed less frequently. It is implicitly assumed that all classifiers of this function class share the same common *** this work we analyze the concept class of linear classifiers. We show that it includes different subclasses that show beneficial properties during the prediction phase. These properties can directly be derived from the structural form of the classifiers and must not be learned in a data dependent training phase. We describe the concept class of contrasts, a class of linear functions that is for example utilized in variance analyses. Models from this concept class share the common property of being invariant against global additive effects. We give a theoretical characterization of contrast classifiers and analyze the effects of replacing general linear classifiers by these new models in standard training algorithms. © Springer International Publishing Switzerland 2014.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Character recognition with neural assemblies 3rd

引用

3rd International workshop on artificial neural networks, IWANN 1995

作者： Vico, Francisco J. Ortega, F. Almaraz, J. Sandoval, F. E.T.S.I. de Telecomunicaciòn Dpto. Tecnologfa Electrìnica Dpto. Psicobiologfa Universidad de Màlaga Plaza E1 Ejido s/n Màlaga29013 Spain

ISBN: (纸本)3540594973

In living beings, any pattern recognition task involves complex processes of concepts formation. We propose a model based on the principle of neural assemblies to develop internal representations of characters. neural assemblies self-organize themselves by extracting the relevant information of the characters set depending on the previously stored characters. The principal consequences of this are that less storage capacity is needed, and it makes easer the clasiffication with a delta rule. Examples of this task are exposed, where it can be seen the way in which the assemblies store the characters, and how the classification of the internal representations is performed. © 1995, Springer Verlag. All rights reserved.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

3D motion estimation of human body from video with dynamic camera work

3D motion estimation of human body from video with dynamic c...

引用

1st iapr TC3 workshop on Multimodal pattern recognition of Social Signals in Human-Computer-Interaction, MPRSS 2012

作者： Ayumi, Matsumoto Wu, Xiaojun Harumi, Kawamura Akira, Kojima Nippon Telegraph and Telephone Corporation Japan NTT Communications Corporation Japan

ISBN: (纸本)9783642370809

Occlusion or camera setting produces a high degree of ambiguity when estimating human body motion from monocular video sequences. Good human motion models are an important means of addressing this problem. In this work, we propose a hierarchical motion model and a motion estimation for it to estimate human motion without camera calibration and with free camera operation. The model is able to generate particles in multi-spaces and thus is able to estimate both camera view and human motion at one time. We showed the possibility of achieving 3D motion estimation for simple movements such as "walking" without camera calibration and with dynamic camera operation. © 2013 Springer-Verlag.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：