检索结果-内蒙古大学图书馆

Moment-based approaches in imaging. Part 1. basic features

IEEE ENGINEERING IN MEDICINE AND BIOLOGY MAGAZINE 2007年第5期26卷 70-74页

作者： Shu, Huazhong Luo, Limin Coatrieux, Jean-Louis Southeast Univ Sch Engn & Comp Sci Nanjing 210096 Peoples R China INSERM U642 F-35000 Rennes France Univ Rennes 1 F-35000 Rennes France

This first article was aimed at providing the basic formulations of moments, a classification, and an introductory bibliography. This first part presents a classification of moments, and, rather than entering into theoretical details, it sketches their different expressions. The companion articles will review their properties and the potential contributions they already bring to imaging.

关键词： Biomedical imaging pattern recognition Deformable models Object segmentation computer vision Image reconstruction Object detection Image coding Application software Image processing

来源：评论

学校读者我要写书评

暂无评论

Precise acquisition and unsupervised segmentation of multi-spectral images

引用

computer vision AND IMAGE UNDERSTANDING 2007年第2-3期106卷 183-193页

作者： Delgado Gomez, David Clemmensen, Line Harder Ersboll, Bjarne K. Carstensen, Jens Michael Univ Pomeu Fabra Dept Technol Computat Imaging Lab Barcelona 08003 Spain Tech Univ Denmark DK-2800 Lyngby Denmark

In this work, an integrated imaging system to obtain accurate and reproducible multi-spectral images and a novel multi-spectral image segmentation algorithm are proposed. The system collects up to 20 different spectral bands within a range that vary from 395 nm to 970 nm. The system is designed to acquire geometrically and chromatically corrected images in homogeneous and diffuse illumination, so images can be compared over time. The proposed segmentation algorithm combines the information provided by all the spectral bands to segment the different regions of interest. Three experiments are conducted to show the ability of the system to acquire highly precise, reproducible and standardized multi-spectral images and to show its applicabilities in different situations. (C) 2006 Elsevier Inc. All rights reserved.

关键词： image acquisition multi-spectral image analysis illumination exploratory data analysis image segmentation pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Hardware implementation of image recognition system based on morphological associative memories and discrete wavelet transform

引用

2nd IEEE Pacific Rim Symposium on Video and Technology

作者： Guzman, Enrique Alvarado, Selene Pogrebnyak, Oleksiy Fernandez, Luis Pastor Sanchez Yanez, Cornelio Universidad Tecnológica de la Mixteca Centro de Investigación en Computación Instituto Politécnico Nacional

ISBN: (纸本)9783540771289

The implementation of a specific image recognition technique for an artificial vision system is presented. The proposed algorithm involves two steps. First, smaller images are obtained using Discrete Wavelet Transform (DWT) after four stages of decomposition and taking only the approximations. This way the volume of information to process is reduced considerably and the system memory requirements are reduced as well. Another purpose of DWT is to filter noise that could be induced in the images. Second, the Morphological Associative Memories (MAM) are used to recognize landmarks. The proposed algorithm provides flexibility, possibility to parallelize algorithms and high overall performance of hardware implemented image retrieval system. The resulted hardware implementation has low memory requirements, needs in limited arithmetical precision and reduced number of simple operations. These benefits are guaranteed due to the simplicity of MAM learning/restoration process that uses simple morphological operations, dilation and erosion, in other words, MAM calculate maximums or minimums of sums. These features turn out the artificial vision system to be robust and optimal for the use in real-time autonomous systems. The proposed image recognition system has, among others, the following useful features: robustness to the noise induced in the patter to process, high processing speed, and it can be easily adapted to diverse operation circumstances.

关键词： artificial vision image recognition morphological associative memories discrete wavelet transform hardware implementation

来源：评论

学校读者我要写书评

暂无评论

computer vision and pattern recognition

引用

INTERNATIONAL JOURNAL OF computer MATHEMATICS 2007年第9期84卷 1265-1266页

作者： Zheng, Nanning Loizou, George Jiang, Xiaoyi Lan, Xuguang Li, Xuelong Xian Jiaotong Univ Xian 710049 Peoples R China Univ London London WC1E 7HU England Univ Munster D-4400 Munster Germany

来源：评论

学校读者我要写书评

暂无评论

Contour detection based on contextual influences

引用

IMAGE AND vision COMPUTING 2007年第8期25卷 1282-1290页

作者： Tang, Qiling Sang, Nong Zhang, Tianxu Huazhong Univ Sci & Technol Inst Pattern Recognit & Artificial Intelligence Wuhan 430074 Peoples R China Minist Educ Image Proc & Intelligent Control Key Lab Wuhan 430074 Peoples R China

A contour detection model, inspired by the behavior of the primary visual cortex, is presented. The response of a central stimulus in the receptive field is affected by the presence of surrounding stimuli - for some stimulus conditions, the response is suppressed and for other conditions the response is enhanced. The visual mechanisms of contextual influences are utilized to extract "coherent" configurations. This is mainly due to the following two reasons: (1) on the one hand, a smooth contour can yield collinear excitation, which highlights smooth contours from irregularly textured surround;(2) on the other hand, similar orientation textures receive iso-orientation surround suppression and region boundary is subjected to the less inhibition, which makes boundary more salient for perceptual pop-out. Accordingly, smooth contours progressively stand out from their surround and at the same time textures are gradually suppressed by their surround through dynamic fine-tuning of contextual information. The proposed method which distinguishes between contours and texture edges is more effective for contour-based object recognition tasks. Initial experiments show that the model can be successfully applied to contour detection. Especially, when object contours are lumped together with unwantedly cluttered surround, the advantage of our approach is more prominent. This study provides a biological scheme for contour detection in computer vision. (c) 2006 Elsevier B.V. All rights reserved.

关键词： contour detection contextual influences visual mechanisms suppression enhancement

来源：评论

学校读者我要写书评

暂无评论

Particle filter based tracking for crossing of targets with similar pattern

Particle filter based tracking for crossing of targets with ...

引用

10th IAPR Conference on Machine vision Applications, MVA 2007

作者： Iwahori, Yuji Okada, Shinya Kawanaka, Haruki Fukui, Shinji Woodham, Robert J. Faculty of Engineering Chubu University Kasugai 487-8501 Japan Faculty of Info. Sci. and Tech. Aichi Pref. University Nagakute 480-1198 Japan Faculty of Education Aichi University of Education Kariya 448-8542 Japan Dept. of Computer Science University of British Columbia Vancouver BC V6T 1Z4 Canada

ISBN: (纸本)9784901122078

Tracking is an important topic in computer vision and object recognition. Recently, a probabilistic approach using particle filters has been applied to track moving objects. This kind of approach often uses a color histogram to estimate a likelihood function for probabilistic tracking. When two similar objects cross each other in view, the likelihood becomes high for both. This often causes tracking to fail. This paper proposes a new method to address the object crossing problem. The method estimates the object region, splits the region into horizontal zones, and calculates similarity based on each split region and each horizontal zone of the target. The new method makes the tracking of similar targets more robust when those targets cross. Results are demonstrated on real video sequences.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Face detection and facial feature localization without considering the appearance of image context

引用

IMAGE AND vision COMPUTING 2007年第5期25卷 741-753页

作者： Phimoltares, S. Lursinsap, C. Chamnongthai, K. Chulalongkorn Univ Dept Math AVIC Bangkok 10330 Thailand King Mongkuts Univ Technol Thonburi Dept Elect & Telecommun Engn Bangor 10140 Gwynedd Wales

Face and facial feature detection plays an important role in various applications such as human computer interaction, video surveillance, face tracking, and face recognition. Efficient face and facial feature detection algorithms are required for applying to those tasks. This paper presents the algorithms for all types of face images in the presence of several image conditions. There are two main stages. In the first stage, the faces are detected from an original image by using Canny edge detection and our proposed average face templates. Second, a proposed neural visual model (NVM) is used to recognize all possibilities of facial feature positions. Input parameters are obtained from the positions of facial features and the face characteristics that are low sensitive to intensity change. Finally, to improve the results, image dilation is applied for removing some irrelevant regions. Additionally, the algorithms can be extended to rotational invariance problem by using Radon transformation to extract the main angle of the face. With more than 1000 images, the algorithms are successfully tested with various types of faces affected by intensity, occlusion, structural components, facial expression, illumination, noise, and orientation. (c) 2006 Elsevier B.V. All rights reserved.

关键词： face detection face location facial feature detection neural visual model pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Interface development for cost effective automated IC orientation checking systems

Interface development for cost effective automated IC orient...

引用

10th International Conference on computer and Information Technology

作者： Amin, Nowshad Khadem, Mohammad Shajib Univ Kebangsaan Malaysia Fac Engn Dept Elect Elect & Syst Engn Bangi 43600 Selangor Malaysia TMIB Core Network Engn Div Dhaka Bangladesh

ISBN: (纸本)9781424415502

IC packages, in semiconductor industries, are being marked through certain sequence by either laser marker or ink markers. A critical step in the final visual inspection is the orientation check of ICs that can be determined by detecting images of Pin-1 notch or Pin-1 dimple, which are molded/marked on the IC packages. This study accomplishes a software interface for a simple cost-effective approach to develop an automated low cost vision system that is capable of detecting the IC orientation on a JEDEC tray for a Laser/Ink Marker System used in the IC industries. The algorithm has the competence and flexibility to distinguish correct orientation for various types of IC packages (QFP, PGA, BGA, Flip chip etc.). The workable prototype possesses input variables, control system and output variables along with software implementation using the pattern recognition template based on RGB (red-green-blue) color method for every pixel of the images. Images of Pin-1 dimple or Pin-1 Notch of the IC packages are considered to perform image matching with the software development. The accuracy level has been achieved to a threshold value of above 80% of the total pixels scanned between the matched images. With this threshold value, matching efficiency between two similar images has been attained near about 100%, based on the proposed algorithmic results. Illumination variation, vibration of the machine on conveyors and handlers, computer's timing gap with the web camera and low resolution (320 x 240 or 277 x 245 pixels) of the taken images have made the image matching a complicated one. However, all the constraints are taken into account for setting the threshold value and obtaining the matching accuracy and have been achieved the appropriate matching algorithm to implement the cost effective automated IC orientation checking system.

关键词： pattern recognition machine vision IC orientation web camera RGB color method

来源：评论

学校读者我要写书评

暂无评论

Stereo vision for obstacle detection: A graph-based approach

Stereo vision for obstacle detection: A graph-based approach

引用

6th International Workshop on Graph-Based Representations in pattern recognition

作者： Foggia, P. Jolion, Jean-Michel Limongiello, A. Vento, M. Univ Naples Federico II Dipartimento Informat & Sistemist I-180125 Naples Italy Univ Salerno Dipartmento Ingn Informaz & Ingn Electrr Fisciano Italy Lyon Res Ctr Images & Informat Syst UMR CNRS 5205 Bat J Verne INSA Lyon F-69621 Villeurbanne France

ISBN: (纸本)9783540729020

We propose a new approach to stereo matching for obstacle detection in the autonomous navigation framework. An accurate but slow reconstruction of the ID scene is not needed;rather, it is more important to have a fast localization of the obstacles to avoid them. All the methods in the literature, based on a punctual stereo matching, are ineffective in realistic contexts because they are either computationally too expensive, or unable to deal with the presence of uniform patterns, or of perturbations between the left and right images. Our idea is to face the stereo matching problem as a matching between homologous regions. The stereo images are represented as graphs and a graph matching is computed to find homologous regions. Our method is strongly robust in a realistic environment, requires little parameter tuning, and is adequately fast, as experimentally demonstrated in a comparison with the best algorithms in the literature.

关键词： stereo vision obstacle detection graph matching autonomous mobile robots automated guided vehicles

来源：评论

学校读者我要写书评

暂无评论

pattern matching for automatic sign language translation system using LabVIEW

Pattern matching for automatic sign language translation sys...

引用

2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007

作者： Domingo, Andreas Akmeliawati, Rini Kuang, Ye Chow School of Electrical and Computer Systems Engineering Monash University Malaysia No. 2 Jalan Kolej Bandar Sunway 46150 Petaling Jaya Selangor D.E. Malaysia

ISBN: (纸本)1424413559

This paper presents an automatic sign language translator, which is able to translate Malaysian sign language using pattern-matching algorithm. The sign language translator is a vision-based system where the image of the sign is captured by a camera, processed and translated into English by the computer. This sign language translator is able to recognize alphabets (A-Z), numbers (0-9), finger spelling, words (13 words) and sentences. Alphabets, numbers and fingers are categorized under static signs while words and sentences are known as dynamic signs where the signs involve motion. Static signs are recognised by matching positions of each fingertip with the database while the recognition of dynamic signs is performed by comparing the trajectory of the motion. The accuracy for static sign is 97.79% while the accuracy for dynamic sign is 80.38% ©2007 IEEE.

关键词： Image processing

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：