检索结果-内蒙古大学图书馆

image ANALYSIS BASED ON EDGE DETECTION TECHNIQUES

Journal of Shanghai Jiaotong university(Science) 2002年第2期7卷 198-203页

作者： NASSIR H.SALMAN(纳瑟) LIU Chong-qing(刘重庆) Inst. of Image Processing & Pattern Recognition Shanghai Jiaotong Univ. Shanghai 200030 China Inst. of Image Processing & Pattern Recognition Shanghai Jiaotong Univ. Shanghai 200030 China

A method that incorporates edge detection technique, Markov Random field (MRF), watershed segmentation and merging techniques was presented for performing image segmentation and edge detection tasks. It first applies edge detection technique to obtain a Difference In Strength (DIS) map. An initial segmented result is obtained based on K means clustering technique and the minimum distance. Then the region process is modeled by MRF to obtain an image that contains different intensity regions. The gradient values are calculated and then the watershed technique is used. DIS calculation is used for each pixel to define all the edges (weak or strong) in the image. The DIS map is obtained. This help as priority knowledge to know the possibility of the region segmentation by the next step (MRF), which gives an image that has all the edges and regions information. In MRF model, gray level l , at pixel location i , in an image X , depends on the gray levels of neighboring pixels. The segmentation results are improved by using watershed algorithm. After all pixels of the segmented regions are processed, a map of primitive region with edges is generated. The edge map is obtained using a merge process based on averaged intensity mean values. A common edge detectors that work on (MRF) segmented image are used and the results are compared. The segmentation and edge detection result is one closed boundary per actual region in the image.

关键词： Difference In Strength (DIS) Markov Random Field (MRF) watershed algorithm K-means edge detection image segmentation image analysis

来源：评论

学校读者我要写书评

暂无评论

Template patch driven image segmentation

Template patch driven image segmentation

引用

2006 17th British Machine Vision Conference, BMVC 2006

作者： Mičušík, Branislav Hanbury, Allan Pattern Recognition and Image Processing Group Inst. of Computer Aided Automation Vienna University of Technology Favoritenstr. 9/1832 A-1040 Vienna Austria

ISBN: (纸本)1904410146

We present a method that partitions a single image into two layers, requiring that one layer has similar properties in terms of pixel colour variation to a provided template patch. First the paper provides a new view on defining a similarity function for a pixel with its small neighbourhood to be part of the texture described by the template patch. This results in better description of pixels near the texture boundary. Second, it is shown how the Maximally Stable Extremal Regions (MSERs), originally designed for wide baseline stereo matching, can be used to locally merge pixels having the same intensity and thus reduce the dimension of the graph representing the image. The MSERs help in texture description and yield significant reduction of memory and computation time. Finally the graph is fed into the ***/*** algorithm to cut the graph into two parts. Performance of the method is presented on some images from the Berkeley database. Finally, restrictions in using the method are discussed.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Algorithm for probe vehicle sampling sizes for traffic flow estimation

引用

Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University 2007年第9期41卷 1416-1419+1424页

作者： Gao, Ling-Ling Li, Zhi-Peng Chen, Yi-Kai Liu, Yun-Cai Inst. of Image Processing and Pattern Recognition Shanghai Jiaotong Univ. Shanghai 200240 China

This paper discussed the reliability of computing the road link speed from probe vehicles. An algorithm for the smallest probe vehicle sampling sizes for traffic flow estimation was proposed. Many factors are considered, such as road style, road link speed and information transmit period of probe vehicle. The field testing using traffic data of Xuhui district in Shanghai presents a good result which validates the effecfiveness of the new model.

关键词： Highway traffic control

来源：评论

学校读者我要写书评

暂无评论

Novel color image segmentation based on color information and region growing

引用

Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University 2007年第5期41卷 802-806+812页

作者： Zhao, Qin-Pei Yao, Li-Xiu Cheng, Jian He, Hu-Yi Yang, Jie Inst. of Image Processing and Pattern Recognition Shanghai Jiaotong Univ. Shanghai 200240 China

This paper discussed a novel segmentation algorithm B-JSEG for color images based on color information and region growing. This method is proposed on the base of JSEG, a popular method in segmentation of color images, and directional operators for edge detection in images. Compared with other methods existed, new parameters are used to characterize the property of color-texture images in the proposed method. With the aim of alleviating over-segmentation, directional operators are integrated into the JSEG method to take account of both homogeneity and discontinuity in regions. It is shown from the experiments on large amounts of images that the proposed method is robust and able to match better with human's perception than JSEG.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Algorithm of medical image compression based on human vision system

引用

Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University 2005年第12期39卷 1971-1974+1978页

作者： Xie, Kai Yang, Jie Inst. of Image Processing and Pattern Recognition Shanghai Jiaotong Univ. Shanghai 200030 China

Based on the study of the characteristics of humans' vision system, this paper designed a new algorithm of medical image compression and combined the masking feature of human vision system and the three component model of the image. The experiments were done on the medical images including CT and MRI. The results show that under the same compression ratio, the method used in the paper can achieve better subjective visual quality. The compression ratio can reach 16:1, if the visually lossless effect is required, i.e., almost all the relevant medical information is reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Speaker normalization by input space optimization for continuous density hidden Markov models

Speaker normalization by input space optimization for contin...

引用

1994 International Symposium on Speech, image processing and Neural Networks, ISSIPNN 1994

作者： Wu, Jianxiong Qi, Zeyu Chan, Chorkin Li, Jiegu Inst. of Image Process. and Pattern Recognition Shanghai Jiaotong Univ. Shanghai China Department of Computer Science Universdy of Hong Kong Hong Kong

ISBN: (纸本)078031865X

This paper proposes a novel method of speaker normalization by means of input space optimization for continuous density hidden Markov models (CDHMM). The parameters of a linear feature transformation function are so determined that, together with the previously trained CDHMM parameters, a mis-classification cost function is minimized for the normalizing data set. Preliminary experimental results on the task of sex adaptation for speaker-independent stop consonant discrimination, evaluated from the DARPA TIMIT speech database, demonstrates the effectiveness of the proposed method. © 1994 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Line-based scan compression algorithm suitable for remote sensing images

引用

Yuhang Xuebao/Journal of Astronautics 2005年第1期26卷 60-65+76页

作者： Wang, Zhen-Hua Tian, Jin-Wen Liu, Jian Lab. for Image Proc. Inst. for Pattern Recognition Huazhong Univ. of Sci. and Technol. Wuhan 430074 China

In this paper, a line-based scan image compression algorithm with low complexity was presented. The algorithm was based on Christos Chrysalis's line-based wavelet transformation coding. There was not image tiling in the algorithm. The supposed algorithm modeled with contexts for different subband after quantifying wavelet coefficients uniformly. A modified Golomb-Rice algorithm with low complexity was adopted as entropy coder. The experiment shows that the memory requirement of the algorithm is far less than that of the SPIHT in compressing images with huge size. The complexity of the entropy coding of the algorithm is reduced largely. The algorithm is especially appropriate for remote sensing image compression system with power and space limited.

关键词： Coding Line-based scan Remote sensing Wavelet transformation

来源：评论

学校读者我要写书评

暂无评论

A hybrid swipe fingerprint mosaicing scheme

A hybrid swipe fingerprint mosaicing scheme

引用

5th International Conference on Audio - and Video-Based Biometric Person Authentication, AVBPA 2005

作者： Zhang, Yong-Liang Yang, Jie Wu, Hong-Tao Inst. of Image Processing and Pattern Recognition Jiaotong University Shanghai 200030 China School of Computer Science and Software Hebei University of Technology Tianjin 300130 China

Due to their very small contact areas and low cost, swipe fingerprint sensors provide the very convenient and reliable fingerprint security solutions and are being increasingly used for mobile phones, PDAs, portable computers and security applications. In this paper, the minimum mean absolute error as the registration criterion is used to find an integer translation shift while the extension of the phase correlation method with singular value decomposition is applied to evaluate a non-integer translation shift. Based on the merits and faults of these two methods, we develop a hybrid swipe fingerprint mosaicing scheme. The proposed scheme succeeds in registering swipe fingerprint frames with small overlap down to 5% of the frame size and improves the mosaicing precision, that is, non-integer translation shift can be directly determined without spatial domain interpolation. Experimental data indicate that our scheme has high reliability and precision and less time consumption, therefore, it is very suitable for the real-time applications. © Springer-Verlag Berlin Heidelberg 2005.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Automatic caption location and extraction in digital video based on SVM

Automatic caption location and extraction in digital video b...

引用

proceedings of 2004 International Conference on Machine Learning and Cybernetics

作者： Cheng, Zhi-Guo Liu, Yun-Cai Inst. Image Proc. and Pattern Recog. Shanghai Jiaotong University 1954 Hua Shan Road Shanghai 200030 China

ISBN: (纸本)0780384032

Text that appears in a scene or graphically added to video can provide an important supplemental source of index information as well as clues for decoding the video's structure and for classification, and we call them closed caption. In this work, a novel algorithm is presented for detecting and locating caption in digital video. The first module of the system divides an image into small blocks featured by pixel value that is fed to SVM (Support Vector Machine) to classify whether they are text blocks or not. The other module is to do post-processing on the classified text blocks to identify the rectangle region of them and OCR can be used further and easily. Experiments conducted with a variety of video sources showe that our method could detect and locate caption region successfully by SVM with comparatively less samples.

关键词： Digital devices

来源：评论

学校读者我要写书评

暂无评论

TOWARDS AN ONTOLOGY-BASED MULTI-AGENT MEDICAL INFORMATION SYSTEM BASED ON THE WEB

引用

Journal of Shanghai Jiaotong university(Science) 2002年第2期7卷 194-197页

作者： ZHANG Quan-hai(张全海) SHI Peng-fei(施鹏飞) Inst. of Image Processing & Pattern Recognition Shanghai Jiaotong Univ. Shanghai 200030 China Inst. of Image Processing & Pattern Recognition Shanghai Jiaotong Univ. Shanghai 200030 China

This paper described an ontology based multi agent knowledge process made (MAKM) which is one of multi agents systems (MAS) and uses semantic network to describe agents to help to locate relative agents distributed in the workgroup. In MAKM, an agent is the entity to implement the distributed task processing and to access the information or knowledge. Knowledge query manipulation language (KQML) is adapted to realize the communication among agents. So using the MAKM mode, different knowledge and information on the medical domain could be organized and utilized efficiently when a collaborative task is implemented on the web.

关键词： multi-agents system (MAS) medical information semantic network ontology

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：