We describe a three-step algorithm for the morphometric analysis of color images of nerve specimens, currently used in the diagnosis of peripheral neuropathies. The algorithm first segments the images by applying a cl...
详细信息
We describe a three-step algorithm for the morphometric analysis of color images of nerve specimens, currently used in the diagnosis of peripheral neuropathies. The algorithm first segments the images by applying a clustering method in the color space. It then identifies and eliminates irrelevant regions and, in the final step. calculates the diagnostic parameters required for clinical analysis. The results obtained on 25 images are reported and compared with corresponding measurements made by neurologists. (C) 1999 Elsevier Science Ltd. All rights reserved.
For a large group that might have a clustered structure, we discuss and implement an algorithm to group individuals into natural clusters using a convenient similarity measure. The cohesiveness of a homogeneous group ...
详细信息
For a large group that might have a clustered structure, we discuss and implement an algorithm to group individuals into natural clusters using a convenient similarity measure. The cohesiveness of a homogeneous group or cluster is also investigated. (C) 1999 Elsevier Science B.V. All rights reserved.
Hybrid classification of 11 Landsat TM quarter images (circa 81 000 km(2)) was performed in an attempt to locate and quantify areas of sand transported by wind in Lapland. The data were employed in the k-means cluster...
详细信息
Hybrid classification of 11 Landsat TM quarter images (circa 81 000 km(2)) was performed in an attempt to locate and quantify areas of sand transported by wind in Lapland. The data were employed in the k-means clustering algorithm after grey-level thresholding, and the resulting normal distribution parameters were used in a maximum likelihood classification. In order to achieve an unbiased classification result, post-classificational manual interpretation was used for selecting the best possible class combination with the aid of ground data and field checks. Wind activity was found on early Holocene anchored inland dunes, glaciofluvial deposits, and in localised areas on fell slopes. Aeolian processes are mainly operative in the mountain birch woodland and treeless tundra north of the Scots Pine forest zone. Sixty-three current localities with a total area of deflated surfaces of circa 10 km(2) (1000 ha) were identified in the study region.
In this paper a real time 2D object recognition algorithm is proposed. Contours are represented by their curvature functions, decomposed in the Fourier domain as linear combination of a set of representative objects. ...
详细信息
In this paper a real time 2D object recognition algorithm is proposed. Contours are represented by their curvature functions, decomposed in the Fourier domain as linear combination of a set of representative objects. Finally, objects are identified by multilevel clustering. (C) 1999 Elsevier Science B.V. All rights reserved.
In this paper, a multispectral image edge detection algorithm is proposed based on the idea that uses global multispectral information to guide local gradient computation. The image is first segmented into a small num...
详细信息
ISBN:
(纸本)0819432946
In this paper, a multispectral image edge detection algorithm is proposed based on the idea that uses global multispectral information to guide local gradient computation. The image is first segmented into a small number of clusters through a clustering algorithm. According to these clusters, a set of linear projection vectors are generated. For a given image, if n clusters are found, there are n(n-1)/2 possible projection vectors. Edge detection is performed by calculating gradient magnitudes separately on each channel. An appropriate projection vector is chosen for each pixel to maximize gradient magnitude. In this way, edges are treated as transitions from one cluster to another. The algorithm has been tested on JERS-1/OPS images, and the experimental results demonstrate its potential usefulness.
The general objective of our study is the development of a clinically robust three-dimensional segmentation and quantification technique of Magnetic Resonance (MR) data, for the objective and quantitative evaluation o...
详细信息
ISBN:
(纸本)0819431338
The general objective of our study is the development of a clinically robust three-dimensional segmentation and quantification technique of Magnetic Resonance (MR) data, for the objective and quantitative evaluation of the osteonecrosis (ON) of the femoral head. This method will help evaluate the effects of joint preserving treatments for femoral head osteonecrosis from MR data. The disease is characterized by tissue changes (death of bone and marrow cells) within the weight-bearing portion of the femoral head. Due to the fuzzy appearance of lesion tissues and their different intensity patterns in various MR sequences, we proposed a semi-automatic multispectral segmentation of MR data introducing data constraints (anatomical and geometrical) and using a classical K-means unsupervised clustering algorithm. The method was applied on ON patient data. Results of volumetric measurements and configuration of various tissues obtained with the semiautomatic method were compared with quantitative results delineated by a trained radiologist.
In Cellular Manufacturing literature, early work focused on the use of routers as a way of forming product families and manufacturing cells. Later, several measures of similarity among machines and parts have been pro...
详细信息
In Cellular Manufacturing literature, early work focused on the use of routers as a way of forming product families and manufacturing cells. Later, several measures of similarity among machines and parts have been proposed by different authors. In this paper, a new clustering algorithm is proposed that considers the number of machines of each type and the most recent configuration of cells in revising the values of similarity coefficient. The potential benefits of the procedure is demonstrated with a simple example.
The World Wide Web provides its users with almost unlimited access to documents on the Internet. The use of intelligent agents is suggested to assist users to locate documents related to their interests instead of bro...
详细信息
The World Wide Web provides its users with almost unlimited access to documents on the Internet. The use of intelligent agents is suggested to assist users to locate documents related to their interests instead of browsing the Web via primitive search engines. A number of key components in such intelligent systems are identified and a system architecture is proposed. In particular, a learning agent is designed along with the underlying algorithms for the discovery of areas of interest from user access logs. The discovered topics can be used to improve the efficiency of information retrieval by prefetching documents for the users and storing then in a document database in the system. A prototype system has also been implemented to illustrate the various concepts. Experiments are performed which show that the area of interest discovered can in fact be used to improve the efficiency of information retrieval on a distributed information system such as the Internet. (C) 1998 Published by Elsevier Science B.V. All rights reserved.
This paper presents a linear assignment algorithm for machine-cell and part-family formation to design cellular manufacturing systems. The present approach begins with the determination of part-family or machine-cell ...
详细信息
This paper presents a linear assignment algorithm for machine-cell and part-family formation to design cellular manufacturing systems. The present approach begins with the determination of part-family or machine-cell representatives by means of comparing similarity coefficients between parts or machines and finding a set of the least similar parts or machines. Using the group representatives and associated similarity coefficients, a linear assignment model is formulated for solving the formation problem by allocating the remaining parts or machines and maximizing a similarity index. Based on the formulated linear assignment model, a group formation algorithm is developed. (C) 1998 Elsevier Science Ltd. All rights reserved.
A method for representing a large distribution system is developed. The method is based on utilising the clustering technique to build an equivalent distribution system. The behaviour of the original large system may ...
详细信息
A method for representing a large distribution system is developed. The method is based on utilising the clustering technique to build an equivalent distribution system. The behaviour of the original large system may then be studied by analysing the equivalent (simpler) system, with less computational time and with high accuracy. Such behavioural features may include voltage regulation, equipment loading and total system losses. The use of the equivalent system leads to saving in both computer and distribution systems operator(s) time. The use of the clustering techniques significantly reduces the complexity of the problem yet, at the same time, provides very accurate results.
暂无评论