This paper describes an approach for object-based image retrieval based on classes of objects in images. In this approach, contours of objects are extracted from images and are represented under a scheme which satisfi...
详细信息
This paper describes an approach for object-based image retrieval based on classes of objects in images. In this approach, contours of objects are extracted from images and are represented under a scheme which satisfies scale, rotation and translation invariance. Classifier learning techniques are used to classify objects in images into different classes. Image similarity calculation is performed based on class information of objects. Experimental results show that the method is effective and efficient.
Designing a system that is able to make use of quantitative and qualitative data for real world applications is a challenging problem. Traditional systems produce representational descriptions that are often not very ...
详细信息
Designing a system that is able to make use of quantitative and qualitative data for real world applications is a challenging problem. Traditional systems produce representational descriptions that are often not very useful to the human expert. To rectify this problem we propose a structure based on contextual fuzzy cognitive maps (CFCMs) for GIS systems. For a given goal, our system structure is hierarchical by context, multi-layered by variations in data over periods of time, and semi-qualitative in that the CFCMs build causal links and relationships between landmarks and concepts.
Fuzzy cognitive maps (FCM) is a powerful framework for representing structured human knowledge and causal inference. This paper presents a new and effective approach to analyzing causal inference mechanism of FCM. We ...
详细信息
ISBN:
(纸本)0780354060
Fuzzy cognitive maps (FCM) is a powerful framework for representing structured human knowledge and causal inference. This paper presents a new and effective approach to analyzing causal inference mechanism of FCM. We focus on binary concept states proposed originally by Kosko (1986). Given initial conditions, FCM is able to reach only certain states in its state space. The problem of finding whether a state is reachable in the FCM is NP hard. In order to effectively carry out the design of fuzzy cognitive maps we propose to divide an FCM into basic FCM modules. This paper also presents a recursive formula for the calculation of FCM inference patterns in terms of key vertices.
作者：
MOHAMED CHERIETYEE-HONG YANGLaboratoire d'Imagerie
de Vision et d'Intelligence Artificielle École de Technologie Supérieure 1100 rue Notre-Dame Ouest Montréal (Québec) H3C 1K3 Canada SAM (Scene Analysis and Modelling Group)
Computer Vision and Graphics Lab Department of Computer Science University of Saskatchewan 57 Campus Drive Saskatoon (Saskatchewan) S7N 5A9 Canada
The paper proposes a genetic-algorithm-based learning strategy that models membership functions of the fuzzy attributes of surfaces in a model based machinevision system. The objective function aims at enhancing reco...
详细信息
The paper proposes a genetic-algorithm-based learning strategy that models membership functions of the fuzzy attributes of surfaces in a model based machinevision system. The objective function aims at enhancing recognition performance in terms of maximizing the degree of discrimination among classes. As a result, the accuracy of recognizing known instances of objects and generalisation capability by recognizing unknown instances of known objects are greatly improved. The performance enhancement of a model based object recognition system consisting of a set of synthetic range images is established by incorporating a dynamic off-line learning mechanism using a genetic algorithm in the feedback path of the system.
A new thresholding algorithm based on all-pole model histogram is presented. The parameters of the all-pole model are estimated from the second derivative of log model histogram. The main merits are that the model can...
详细信息
ISBN:
(纸本)0818685123
A new thresholding algorithm based on all-pole model histogram is presented. The parameters of the all-pole model are estimated from the second derivative of log model histogram. The main merits are that the model can produce the desired number of peaks in model histogram and the algorithm is efficient in computation. The proposed algorithm can be used for binarisation and multilevel thresholding and good results have been achieved for a wide range of images.
Three techniques of straight line Hough transform are proposed by a generalised mathematical formulation of the Hough transform in terms of aggregation and weight functions. Amongst these techniques, inclusive of the ...
详细信息
Three techniques of straight line Hough transform are proposed by a generalised mathematical formulation of the Hough transform in terms of aggregation and weight functions. Amongst these techniques, inclusive of the conventional Hough transform, it is shown by experimental results on a set of 3D nonparametric objects, and in a controlled and inherent noise environment, that the fuzzy Hough transform approach performs the best, as a global shape descriptor.
In this paper, a new method is proposed for learning continuous valued features and mapping them into fuzzy concepts. Further, an efficient method of updating fuzzy evidences is proposed which enhances recognition of ...
详细信息
In this paper, a new method is proposed for learning continuous valued features and mapping them into fuzzy concepts. Further, an efficient method of updating fuzzy evidences is proposed which enhances recognition of approximate shapes. The techniques are tested in a model based 3D object recognition system that employs a fuzzy Hough transform approach for global shape description.
Diagnosing electronic systems for symptoms supplied by customers is often difficult as human descriptions of symptoms are for the most part uncertain and ambiguous. As a result, traditional expert systems are not effe...
详细信息
Diagnosing electronic systems for symptoms supplied by customers is often difficult as human descriptions of symptoms are for the most part uncertain and ambiguous. As a result, traditional expert systems are not effective in providing reliable analysis, often require a large set of rules, and lack flexibility in terms of learning and modification, In this paper, we propose a fuzzy logic-based neural network (FLBN) to develop a case-based system for diagnosing symptoms in electronic systems, We demonstrate through data obtained from a real call-log database that the FLBN is able to perform fuzzy AND/OR logic rules and to learn from samples, Such a system is simple to develop and can achieve the performance similar to that of the human expert.
Most image-retrieval systems rely on similarity measures for collecting images of similar types. Similarity measures are an integral part in the development of image management systems. In this paper, we propose frame...
Most image-retrieval systems rely on similarity measures for collecting images of similar types. Similarity measures are an integral part in the development of image management systems. In this paper, we propose frame-based similarity measures for accessing structured images, e.g. images can be understood by inferring from objects present and the relationships among them. The image content is described in the following ways: (1) adjacency blocks and/or (2) unary and binary attributes that are used to fill frame slots for representing image structures. The retrieval is based on similarity measures by comparing the contents of the query image and database image. The frame-based representation scheme is application-independent. Our similarity measures allow for images to be retrieved with different degrees of similarity and are flexible. We have developed a prototype system using the paradigms proposed. We demonstrate the usefulness of our system with some experimental results. (C) 1997 Academic Press Limited.
暂无评论