Abraham Kandel. Fuzzy Techniques in Pattern Recognition. Wiley, 1982.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....in nature, which enables us to combine even visually degraded features in the brain using the millions of neurons working in parallel. Fuzzy sets have the ability to model vagueness and ambiguity in data which is encountered in character recognition as well as in other pattern recognition problems [2,8,10,23]. Thus, to enable an OCR system to recognize characters even from degraded text images, it is felt necessary to incorporate fuzzy feature extraction concepts in a neural network. Our approach combines the robustness of feature extraction with the speed of operation of neural networks in a ....

A.Kandel, Fuzzy techniques in pattern recognition (John Wiley & Sons, USA, 1982).

....functional methods [2] 3] which try to minimize the within group sum of squared errors. This has been successfully used for detecting edges from the images[51] 21] 6] There are other techniques used in the low level vision, histogram equalization [41] 16] and measuring geometrical features[46][27]. The high level vision ambiguities can be solved with the help of rule based techniques [22 26] 20] 49] applying hybrid fuzzy artificial neural networks[55] 44] 47] 32] possibility theory[18] fuzzy grammars[31] 42] In section 2 we will present some techniques of image segmentation and ....

....is dependent on the type of prototype. If the prototype is chosen to be a straight line, then the algorithms tend to detect the lines in the data. The type of distances can also be varied to fit into the shape of clusters. A variety of distances as well as linear prototypes have been proposed[27][6] An extended form of this algorithm can also be utilized to recognize planes. Dave [7] has proposed a new algorithm fuzzy c Shells to detect circular or elliptical edges. This opens a new class of algorithms which detects non linear curves or surfaces. 2.1 Fuzzy C Means (FCM) Algorithm: ....

[Article contains additional citation context not shown here]

A. Kandel, Fuzzy techniques in pattern recognition, John Wiley & Sons, New York, 1982.

....of the three techniques: FCM, k means (see Dud et al. 88] nd Rosenreid et al. 89] nd the Bwesin bsed pproch. Interested reders cn explore the voting lgorithms for MR brin segmentation. We refer interested reders to n extensive rticle on dt clustering by Jin et al. 90] nd book by Kndel et al. [91]. Recently, Acton et al. 92] published work in fuzzy clustering pplied to SPECT. Interested reders cn look t that ppliction. Pros and Cons of the Clustering Technique: The major advantage of the clustering technique is in the ease of implementation. The major weaknesses of this method are: 1) ....

Kandel, A., Fuzzy Techniques in Pattern Recognition, Wiley Interscience, NY, ISBN: 0471091367, 1982.

....measure corresponds to the Tanimoto Coefficient, 7] operating on binary vectors: A t B A t A B t B Gamma A T B In the language of computer programming this is just the count of 1 s in the exclusive or of bit vectors A and B, divided by the count of 1 s in their logical or. In [8], the measure is referred to as association. While the authors do not state that these various forms fail to satisfy the triangle inequality, they describe them along with other non metric measures. Other sources such as [9] mention explicitly the set function d4n , but again fail to note that it ....

A. Kandel, Fuzzy techniques in pattern recognition. John Wiley & Sons, Inc., 1982.

....them into clusters so that points from one cluster are, in general, closer to each other than points belonging to different clusters. There exist different clustering techniques; a survey of main non fuzzy techniques is given, e.g. in [10] the main ideas of fuzzy clustering are described in [1, 2, 3, 4, 5, 6, 7, 8, 9, 12, 13, 14, 15]. It is known that different clustering methods lead to results of different quality, so it is extremely important to find the best clustering technique. 1.2 Non clustering applications of clustering techniques: before comparing different clustering methods, we must first check whether it makes ....

A. Kandel, Fuzzy techniques in pattern recognition, Wiley-Interscience, NY, 1982.

....data can be formulated in statistical terms, statistical techniques (see, e.g. 13] are appropriate if we have sufficiently many data. In other situations, we must use heuristic classification methods, in particular, methods that use fuzzy logic. The main idea of fuzzy clustering is described in [1, 2, 3, 4, 5, 6, 8, 9, 10, 15, 23, 24]. The goal of fuzzy clustering: typical representatives and how to use them. We start with objects which we want to classify (i.e. to cluster) To classify, we use several (numerical) characteristics of these object. Let us denote the total number of these characteristics by s. The s real ....

....widely used approach. We have described how to classify an object when the clusters (or, to be more precise, their typical representatives) have already been found. How can we find these representatives The most widely used fuzzy clustering method is the method of Fuzzy C Means (Fuzzy ISODATA) [1, 2, 3, 4, 5, 6, 10, 15]. This method is based on the natural idea that each characteristic of a typical representative should be equal to an average over all elements of the corresponding cluster. If we have crisp clustering, then we would simply take the arithmetic average. However, since we have fuzzy clustering, it ....

A. Kandel, Fuzzy techniques in pattern recognition, Wiley-Interscience, NY, 1982.

....of set whose boundaries are fuzzy or unclear, and whose formal definition is nearly identical to that of a p concept. An axiomatic theory of fuzzy sets was introduced by Zadeh [32] and they have since received much treatment by researchers in the field of pattern recognition. See Kandel s book [14] for a good introduction. We distinguish two possible goals for a learning algorithm in the p concept model. The first and easier goal is that of label prediction: the algorithm wishes to output a hypothesis that maximizes the probability of correctly predicting the f0; 1g label generated by c on ....

Abraham Kandel. Fuzzy Techniques in Pattern Recognition. Wiley, 1982.

....data can be formulated in statistical terms, statistical techniques (see, e.g. 21] are appropriate if we have sufficiently many data. In other situations, we must use heuristic classification methods, in particular, methods that use fuzzy logic. The main idea of fuzzy clustering is described in [3, 4, 5, 6, 7, 8, 11, 12, 13, 27, 49, 50]. The goal of fuzzy clustering: typical representatives and how to use them. We start with objects which we want to classify (i.e. to cluster) To classify, we use several (numerical) characteristics of these object. Let us denote the total number of these characteristics by s. The s real ....

....widely used approach. We have described how to classify an object when the clusters (or, to be more precise, their typical representatives) have already been found. How can we find these representatives The most widely used fuzzy clustering method is the method of Fuzzy CMeans (Fuzzy ISODATA) [3, 4, 5, 6, 7, 8, 13, 27]. This method is based on the natural idea that each characteristic of a typical representative should be equal to an average over all elements of the corresponding cluster. If we have crisp clustering, then we would simply take the arithmetic average. However, since we have fuzzy clustering, it ....

A. Kandel, Fuzzy techniques in pattern recognition, Wiley-Interscience, NY, 1982.

....case that the values of the opinions (the fuzzy values ) are not functionally related to probabilities. Heckerman has a detailed discussion of the use of the min operator in MYCIN [30] and its relationship to probabilities. The conjunctive combination rule is an example of a fuzzy logic rule [16, 31] which is nonetheless applicable in some situations. A conjunctive combination is most common in the two label case, and applies only to one of the two labels, and thus will be considered only in terms of the odds formulation for the representation of the opinions. For this case, the conjunction ....

A. Kandel, Fuzzy Techniques in Pattern Recognition, Wiley Press, New York (1982).

....data can be formulated in statistical terms, statistical techniques (see, e.g. 19] are appropriate if we have sufficiently many data. In other situations, we must use heuristic classification methods, in particular, methods that use fuzzy logic. The main idea of fuzzy clustering is described in [4, 5, 6, 7, 8, 9, 11, 12, 16, 22, 75, 76]. The goal of fuzzy clustering: typical representatives and how to use them. We start with objects which we want to classify (i.e. to cluster) To classify, we use several (numerical) characteristics of these object. Let us denote the total number of these characteristics by s. The s real ....

....widely used approach. We have described how to classify an object when the clusters (or, to be more precise, their typical representatives) have already been found. How can we find these representatives The most widely used fuzzy clustering method is the method of Fuzzy CMeans (Fuzzy ISODATA) [4, 5, 6, 7, 8, 9, 16, 22]. This method is based on the natural idea that each characteristic of a typical representative should be equal to an average over all elements of the corresponding cluster. If we have crisp clustering, then we would simply take the arithmetic average. However, since we have fuzzy clustering, it ....

A. Kandel, Fuzzy techniques in pattern recognition, Wiley-Interscience, NY, 1982.

No context found.

Abraham Kandel. Fuzzy Techniques in Pattern Recognition. Wiley, 1982.

No context found.

A. Kandel, Fuzzy Techniques in Pattern Recognition, NY, Wiley, 1982.

No context found.

Kandel, A. (1982) Fuzzy Techniques in Pattern Recognition. New York: John Wiley and Sons.

No context found.

Kandel, A. (1982) Fuzzy Techniques in Pattern Recognition. New York: John Wiley and Sons.

No context found.

A. Kandel. Fuzzy Techniques in Pattern Recognition. John Wiley & Sons, Inc., New York, NY, 1982.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC