Date of Submission


Date of Award


Institute Name (Publisher)

Indian Statistical Institute

Document Type

Doctoral Thesis

Degree Name

Doctor of Philosophy

Subject Name

Computer Science


Machine Intelligence Unit (MIU-Kolkata)


Pal, Sankar Kumar (MIU-Kolkata; ISI)

Abstract (Summary of the Work)

Pattern recognition and machine learning form a major area of research and develop- ment activity that encompasses the processing of pictorial and other non-numerical information obtained from the interaction between science, technology and society. A motivation for the spurt of activity in this field is the need for people to com- municate with the computing machines in their natural mode of communication. Another important motivation is that the scientists are also concerned with the idea of designing and making intelligent machines that can carry out certain tasks that we human beings do. The most salient outcome of these is the concept of future generation computing systems. Machine recognition of patterns can be viewed as a two-fold task, consisting of learn- ing the invariant and common properties of a set of samples characterizing a class, and of deciding that a new sample is a possible member of the class by noting that it has properties common to those of the set of samples. The task of pattern recognition by a computer can be described as a transformation from the measurement space M to the feature space F and finally to the decision space D, i.e., M → F→ D. Here the mapping 8 : F→ Dis the decision function, and the elements d€D are termed as decisions. When the input pattern is an image, some processing tasks such as enhancement, filtering, noise reduction, contour extraction and skeleton extraction are performed in the measurement space, in order to extract salient features from the image pat- tern. This is what is basically known as image processing (189, 70]. The ultimate aim is to make its understanding, recognition and interpretation from the processed information available from the image pattern. Such a complete image recogni- tion/interpretation scheme is called a vision system (5) which may be viewed as consisting of three levels, viz., low level, mid level and high level corresponding to M, F and D with an extent of overlapping among them. The theory of fuzzy set has been introduced in 1965 by Zadeh [226] as a new way of representing vagueness in everyday life. This theory [228, 232, 100, 156, 109, 110, 222, 216, 178] provides an approximate and yet effective means for describing the characteristics of a system which is too complex or ill-defined to admit precise mathe- matical analysis. It attempts to model the human thinking process and behavior, and is reputed to handle, to a reasonable extent, uncertainties (arising from deficiencies of information) in various applications particularly in decision making models under different kinds of risks, subjective judgment, vaguencss and ambiguity. The deficien- cies may result from various reasons, viz., incomplete, imprecise, not fully reliable, vague or contradictory information depending on the problem. Since this theory is a generalization of the classical set theory, it has greater flexibility to capture various aspects of incompleteness or imperfection in information about a situation. The relevance of fuzzy sets to pattern recognition and image processing problems has been adequately reported in literature [20, 22, 99, 75, 51, 103, 227, 196, 166]. It is found that the concept of fuzzy sets can be exploited in representing linguis- tically phrased input features for processing, in extracting ill-defined image regions, primitives, properties and relations among them, in measuring image information, in providing an estimate/representation of missing or contradictory information, and multiclass membership for ambiguous patterns; thereby reducing the uncertainty in a recognition system.


ProQuest Collection ID:

Control Number


Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.


Included in

Mathematics Commons