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 (PR) is an activity that we humans normally excel in. We do it almost all the time, and without conscious effort. We receive information via our various sensory organs, which is processed instantaneously by our brain so that, almost immediately, we are able to identify the source of the information, without having made any perceptible effort. What is even more impressive is the accuracy with which we can perform recognition tasks even under non-ideal conditions, for instance, when the information that needs to be processed is vague, imprecise or even incomplete. In fact, most of our day-to-day activities are based on our success in performing various pattern recognition tasks. For example, when we read a book, we recognize the letters, words and, ultimately, concepts and notions, from the visual signals received by our brain, which processes them speedily and probably does a neurobiological implementation of template-matching!The discipline of Pattern Recognition (or pattern recognition by machine) essentially deals with the problem of developing algorithms and methodologies/devices that can enable the computer-implementation of many of the recognition tasks that humans normally perform. The motivation is to perform these tasks more accurately, or faster, and perhaps, more economically than humans and, in many cases, to release them from drudgery resulting from performing routine recognition tasks repetitively and mechanically. The scope of PR also encompasses tasks humans are not good at, like reading bar codes. The goal of pattern recognition research is to devise ways and means of automating certain decision-making processes that lead to classification and means of automating certain decision-making processes that lead to classification and recognition.Machine recognition of patterns can be viewed as a two-fold task, consisting of learning 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 + D is the decision function, and the elements d e D ard termed as decisions.PR has been a thriving field of research for the past few decades, as is amply borne out by the numerous books [30, 32, 41, 118, 123, 125] devoted to it. In this regard, mention must be made of the seminal article by Kanal (61), which gives a comprehen- sive review of the advances made in the field till the early nineteen-seventies. More recently, a review article by Jain et al. [60] provides an engrossing survey of the ad- vances made in statistical pattern recognition till the end of the twentieth century. Though the subject has attained a very mature level during the past four decades or so, it remains evergreen to the researchers due to continuous cross-fertilization of ideas from disciplines like computer science, physics, neurobiology, psychology, engineering, statistics, mathematics and cognitive science. Depending on the practical need and demand, various modern methodologies have come into being,


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