D. Dutta Majumder

A new shape preserving parallel thinning algorithm for 3D digital images

This paper is concerned with a new parallel thinning algorithm for three-dimensional digital images that preserves the topology and maintains their shape. We introduce an approach of selecting shape points and outer-layer used for erosion during each iteration. The approach produces good skeleton for different types of corners. The concept of using two image versions in thinning is introduced and its necessity in parallel thinning is justified. The robustness of the algorithm under pseudo-random noise as well as rotation with respect to shape properties is studied and the results are found to be satisfactory.

Application of circle criteria for stability analysis of linear SISO and MIMO systems associated with fuzzy logic controller

The concept of the sector bound nonlinearity has been considered for frequency domain stability analysis of linear single-input single-output (SISO) and decoupled multi-input multi-output (MIMO) systems associated with the fuzzy logic controller. For analysis of the fuzzy logic controller, the systems model is considered to be available in transfer-function form, but for generation of the fuzzy logic controller no model description is necessary. A generalized Nyquist-type stability analysis is presented.

Topology preservation in 3D digital space

Abstract In a 3D two-tone digital space, the conditions under which sequential transformation of an object point to a non-object point, or its inverse, does not affect the image topology are investigated. The concept of border-connectivity is introduced and an efficient algorithm for checking a simple point is proposed. In this connection, some other interesting properties of 3D digital geometry are also discussed. This investigation may be used in thinning and topology preserving morphological transformations in 3D digital space.

Correlation between two fuzzy membership functions

The need for a measure of correlation between two membership functions is stated. The properties that the correlation measure may possess are examined. A measure of correlation is defined on the basis of those properties. The definition is extended to the cases when (a) the domain is finite and (b) the domain is a subset of R^n. The problems encountered while extending the definition are also discussed.

Symmetry analysis by computer

Abstract Approximate locations of axes of symmetry of a 2-dimensional region are detected on the basis of its border. The border, described in terms of certain directional codes, is treated as a regular polygon in a hierarchical manner where a lower level means a greater number of sides. At each level of the hierarchy, the best axis of symmetry is found which for a lower level gives a more accurate position of the unknown axis of symmetry than for a higher level. Along with an axis of symmetry, a certain error is found on the basis of which the degree of symmetry of a 2-dimensional region is defined. Programs are written in FORTRAN IV and are implemented on an EC-1033 computer.

L 2 -stability and the related design concept for SISO linear system associated with fuzzy logic controller

A hybrid (fuzzy and nonfuzzy) design concept has been proposed for the linear single-input single-output (SISO) system associated with fuzzy logic controllers. In the present design techniques, the concept of L2-stability and its graphical interpretation, i.e. the circle criterion, are used. Thus the use of the classical Nyquist locus and the gain-phase chart are brought into the picture. The drawbacks of the L2-stability/circle criterion are indicated and overcome. In the present design technique, which is graphical in nature, the designer is given a feel for the system. Examples are provided to illustrate the application of hybrid controllers structure for the synthesis of the linear SISO system associated with the fuzzy logic controller.

Fuzzy divergence, probability measure of fuzzy events and image thresholding

Abstract A new measure called divergence between two fuzzy sets is introduced along with a few properties. Its application to clustering problems is indicated and applied to an object extraction problem. A tailored version of the probability measure of a fuzzy event is also used for image segmentation. Both parametric and non-parametric probability distributions are considered in this regard.

A note on the use of graylevel co-occurence matrix in threshold selection

Abstract Graylevel thresholding is one of the most popular and economic approaches for segmentation. Graylevel co-occurrence matrices are being successfully used to measure textural properties of the image. In this report, for threshold selection we have considered four new measures based on the graylevel co-occurrence matrix, which in some way or other reflect the homogeneity in different regions of an image. They are also compared with two other measures reported already. Experimental results reveal that the newly proposed techniques are more effective for segmenting noisy images.

Bacterial colony counting using distance transform

A distance-transform based technique is presented for the segmentation of monochrome images of colonies grown on membrane filters. This is used to count the number of Escherichia coli in a given water sample, which is used as a parameter for determining water quality. The result is compared with fuzzy c-means clustering approach.

Fuzzy logic control of a nonlinear multivariable steam generating unit using decoupling theory

A nonlinear multivariable steam generating unit (200 MW) has been decoupled using the existing decoupling theory. A set of fuzzy logic controllers, which virtually reduce to nonlinear multilevel relay elements, is designed for the decoupled subsystems to make the closed-loop subsystems asymptotically stable. Subsequently it has been shown, through digital simulation and field simulation, that the closed-loop subsystems track the desired state parameters under different operating conditions. A frequency domain stability analysis has been presented assuming that the decoupled subsystems are linear in nature and decoupling is accurate.