| dc.description.abstract | The results of an investigation carried out on certain pattern recognition aspects of a class of two-dimensional line drawings and three-dimensional objects are reported in this thesis. The motivation for the proposed schemes for coding and recognizing the two and three-dimensional objects has its origin in the neurophysiological evidence on pattern and contour coding and edge feature extraction in the visual system of mammalian species.
The thesis is divided into six chapters. A brief bibliographic survey of the research activity in related areas and an introduction to the problem under consideration are given in the first chapter. The second chapter deals with the study of a hypothetical model for visual recognition of alphanumerals. The model incorporates the concept of a short line extractor neuron and the known structural organization (neurophysiological) of the mammalian visual cortex and the concept of ‘lateral inhibition’. Based on the findings of Hubel and Wiesel that there are cortical cells with different orientations of their field axes, four basic types of short line extractors are proposed to extract four types of short line features. This is in accordance with the usual practice in pattern recognition studies, of using a 5-bit quantization of the slopes of the line segments in a given pattern. Alphanumerals are taken as the test patterns for the recognition task. It is found that correct recognition of the letters H and T requires the extraction of the largest number of features.
The results of an investigation carried out on certain pattern recognition aspects of a class of two-dimensional line drawings and three-dimensional objects are reported in this thesis. The motivation for the proposed schemes for coding and recognizing the two and three-dimensional objects has its origin in the neurophysiological evidence on pattern and contour coding and edge feature extraction in the visual system of mammalian species.
The thesis is divided into six chapters. A brief bibliographic survey of the research activity in related areas and an introduction to the problem under consideration are given in the first chapter. The second chapter deals with the study of a hypothetical model for visual recognition of alphanumerals. The model incorporates the concept of a short line extractor neuron and the known structural organization (neurophysiological) of the mammalian visual cortex and the concept of ‘lateral inhibition’. Based on the findings of Hubel and Wiesel that there are cortical cells with different orientations of their field axes, four basic types of short line extractors are proposed to extract four types of short line features. This is in accordance with the usual practice in pattern recognition studies, of using a 5-bit quantization of the slopes of the line segments in a given pattern. Alphanumerals are taken as the test patterns for the recognition task. It is found that correct recognition of the letters H and T requires the extraction of the largest number of features.
The above ideas have led to the investigation of machine algorithms which duplicate the performance of the short line extractor neurons. To this end, given a pattern in digitized binary form, four different pairs of operators are proposed for extracting the short line features viz., the medial lines of the vertical, horizontal, right and left inclined line segments. This has become possible because of two new concepts viz., a turning point and an end point which indicate the presence of a junction and an open end respectively in the pattern. Thus, the algorithm extracts these points during the first stage and during the second stage develops the medial line or the skeleton of the given pattern by a simple search procedure. The proposed method and the results obtained are discussed in chapter 3.
The concepts of turning and end points introduced in chapter 3, facilitate easy encoding of the class of two-dimensional line drawings considered. This forms the topic for the fourth chapter. The code for a given line drawing is a sequence of turning and end points and is based on how these points are connected in the pattern. Using the informationally rich points from a topological point of view, a scheme for recognizing alphanumerals of a particular font is evolved using simple decision rules. From the code sequence developed for a pattern, it is shown that information about such characteristics as the number of independent loops, the number of junctions/nodes, number of limbs in the pattern and their topological arrangement can be extracted.
The above concepts of coding two-dimensional line drawings are extended to seek solution to the perceptual problems of three-dimensional objects by machine in the fifth chapter. Trihedral objects like those composed of long, thin and narrow rectangular prisms connected at their ends are considered for this purpose. The specific tasks administered to the machine are as follows:
1. Given two object views to find out whether they portray objects of identical shape, mirror image objects, partially identical or partially mirror image objects.
2. Given one view of an object to visualize its other views resulting from its known rotations.
The input format to the program is the two-dimensional line drawing (portraying a given three-dimensional object) in the digitized binary form. From the set of all nodes (picture points at which two lines meet at other than 180°) and the set of all junctions (picture points at which more than two lines meet), through a process of removal of redundancy, a set of ‘cardinal nodes’ and a set of ‘cardinal junctions’ are defined. These points are special points indicating the presence of bends and open ends in the object and are the three-dimensional counterparts of the turning and end points of the two-dimensional case. The skeleton of the three-dimensional object is obtained as an ordered and connected path passing through the cardinal points. The skeleton is represented as...
a sequence of ‘slope-code’ numbers (numbers representing the different slopes of the line segments in the given drawing). To solve the first task, the two sequences representing the skeletons of the two given views are tested for skeletal, mirror, partial skeletal and partial mirror matches. A particular match reflects a corresponding shape relation between the objects portrayed by the two views. In fact, by such a study, a finer analysis leading to the detection of shape relations between the objects and their correlation is possible. Some results of computer simulation of the proposed model are also presented. To solve the second task, appropriate transformations are defined on the sequence representing the skeleton of the given view corresponding to the given amount and sense of rotation. From the transformed sequence, the skeleton for the new view is obtained. The faces are constructed around this skeleton from a knowledge of the transformed cardinal nodes and junctions.
In the final chapter the results of the investigation carried out on the problems posed in the thesis are summarised. The scope for future research in this area is also indicated. | |
