Image morphological processing

Mathematical Morphology with applications in image processing and analysis has been becoming increasingly important in today's technology. Mathematical Morphological operations, which are based on set theory, can extract object features by suitably shaped structuring elements. Mathematical Morphological filters are combinations of morphological operations that transform an image into a quantitative description of its geometrical structure based on structuring elements. Important applications of morphological operations are shape description, shape recognition, nonlinear filtering, industrial parts inspection, and medical image processing. In this dissertation, basic morphological operations, properties and fuzzy morphology are reviewed. Existing techniques for solving corner and edge detection are presented. A new approach to solve corner detection using regulated mathematical morphology is presented and is shown that it is more efficient in binary images than the existing mathematical morphology based asymmetric closing for corner detection. A new class of morphological operations called sweep mathematical morphological operations is developed. The theoretical framework for representation, computation and analysis of sweep morphology is presented. The basic sweep morphological operations, sweep dilation and sweep erosion, are defined and their properties are studied. It is shown that considering only the boundaries and performing operations on the boundaries can substantially reduce the computation. Various applications of this new class of morphological operations are discussed, including the blending of swept surfaces with deformations, image enhancement, edge linking and shortest path planning for rotating objects. Sweep mathematical morphology is an efficient tool for geometric modeling and representation. The sweep dilation/erosion provides a natural representation of sweep motion in the manufacturing processes. A set of grammatical rules that govern the generation of objects belonging to the same group are defined. Earley's parser serves in the screening process to determine whether a pattern is a part of the language. Finally, summary and future research of this dissertation are provided.

Name thesis:degree_name

Doctor of Philosophy in Computing Sciences - (Ph.D.)

Discipline thesis:degree_discipline

Computer Science

Year

2003

Author dc:creator

• Gaddipati, Vijayalakshmi

Contributors dc:contributor

• Frank Y. Shih
• James A. McHugh
• Yun Q. Shi

• mathematical morphology
• image processing
• sweep morphology
• Computer Sciences

Repository record dc:identifier

https://digitalcommons.njit.edu/dissertations/573

OAI identifier oai:identifier

oai:digitalcommons.njit.edu:dissertations-1628