Discrete black and white object recognition via morphological functions

Author

Sinha, Divyendu ; Giardina, Charles R.

Author_Institution

Dept. of Electr. Eng. & Comput. Sci., Stevens Inst. of Technol., Hoboken, NJ, USA

Volume

12

Issue

3

fYear

1990

fDate

3/1/1990 12:00:00 AM

Firstpage

275

Lastpage

293

Abstract

Two morphological algorithms that attempt to recognize a black and white object directly in its discrete domain are presented. The first algorithm is based on covariance functions, while the second is based on a variant of size distribution functions. In both these algorithms, the scale correction has been automated. Also presented is a complete geometric and algebraic characterization of objects that are identical with respect to the proposed methodologies, and it is shown that the induced equivalent classes over binary images contain objects that are structurally very similar. This has been accomplished by introducing the notions of a strongly attached pixel, discrete structure of an image, and a structure preserving operation. An outcome of the analysis is the insight into the relationship between the discrete structure of an image and the induced equivalence classes

Keywords

pattern recognition; picture processing; algebraic characterization; binary images; black-and-white object recognition; covariance functions; discrete object recognition; discrete structure; geometric characterization; induced equivalent classes; morphological functions; scale correction; size distribution functions; strongly attached pixel; structure preserving operation; Algebra; Artificial intelligence; Distribution functions; Ear; Feature extraction; Image analysis; Image texture analysis; Morphology; Object recognition; Pixel;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/34.49053

Filename

49053