Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Texture segmentation by threshold decomposition filtering

Open Access Open Access

Abstract

An optoelectronic system is described that can segment a natural scene into regions of different texture characteristics, independent of the illumination levels in those regions. The system consists of a cascade of a thresholding hard-limiting spatial light modulator with controllable threshold, a bank of coherent spatial filters designed for specific textures, a square-law operation (coherent-to-incoherent conversion), a low-pass incoherent spatial filter, and a final thresholding-hard-limiting operation. The scheme works because thresholding at the local texture median produces a binary distribution that preserves considerable texture-related information and that has maximum energy per unit area in non-zero spatial frequencies. In addition, that energy per unit area is the same, independent of the specific texture, implying that only the distribution of spectral energy is different and that selective filtering can be used to discriminate in favor of a given texture and against others. The basic system and its underlying theory of operation will be discussed, and the results of numerical experiments will be presented.

© 1992 Optical Society of America

PDF Article
More Like This
Noise immunity of threshold-decomposition morphological image processing

Joseph L. Tasto and William T. Rhodes
ThD5 OSA Annual Meeting (FIO) 1992

Segmentation of Textured Images

Allan G. Weber and Alexander A. Sawchuk
FB1 Machine Vision (MV) 1985

Gabor functions and textural segmentation

Mark R. Turner
WJ38 OSA Annual Meeting (FIO) 1985

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.