scispace - formally typeset
Proceedings ArticleDOI

Rapid Texture Identification

Kenneth I. Laws
- Vol. 0238, pp 376-381
TLDR
In this article, the texture energy approach requires only a few convolutions with small (typically 5x5) integer coefficient masks, followed by a moving-window absolute average operation.
Abstract
A method is presented for classifying each pixel of a textured image, and thus for segmenting the scene. The "texture energy" approach requires only a few convolutions with small (typically 5x5) integer coefficient masks, followed by a moving-window absolute average operation. Normalization by the local mean and standard deviation eliminates the need for histogram equalization. Rotation-invariance can also be achieved by using averages of the texture energy features. The convolution masks are separable, and can be implemented with 1-dimensional (vertical and horizontal) or multipass 3x3 convolutions. Special techniques permit rapid processing on general-purpose digital computers.

read more

Citations
More filters

Discriminating isotrigo ntextures

T. Maddess, +1 more
TL;DR: In this paper, human discrimination performance for 18 isotrigon texture types and compared it with outputs from statistical discriminant models was determined, and Physiologically plausible mechanisms for such calculations are presented.
Journal ArticleDOI

Defect Inspection for SMD Inductors

TL;DR: In this paper, a machine vision inspection method for winding high frequency inductors is presented to improve the quality of component detection, an important issue for surface mounted device (SMD) inductors manufacturers.
Journal ArticleDOI

CAD System for Liver Diseases using Histological and Imaging features

TL;DR: The current work for characterization of liver disease has been carried out using histological and imaging data using the BUPA liver disorders dataset created by University of California, Irvine as histological data and ultrasound images taken from ultrasoundcases.info.
Journal ArticleDOI

LSR: A Light-Weight Super-Resolution Method

TL;DR: In this paper , a light-weight super-resolution (LSR) method from a single image targeting mobile applications is proposed, which predicts the residual image between the interpolated low-resolution and high-resolution images using a self-supervised framework.
References
More filters
Journal ArticleDOI

Textural Features for Image Classification

TL;DR: These results indicate that the easily computable textural features based on gray-tone spatial dependancies probably have a general applicability for a wide variety of image-classification applications.
ReportDOI

Textured Image Segmentation

TL;DR: In this article, texture energy is measured by filtering with small masks, typically 5x5, then with a moving-window average of the absolute image values, leading to a simple class of texture energy transforms, which perform better than any of the preceding methods.
Related Papers (5)