A Novel 2D Texture Classifier For Gray Level Images
نویسنده
چکیده
In this paper a new fuzzy method for 2D texture classification is proposed. A fuzzy rule base system is designed based on computed Geometric Moments (GMs), which are rotation, scale and translation invariant, for each texture class. Although GMs are applied to classify texture, utilizing fuzzy inference system (FIS) to make decision, develops much more robust classifier. Where GMs are inputs and likelihood of belonging to one class is the output of fuzzy system, the optimized threshold value is obtained by Genetic Algorithm, to make final decision. 90.8% classification rate proves the system efficiency.
منابع مشابه
Texture Classification Based On Empirical Wavelet Transform Using LBP Features
Automatic inspection systems become more importance for industries with high productive plans especially in texture industry. A novel approach to Local Binary Pattern (LBP) feature for texture classification is proposed in this system. At the first, the proposed Empirical Wavelet Transform (EWT) based texture classification is tested on gray scale and color images by using Brodatz texture image...
متن کاملAutomatic classification of Non-alcoholic fatty liver using texture features from ultrasound images
Background: Accurate and early detection of non-alcoholic fatty liver, which is a major cause of chronic diseases is very important and is vital to prevent the complications associated with this disease. Ultrasound of the liver is the most common and widely performed method of diagnosing fatty liver. However, due to the low quality of ultrasound images, the need for an automatic and intelligent...
متن کاملTexture analysis of the ovarian lesions by CT scan images
Introduction: To explore diagnostic potential of computerize texture analysis methods in discrimination of the normal, benign and malignant ovarian lesions by CT scan imaging. Materials and Methods: Ovarian CT image database consists of 10 normal, 10 benign and 3 malignant which were reported by radiologist and proven by clinical examinat...
متن کاملA Novel Neural Networks-Based Texture Image Processing Algorithm for Orange Defects Classification
In this paper is proposed, implemented and evaluated a novel radial basis probabilistic neural network (RBPNN) based classification algorithm for classification fruit surface defects in color and texture of a very important fruit as orange. The proposed algorithm takes orange images as inputs then the texture and gray features of defect area are extracted by computing a gray level cooccurrence ...
متن کاملClassification of satellite cloud imagery based on multi-feature texture analysis and neural networks
The aim of this work was to develop a system based on modular neural networks and multi-feature texture analysis that will facilitate the automated interpretation of cloud images. This will speed up the interpretation process and provide continuity in the application of satellite imagery for weather forecasting. A series of infrared satellite images from the Geostationary satellite METEOSAT7 we...
متن کامل