An Efficient Feature Fusion Technique for Surface Grading of Ceramic Tiles

نویسندگان

  • M. Senthilkumar
  • V. Palanisamy
چکیده

Automated grading system plays an important role in many industries. In ceramic industries, the grading of ceramic tiles is a difficult task as it has huge variations of surface properties. In this paper, automated surface grading system based on Discrete Wavelet Transform (DWT) and Gray Level Co-occurrence Matrices (GLCM) is presented. Texture information’s in ceramic tiles are effectively represented by DWT at various decomposition levels. From the decomposition, DWT energy features are extracted. Also, the statistical features; correlation, contrast, energy, homogeneity are extracted from the GLCM of ceramic tiles. Feature fusion is employed for effective classification using Feed Forward Neural Network (FFNN) classifier. The evaluation of the system is carried on VxC TSG image database. Experimental results show that the proposed surface grading system produces 99.18% accuracy using 4 level DWT features along with GLCM features th

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Automatic color grading of ceramic tiles using machine vision

We present a method designed to solve the problem of automatic color grading for industrial inspection of plain and patterned ceramic tiles. We discuss problems we were confronted with, like the temporal and spatial variation of the illumination, and the ways we dealt with them. Then, we present results of correctly grading a series of ceramic tiles, the differences of which were at the thresho...

متن کامل

Performance evaluation of soft color texture descriptors for surface grading using experimental design and logistic regression

This paper presents a novel approach to the question of surface grading, the soft color texture descriptors method. This method is extracted from an extensive evaluation process of several factors based on the use of two well established statistical tools: experimental design and logistic regression. The utility of different combinations of factors is evaluated in regard to the problem of autom...

متن کامل

Investigating the Effect of Pigment and Solvent Components on the Physical Properties of Digital Ink for the Decoration of Ceramic Tiles

The inkjet printing machine was initially used on ceramic parts as a small device in designing and advertising offices limitedly. In recent years, this device has been applied professionally to create high-quality patterns in the industry. In this method, liquid ceramic ink is sprayed on the specified parts by piezoelectric nozzles and after drying and discharging, the organic matter is baked a...

متن کامل

Visual Inspection for Fired Ceramic Tile’s Surface Defects using Wavelet Analysis

This paper deals with the visual inspection of ceramic’s tiles surfaces for the purpose of detecting flaws using a wavelet approach. Surface defects in the ceramic tiles are viewed as in-homogeneities in regularity and orientation fields. To improve the homogeneity of batches received by final users and to detect manufacturing defaults, most production lines for ceramic tiles must integrate a v...

متن کامل

Cerámica y Vidrio Preparation and characterization of photochromic effect for ceramic tiles

Ceramic tile industry is developing due to the technological researches in scientific area and new tiles which are not only a traditional ceramic also have many multiple functionalities have been marketed nowadays. These tiles like photocatalytic, photovoltaic, antibacterial and etc. improve the quality of life and provide lots of benefits such as self cleaning, energy production, climate contr...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015