Aytül Erçil

An efficient method for texture defect detection: sub-band domain co-occurrence matrices

Abstract In this paper, an efficient algorithm, which combines concepts from wavelet theory and co-occurrence matrices, is presented for detection of defects encountered in textile images. Detection of defects within the inspected texture is performed first by decomposing the gray level images into sub-bands, then by partitioning the textured image into non-overlapping sub-windows and extracting the co-occurrence features and finally by classifying each sub-window as defective or non-defective with a Mahalanobis distance classifier being trained on defect free samples a priori. The experimental results demonstrating the use of this algorithm for the visual inspection of textile products obtained from the real factory environment are also presented. Experiments show that focusing on a particular band with high discriminatory power improves the detection performance as well as increases the computational efficiency.

Real-time Defect Inspection of Textured Surfaces

Texture analysis plays an important role in the automated visual inspection of textured images to detect their defects. For this purpose, model-based and feature-based methods are implemented and tested for textile images in a laboratory environment. The methods are compared in terms of their success rates in determining the defects. The Markov Random Field model is applied on different DSP systems for real-time inspection.

Hand Recognition Using Implicit Polynomials and Geometric Features

Person identification and verification using biometric methods is getting more and more important in todays information society; resulting in increased utilization of systems that combine high security and ease of use. Hand recognition is a promising biometric that is being used in low-level security applications for several years. In this work, implicit polynomials, which have proven to be very successful in object modeling and recognition, have been proposed for recognizing hand shapes and the results are compared with existing methods.

Texture defect detection using subband domain co-occurrence matrices

In this paper, a new defect detection algorithm for textured images is presented. The algorithm is based on the subband decomposition of gray level images through wavelet filters and extraction of the co-occurrence features from the subband images. Detection of defects within the inspected texture is performed by partitioning the textured image into non-overlapping subwindows and classifying each subwindow as defective or nondefective with a mahalanobis distance classifier being trained on defect free samples a priori. The experimental results demonstrating the use of this algorithm for the visual inspection of textile products obtained from the real factory environment are also presented.

Comparative evaluation of texture analysis algorithms for defect inspection of textile products

Quality control is one of the basic issues in textile industry. Texture analysis plays an important role in the automated visual inspection of texture images to detect their defects. For this purpose, model-based and feature-based methods are implemented and tested for textile images in a laboratory environment. The methods are compared in terms of their success rates in determining the defects.

Markov random fields and Karhunen-Loeve transforms for defect inspection of textile products

In this paper the problem of using machine vision in quality inspection of textile fabrics is considered. A model based approach with Markov random fields (MRF) as the texture model and a new method based on Karhunen-Loeve transforms is studied for the defect inspection of textile fabrics. The results are illustrated on real fabric images, and the real time implementation of the MRF approach on a two TMS320C40 based parallel processing system is given.

Texture defect detection using the adaptive two-dimensional lattice filter

In this paper, the eight parameter two-dimensional adaptive lattice filter is used to detect defects in textures corresponding to raw textile fabrics. A novel histogram modification technique is also applied for preprocessing the gray level texture image. Moreover, with the proposed scheme, it is possible to detect defects using the defective image only.

Conversions between Parametric and Implicit Forms Using Polar/Spherical Coordinate Representations

Since parametric and implicit forms have complementary advantages with respect to certain geometric operations, it can be useful to convert from one form to the other. In this paper, a new method for converting between parametric and implicit forms based on polar/spherical coordinate representations is introduced.

A comparative study on the adaptive lattice filter structures in the context of texture defect detection

In this paper, the three-, the six-, and the eight-parameter two-dimensional gradient based adaptive lattice filters are compared in the context of defect detection in textures corresponding to textile fabrics. A novel histogram modification technique is also applied for preprocessing the gray level texture image. Moreover, with the proposed scheme, it is possible to detect defects in an unsupervised manner.

2D object recognition using implicit polynomials and algebraic invariants

The problem studied in this paper is the recognition of free-form objects from their 2D visual data in a manufacturing environment and the integration of CAD systems with recognition systems. A system based on implicit polynomials and algebraic invariants is developed. Integration of such a visual system with the computer aided design (CAD) phase of the production has been attempted allowing the data exchange in between. To allow this exchange, data produced by CAD system had to be converted to some format in order to be acceptable by the recognition system. Since many CAD packages use parametric form for representing designed objects, the conversion from parametric representation to its implicit correspondent is studied. Even if the conversion proved to be successful, problems between fitted and converted implicit polynomials arose. So this topic is left as a research topic for future studies.