The economic viability of a weaving plant is significantly influenced by its efficiency in eliminating fabric faults. Textile faults have traditionally been detected by human visual inspection, but it is time consuming and does not achieve a high degree of accuracy.Mechanisms with automatic operation are much better. Industrial vision systems may form the basis of a method with a very high degree of accuracy for textile inspection. This work presents a simple system designed for fabric inspection and shows its efficiency in detecting twelve kinds of common defects. The results show that the success of system implementation depends on the choice of the specific approach.Visual inspection is an important part of quality control in the textile industry. The term &dquo;textile defect&dquo; covers a whole range of faults occurring in fabrics, resulting from all previous stages of processing. Even though the incidence of serious weaving faults can be reduced by modem weaving technology, fault detection in many plants still continues to create considerable extra costs. To increase accuracy, plant workers are attempting to replace traditional manual inspection with automated visual inspection, which uses a camera and imaging routines. Image acquisition and automatic evaluation may form the basis for a system that will ensure a very high degree of fabric quality control. The main difficulty with automatic fabric inspection is the great diversity of textile types and defects. In this work, we present a proposal for a vision system of fabric inspection and assess its ability to detect faults in plain weaves. Structure of the Vision SystemA common alternative to human visual fault detection is a computer vision system for detecting differences in images acquired by a camera [3,5]. A fabric image from a camera fundamentally depends on two factors, illumination and the way in which the textile reflects that illumination. Defects in a textile sample show changes in the surface that reflect toward the camera. Therefore, these defects can be seen in an acquired image and detected by comparing samples with and without faults.This fact is of little practical consequence, however, unless these images are correctly related to a specific fault in an adequate time interval between image acquisition and processing analysis. ' As the complexity of an algorithm grows, it becomes more and more difficult to execute image examination in real time. We have therefore implemented a method specifically designed for textile fault detection based on a fast approach. The architecture of our implementation, shown in Figure 1, is based on the selection of possible values for variations in an image pattern and a method for quantifying this pattern. After these specifications, the main process is repeated until a certain number of frames (NF) are acquired or all the fabrics are tested. The main process acquires and inspects each image using a specified approach. Figure 2 shows the flowchart of the main process, which clan be decomposed into a sequen...
This work presents an application of software engineering to fabric inspection. An inspection system has been developed for textile industries that aims automatic failure detection. Such as wood, paper and steel industries, this environment has particular characteristics in which surface defect detection is used for quality control. This system combines concept from software engineering and decision support. Detection of defects within the inspected texture is performed in a first step acquiring images by CCD cameras, then extracting texture features and, finally by classifiers being trained a priori on database of defective and non-defective samples. The extracted data depend on the type of method selected for image analysis. The used types are based on segmentation or fractal dimension. Two usual segmentation techniques were adapted and improved. A new algorithm was developed to calculate efficiently fractal dimension of textures. Experiments show the accuracy and applicability of the proposed techniques for a real factory environment.
Pbs-Grad. em Comp. Ap1ic.e Automaqiio -CAA -P6s-Grad. Eng. Mecgnica -PGMEC -UFF r Passo da Piitria 156,CEP 24 210-2407Niter6i,RJ -aconci@caa.uff.br 2Dep. Engenharia Mecsnica -Pontificia Universidade Cat6lica do Rio de Janeiro -PUC-Rio r Marques de Siio Vicente 225, CEP 22 953-900, Rio de Janeiro,RJ -cproenca@mec.puc-rio.br 2 Abstract Many texture classification schemes require an excessively large image area for texture analysis, use a large number of features to represent each texture or are computationally very demanding. In this paper, we describe a segmentation method using color and fractal dimension for real time texture classifcation. The boxcounting approach is used to estimate the fractal dimension (FD). A seed block which embodies information about color features and FD is used by a region growing method. Experimental results indicate that the proposed method is promising for color texture segmentation. This scheme is computationally very efficient and it is suited for texture image recognition.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.