Description

ABSTRACT

Quality inspection is an important aspect of modern industrial manufacturing. In textile industry production, automate fabric inspection is important to maintaining the fabric quality. For a long time the fabric defects inspection process is still carried out with human visual inspection, and thus, insufficient and costly. Therefore, automatic fabric defect inspection is required to reduce the cost and time waste caused by defects. The development of fully automated web inspection system requires segmentation and classification of detection algorithms. The detection of local fabric defects is one of the most intriguing problems in computer vision. Texture analysis plays an important role in the automated visual inspection of texture images to detect their defects. Various approaches for fabric defect detection have been proposed in past and the purpose of this paper is to categorize and describe these algorithms. This paper attempts to present the survey on fabric defect detection techniques, with a comprehensive list of references to some recent.

INTRODUCTION

Quality assurance of product is considered as one of the most important focuses in the industrial production. So is the textile industry too. Textile product quality is seriously degraded by defects. So, early and accurate fabric defect detection is an important phase of quality control. Manual inspection is time-consuming and the level of accuracy is not satisfactory enough to meet the present demand of the highly competitive international market. Hence, expected quality cannot be maintained with manual inspection. Automated, i.e. computer vision based fabric defect inspection system is the solution to the problems caused by manual inspection. Automated fabric defect inspection system has been attracting the extensive attention of the researchers of many countries for years. The high cost, along with other disadvantages of human visual inspection has led to the development of automated defect inspection systems that are capable of performing inspection tasks automatically. The global economic pressures have gradually led business to ask more of itself in order to become more competitive. As a result, intelligent visual inspection systems to ensure high quality of products in production lines are in increasing demand for printed textures (e.g. printed fabrics, printed currency, wallpaper) requires evaluation of color uniformity and consistency of printed patterns, in addition to any discrepancy in the background texture, but has attracted little attention of researchers. Human inspection is the traditional means to assure the quality of the fabric. It helps instant correction of small defects, but a human error occurs due to fatigue and fine defects are often undetected. Therefore, automated inspection of fabric defect becomes a natural way to improve fabric quality and reduce labor costs.

EXISTING SYSTEM

An automated defect detection and identification system enhances the product quality and results in improved productivity to meet both customer needs and to reduce the costs associated with off-quality. The inspection of real textile defects is particularly challenging due to the large number of textile defect classes, which are characterized by their vagueness and ambiguity classifies.

PROPOSED SYSTEM

Here we find with the HSV conversion to find the texture and shape of cloth by processing we improve the quality by segmentation and reducing the noise and makes simple to find the color features in it and it classifies by the feature matching classification.

BLOCK DIAGRAM

ADVANTAGES

• Different type of datasets can accept
• Classification  accuracy  is clear

APPLICATIONS

• Cloth industrial applications
• Shopping malls applications

CONCLUSION

In this paper, we proposed recognition types of clothing by using a combination HSV conversion and feature matching classification base on Bag of Features. The three sub-windows can optimize and improve the performance of interest point detection with height accuracy score. The experiment showed the proposed method achieves the precision score 73.57%.