Classifying Web Defects with a Back-Propagation Neural Network by Color Image Processing

Abstract

The aim of this research is to construct an appropriate back-propagation neural network topology to automatically recognize neps and trash in a web by color image processing. After studying the ideal background color under moderate conditions of brightness and contrast to overcome the translucent problem of fibers in a web, specimens are reproduced in a color BMP image file format. Assuming that neps and trash can be distinguished without difficulty from the color image, the image-taking device in the system can be easily altered as long as the optical conditions for other color image resources (i.e., CCD) are considered to ensure image quality. With a back-propagation neural network, the RGB (red, green, and blue) values corresponding with the image pixels are used to perform the recognition, and three categories (i.e., normal web, nep, and trash) can be recognized. The numbers and areas of both neps and trash can also be determined. According to experi mental analysis, the recognition rate can reach 99.63% under circumstances in which the neural network topology is 3-3-3. Both contrast and brightness are set at 60% with an azure background color. The results show that both neps and trash can be recognized well, and the method is suitable not only for cotton and man-made fibers of different lengths, but also for different web thicknesses as to a limit of 32.9 g/m2. Since neps and trash in a web can be recognized, yarn quality not only can be assessed but also improved using a reference for adjusting manufacturing parameters.

Detecting Fabric Defects with a Neural Network Using Two Kinds of Optical Patterns

“…Another interesting point is that the trained network performs better in classifying non-3D defects compared with 3D defects. The reasons for this behavior are not easily understood, but they are probably connected to the combination of gray level values with 3D range profile data: the properties of a Hat defect are probably better represented by this combination, while a three-dimensional defect is more difficult to learn and should need more input data, such as the color RGB values of each pixel [ 13]. Because the optical sensor used in the image acquisition is also able to acquire the RGB data, we can test the possibility of such extended input patterns in future work.…”

Predicting Cotton Fibre Maturity by Using Artificial Neural Network

“…Artificial neural networks have been the employed in the textile industry for more than two decades now. The neural networks have been the topic of various research studies in the textile industry like prediction of tensile properties of ternary blended open-end yarn [19], thermal resistance of knitted fabrics [20], segregation of cotton bales on its fibre attributes in yarn properties [21], classification of card-web defects [22], predicting the levelling action point at draw frame [23], control of sliver evenness [24] and predicting the spin ability of the yarn [25]. Similarly, artificial neural network can be used to model the spinning process by taking the machine settings and fibre quality parameters [26] and fibre to yarn predictions [27] as the input.…”

Review of Application of Artificial Neural Networks in Textiles and Clothing Industries over Last Decades

“…The results showed that the total classification rate for a wavelet function with a maximum vanishing moment of four and three resolution levels can reach 100%, and differently scaled fabric images had no obvious effect on the classification rate. Shiau et al, (2000) constructed a back-propagation neural network topology to automatically recognize neps and trash in a web by color image processing. The ideal background color under moderate conditions of brightness and contrast to overcome the translucent problem of fibers in a web, specimens were reproduced in a color BMP image file format.…”