Research On Recognition Of Weft Knitted Fabric Structure Based On Image Processing

Nowadays, in the field of Textile industry, analysis and recognition of knitted fabric mainly depend on manual work or special equipment. Though this way is authoritative, it is not easy to manipulate, and hard to master. Moreover, it is time consuming and tedious. So it has become necessary to research on how to get and analyze knitted fabric structure with computer automatically.In this work, we provide some algorithms to get and analyze knitted fabric construction parameters and structure using Digital Image Processing and Pattern Recognition technology, and develop the flow and technical route of automatic analysis of knitted fabric parameters and structure recognition. First, we analyze the method of knitted fabric image getting and pre-processing to represent more information of knitted fabric construction parameters and characteristic. Then we depict particularly the algorithm of getting knitted fabric construction parameters—vertical and horizontal densities, coil distance: According to the character that knitted fabric's structure is periodic on space, after pre-processing the knitted fabric's image, the point that presents periodic characteristic is achieved with Fast Fourier Transform. Then the image is reconstructed using Inverse Fourier Transform. And the information of the knitted fabric's space frequency is achieved. Using information, the vertical and horizontal densities and coil distance can be calculated. Finally, the results of calculating are compared to the results of manual measuring.In this work, We provided the flow of weft knitted fabric structure analysis and recognition: First, the image of the sample is inputted to computer by scanner. Secondly, image has been pre-processed by some methods, such as Gray Transform, De-noising, Binary-valued to achieve the distinct binary image. Thirdly, the edge image is gained by using Laplacian Operator to detect the binary image. Then the unit image is abstracted from the edge image according to the principle that the unit can present the minimum structure cycle. The characteristic parameters such as chain codes, shape number, surface area, boundary length, are achieved by abstracting characteristic separately from marked targets. Finally, the unknown image can be recognized by these characteristics.The technical route and algorithms we provided above, have gained feasibility validation and achieve applicable results, have certain theoretical value and use for reference in the domain. Because the shape number has no changes when the fabric sample is translated and revolved, we choose the shape number as the characteristic to come over the error during the sampling. The pattern draft recognition method has some innovation in this field, especially analyzing the weft plain knitted fabric, rib knitted fabric and pearl knitted fabric.