Fabric density analysis method and system

Abstract

The invention relates to a fabric density full-automatic analysis method and system. The system comprises an image capturing device, an analysis device, a display unit, a control module, an algorithmmodule and an experiment result management module, wherein the control module obtains a high-definition image to the algorithm module, and outputs the image for display; the algorithm module performsautomatic calibration through a scale target, then performs automatic segmentation on the clear image, directly segments warp yarns and weft yarns in the image, detects one weft yarn in the segmentedimage by using a straight line detection method, performs segmentation correction on the segmented image, and calculates the number of the warp yarns and the weft yarns in the image; and the experiment result management module converts the number of fibers in a standard unit length by combining the automatic calibration result and the number of warp and weft yarns in the image, and completes automatic output of a fiber density experiment result. According to the method, fabric density statistics can be more intelligent, more efficient and more accurate, and the situation that experiment results are inconsistent and even wrong due to experience differences of experimenters, long-term fatigue work, human subjectivity and other reasons is avoided.

Description

technical field [0001] The invention relates to an automatic fabric density analysis method and system, in particular to an automatic scale calibration, which uses deep learning to automatically segment the warp and weft, and uses image processing to correct the angle of the automatically segmented image. And a method and system for automatically calculating the number of warp and weft directions of a fabric per unit length. Background technique [0002] So far, based on the statistical analysis of fabric density, it has only been done manually through a magnifying glass; in the face of a rapidly developing society, the demand for fabric products in the textile industry is also changing with each passing day. Manual identification through a magnifying glass. The traditional magnifying glass identification method has the problems of high labor intensity and low efficiency. The warp and weft density of a sample needs to be concentrated on artificial mental counting and statist...

AI Technical Summary

Problems solved by technology

[0002] So far, based on the statistical analysis of fabric density, it has only been done manually through a magnifying glass; in the face of a rapidly developing society, the demand for fabric products in the textile industry is also changing with each passing day. Manual identification through a magnifying glass. The traditional magnifying glass identification method has the problems of high labor intensity and low efficiency. The warp and weft density of a sample needs to be concentrated on artificial mental counting and statistics under a magnifying glass. Because the weaving methods and colors of fabrics vary widely , this kind of monotonous large-scale repetitive work can easily cause eye fatigue, and the resulting low efficiency and human errors are inevitable; because the nature of the work determines that it is boring and difficult to recruit, resulting in rising labor costs, And due to the strict testing standards, the consequences of making mistakes are serious, so the experience requirements for technicians are even higher; in the face of a large number of fabric densities that need to be tested urgently, traditional manual testing is inefficient, high testing standards, and high labor costs. The current method can no longer Meet the needs of the market; although there are currently methods of fabric density detection using image processing methods, these methods have certain requirements for the fabric itself, for example: the fabric can only be plain weave, only twill weave or plain color can be detected fabrics, or fabrics in the testing process, such as strictly maintaining the weft level, etc.

Images