Collecting method of hyperspectral image for recognizing wetted area of colorful fabric

Abstract

The invention discloses a collecting method of a hyperspectral image for recognizing a wetted area of a colorful fabric. The collecting method is characterized in that an EVA (ethylene vinyl acetate)foam improved clamping device is used for providing a precise division boundary for the image extracting of a tested area; the hyperspectral image is a gray level image set at a plurality of wavebandchannels, the gray level images at the near-infrared wave band can be extracted, and the image brightness value is unrelated with R (red), G (green) and B (blue) components, so as to effectively overcome the influence by the fabric color; direct current is used for supplying power for a diffuse reflection type halogen light source, and the intensity of light provided by a light source is stable; amotor is used for pushing a specimen on a specimen carrying box at uniform speed through an electrically-controlled conveying belt so as to enable a CCD (charge coupled device) camera to scan by lines, and the light intensity in the scanning process of the fabric each time is the same, and is equivalent to the uniform light intensity of the fabric surface; after the image is collected by a hyperspectral image collecting system, white board correction and dark current correction methods are adopted, and the influence by the nonuniform light radiation at the image surface of the original fabricis further eliminated; the wetted area and the unwetted area have better contrast degree in the gray level image at the infrared waveband, and the influence by the texture of the fabric surface can be effectively overcome by proper resolution ratio.

Description

【Technical field】 [0001] The invention relates to the technical field of textile and garment performance testing, in particular to a hyperspectral image acquisition method for identifying wet areas of multi-color fabrics. 【Background technique】 [0002] The identification of the wet area of ​​the fabric in the process of traditional artificial fabric wetness rating is easily affected by the assessor's physiology and psychology, light environment, fabric texture and color, and the experimental results have large errors and poor consistency. In order to solve these problems, an image processing-based identification method of fabric wetted area appeared for the spraying method of AATCC standard. [0003] The difficulty of the fabric wetting area recognition method based on image processing is that the contrast between the wetting area and the non-wetting area to be segmented is small, and the segmentation results are greatly affected by uneven illumination on the sample surface...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to overcome the deficiencies of the above-mentioned prior art, and provide a hyperspectral image acquisition method for identifying the wet area of ​​multi-color fabrics, which aims to solve the problem of identifying the wet area of ​​the fabric based on the image processing algorithm. , fabric texture, uneven lighting, lighting changes and other interference effects, resulting in technical problems such as low contrast between wetted and non-wetted areas and easy mis-segmentation of test areas

Images