Image Processing By Computer Used In Evaluating The Fabric Pilling

In this paper,several methods based on image technologies,which make use of newly developed theories in information science,are proposed for automatic detection of pilling on surface of plain fabrics. Image processing technique has the advantages of quickness,accuracy and automation. At present,many manual-testing works can be replaced by image processing technique.How to evaluate the grade of textile pilling is an important thing of textile testing fields. The common way we use is to judge the grades according to the standard sample,but it is greatly subjective and will produce different results among different people. It is difficult for us to describe precisely and quantificationally the amount of pilling. The subject will make some things to introduce the image processing technique into the textile field to evaluate the amount of pilling by image processing technique. And evaluating the grade of fabric pilling has some progresses on the objective and quick evaluation of the amount of pilling.The content includes:1.Analyze the main factors that rises the pilling of the fabric. We make a number of experimentes about the pilling of the fabric on different the craft parameters, such as different blend ratio, yarn degree and the fabric warp density and weft density etc.. Then we analysis and study respectively the results to get in the experimentes and the influences factors that rises the pilling of the fabric.2. Collect the the external appearance picture of The fabric tries. We captured a large number of pictures from surface external appearance on fabric samples that we have collected and standard samples, making use of current a higher distinguish rate capture picture numerical equipments, such as digital camera, scanner, giving or getting an electric shock a mirror etc..3.The processing of the numerical picture.Through transforming the pictures, strengthening the pictures, sharpening the picture, smoothing the pictures etc. we carry on processing the pictures that we have captured from fabric samples and standard samples.4.Take out characteristic valueAnalysed and calculated the processed pictures and taken out characteristic value, such as the hair ball quantity, the hair ball surface of sphere accumulate etc. characteristic parameter.5.Contraste and analyzeContrasted and analyzed each influence factor to rise ball of fabric. Selected characteristic parameter. Made use of characteristic vector from standard sample pictures that rise the ball to assess pilling grade of fabric sample. Since new means with tradition manual means are sameness, we think that it has hope and is viable to develop image processing technique to test pilling on surface of fabrics .The result is correspondent with the method of manual discriminant.The results of experimental are satisfied and the method using computer vision and digital image processing technology to recognize pilling is promising.