A dynamic detection method for fabric defects driven by visual data
A data-driven, dynamic detection technology, applied in image data processing, electrical digital data processing, special data processing applications, etc., can solve problems such as weak detection universality, low detection accuracy, and inaccurate defect segmentation.
Active Publication Date: 2017-09-01
XI'AN POLYTECHNIC UNIVERSITY
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The purpose of the present invention is to provide a dynamic detection method for fabric defects driven by visual data, which solves the problems of low detection accuracy, inaccurate defect segmentation and poor detection universality in the prior art
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0076] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0077] The present invention is a dynamic detection method for fabric defects driven by visual data, such as figure 1 As shown, the specific steps are as follows:
[0078] Step 1, convert the fabric image collected in RGB space into fabric image in HSV space; specifically:
[0079] The RGB space fabric image collected by the image sensor is converted into the fabric image of the HSV space, and the conversion process is shown in formula (1);
[0080]
[0081] Among them, the value ranges of R, G, and B are all [0,255]; the value range of H is [0,360]; the value range of S is [0,1]; the value range of V is [0,255].
[0082] Step 2, extract the saturation feature S and brightness feature V of the image to form a saturation feature map and a brightness feature map, specifically: use the saturation S and brightness V in the HSV space that con...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a fabric defect dynamic detection method based on visual data drive. The method specifically comprises the following steps that first, a collected fabric image in RGB space is converted into an HSV space fabric image; second, the saturation feature S and the luminance feature V of the image are extracted to form a saturation feature map and a luminance feature map; third, saliency maps are formed on the saturation feature map and the luminance feature map obtained in the second step through visual data drive; fourth, based on the third step, a range is used for determining a threshold value, and defect information is segmented; fifth, the segmented defect information is fused into integrated defect information. By means of the fabric defect dynamic detection method based on visual data drive, the problems that detection accuracy is not high, defects cannot be segmented accurately and detection universality is not high in the prior art are solved.
Description
technical field [0001] The invention belongs to the technical field of dynamic detection methods for fabric defects, and in particular relates to a dynamic detection method for fabric defects driven by visual data. Background technique [0002] Fabric defect detection is one of the most important parts of textile quality control. At present, traditional fabric defect detection is done by manual offline detection. However, human attention is affected by factors such as time, detection environment, and mood, which can easily cause defects such as false detection and missed detection. In order to solve the shortcomings of manual detection, automatic detection of fabric defects has become one of the hot topics studied by scholars at home and abroad in recent years. With the development of computer and image processing technology, the image processing algorithm, which is the key technology of fabric defect detection, must become a research hotspot. [0003] In the space domain...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/30
CPCG06T7/0004
Inventor 管声启吴宁
Owner XI'AN POLYTECHNIC UNIVERSITY