Gray level illumination compensation method for uniform target surface defect detection
A defect detection and compensation method technology, applied in the field of computer vision, to achieve the effect of multi-algorithm space, wide application range, and reduced demand
Pending Publication Date: 2021-06-18
SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
At present, few people perform gray-scale illumination compensation on the collected images. Based on the above theory, this patent proposes a gray-scale value compensation method based on an ideal illumination model.
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
[0030] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.
[0031] Refer to attached figure 1 , attached Figure 2a ~ Figure 2d , the concrete steps of the present invention are as follows:
[0032] Step 1: Calibrate the surface vibration industrial camera, and use the industrial camera to collect images of the paper tube to be inspected;
[0033] Step 2: Perform the following steps 2.1 to 2.4 for each original image;
[0034] Step 2.1: remove the high-frequency components of the image to be detected, and perform average filtering on the image;
[0035] Step 2.2: average the gray value of the averaged image; add and average the row gray values to obtain a row average curve; add and average the column gray values to obtain a column average curve;
[0036] Step 2.3: Using the average of multiple images (not less than 100) to obtain the gray value line average smooth curve, and normalize the line ...
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 relates to an illumination compensation method based on uniform target surface defect detection. The method comprises the following steps: firstly, carrying out image acquisition on a detection target by using a calibrated industrial camera; secondly, subjecting the image to average preprocessing, and reducing local noise generated by a single bright spot and a single dark spot; respectively carrying out row averaging and column averaging processing again to obtain a row averaging curve and a column averaging curve; carrying out average value processing on the plurality of images and a plurality of obtained row average curves and column average curves so as to obtain a smooth row average curve and a smooth column average curve; carrying out normalization processing on the smooth gray average value, then carrying out interpolation processing based on a normalized value, and obtaining a continuous and smooth ideal model gray image model based on the illumination condition; and obtaining an illumination compensation template by using a difference value between the maximum gray value image and the interpolated ideal gray value image. According to the method, the image gray scale with uneven illumination can be effectively compensated, and a high-quality image which is closer to uniform illumination is provided for subsequent processing.
Description
technical field [0001] The invention relates to the technical field of computer vision, in particular to a grayscale illumination compensation method for uniform target surface defect detection. Background technique [0002] The technical background of this image gray value illumination compensation technology is based on the surface defect detection of cylindrical paper tubes. Defect detection requires high image quality. Uneven illumination causes large differences in the gray value of the collected images. Many algorithms are difficult to use in subsequent processing, especially algorithms based on gray features. To obtain an image with uniform illuminance, a light source with a shape similar to the target is required. Currently, tunnel light sources are mostly used to obtain images with uniform grayscale illuminance. Large; the market standard light source is difficult to meet the demand, and the structure of the light source becomes complicated, and the custom-made lig...
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 IPC IPC(8): G06T5/50G06T5/00G06T3/40G06T7/90
CPCG06T5/50G06T3/4023G06T7/90G06T2207/20024G06T2207/20224G06T5/70
Inventor 刘明洋贺云白鑫林徐永利徐志刚侯雯中陈月玲杜木雄张世轩
Owner SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI