Paper defect detection method based on near-field uniform illumination

Abstract

The invention discloses a method for detecting paper defects with near-field uniform illumination, comprising the following steps: 1) calculating the spacing d of lamp beads according to Sparrow's law; The angle α between the direction of the lamp bead pointing to the camera; 3) According to the empirical formula obtained from the experiment: calculate the actual total power Wn of the nth lamp bead, where W represents the rated power of the lamp bead, that is, the middle position lamp The power of the beads, t is the weight coefficient, h is the height from the camera to the detection paper surface; 4) increase the actual total power of each lamp bead to meet the Wn value calculated in step 3); obtain the detected paper image, Direct detection of paper defects by threshold method. The present invention realizes the increase of the far-end luminous flux by increasing the power of the lamp bead in the direction of the far end from the middle lamp bead, so that the gray level uniformity of the image captured by the camera is significantly improved, thereby effectively improving the imaging quality of the paper and making the detection of paper defects easier Accurate, higher detection efficiency.

Description

technical field [0001] The invention relates to the field of paper quality detection in industrial production, in particular to a paper defect detection method with near-field uniform illumination. Background technique [0002] Paper disease refers to the defects or flaws on the paper caused by the production process during the production process of paper, and these defects will affect the quality of the paper. The main function of the paper defect detection system is to detect the existence of paper defects in advance and mark them, so that the areas with paper defects can be removed in time when the paper is rewound. [0003] In the prior art, taking the uniformity of the grayscale of the detected paper defect image as the optimization goal, on the basis of fitting the illuminance distribution function of the LED point light source, the bacterial colony algorithm is used to optimize the parameters of the light source system, and Results The structure of the light source s...

AI Technical Summary

Problems solved by technology

[0005] 1. The gray level uniformity of the image obtained by the existing technology can reach 95%. Before optimization, the filter algorithm is used to make the gray level of the paper image more uniform (but it is easy to filter out small paper defect information), and the image data is obtained. Subtract the pixel value from the standard image, execute at least two loops, read the image data twice, the algorithm complexity is high, the time to judge the paper defect is long, and the execution efficiency of the application is low

Under the current experimental conditions, the maximum speed for detecting paper defects is 300 m / min, and there is still room for improvement

[0006] 2. The existing technology simply observes whether the gray value of the image of the paper is uniform, and uses various algorithms to adjust the gray value of the image, without considering that the light flux emitted by multiple (LED) light sources diffusely reflects and enters the camera is different. It has a great influence on the gray value of the paper image

Paper is used as a secondary light source. Not all the light emitted by the lamp beads is perpendicular to the camera. Most of the light emitted by the (LED) lamp beads in the middle position enters the camera vertically, and only part of the light emitted by the lamp beads in the other positions passes through diffuse reflection. Entering the camera from different angles will cause the gray value at both ends of the paper to be lower than that in the middle of the paper, resulting in uneven gray levels, which will affect the paper defect recognition effect

[0007] 3. The structural modeling of the light source system in the prior art is complex, and the calculation of the power parameters of the light source needs to be realized through complex algorithms, and the power control circuit needs to dynamically adjust the power of the lamp beads multiple times according to the change of the gray value of the image. cumbersome operation

Images