Method and system for counting paper through machine vision

Abstract

The invention provides a method and system for counting paper through machine vision, and relates to the technical field of paper counting, and the method comprises the following steps: building an extraction algorithm for shooting stacked paper through an imaging system, analyzing image features, determining splicing feature points of paper stacked images, and building a relation model of paper thickness and pressure; combining the model with a gray projection method to realize paper counting; the machine vision technology can quickly, accurately and automatically count paper through an industrial camera and an image processing algorithm, so that the working efficiency is greatly improved; through an accurate image processing algorithm and high-quality camera shooting equipment, high-precision counting can be guaranteed through machine vision, and the situation of repeated counting or missed counting is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of paper counting, and in particular to a method and system for counting paper using machine vision. Background Art

[0002] Printing plants often need to check paper in their daily work to achieve accurate statistics of paper inventory. Traditional paper counting machines and equipment must be in direct contact with paper during operation, which requires very high machine precision. Improper handling will cause paper creases or damage, and the counting speed is slow and there is a lot of noise.

[0003] Machine vision is a comprehensive technology. Simply put, machine vision is to use machines to replace human eyes for measurement and judgment. The machine vision system converts the captured target into an image signal through machine vision products, transmits it to a dedicated image processing system, obtains the morphological information of the captured target, and converts it into a digital signal based on pixel distribution, brightness, color and other information; the image system performs various operations on these signals to extract the characteristics of the target, and then controls the equipment action on site based on the judgment results. In some dangerous working environments that are not suitable for manual operations or occasions where artificial vision cannot meet the requirements, machine vision is often used to replace artificial vision; at the same time, in the process of mass industrial production, the efficiency and accuracy of product quality inspection using artificial vision are low, and the use of machine vision detection methods can greatly improve production efficiency and the degree of automation of production. In addition, machine vision is easy to realize information integration and is the basic technology for realizing computer integrated manufacturing.

[0004] Therefore, if paper counting can be combined with machine vision technology, work efficiency can be greatly improved. Summary of the invention

[0005] In order to solve the above-mentioned technical problems of existing paper counting, the present invention provides a method and system for paper counting using machine vision, which greatly improves the counting accuracy and efficiency, does not cause creases or damage to the paper, and saves manpower.

[0006] The technical solution adopted by the present invention to solve the technical problem is: a method for counting paper sheets by machine vision, comprising the following steps: S1: An imaging system was built to photograph stacked paper sheets and analyze image features. The imaging system is used to capture images of stacked paper sheets. The system uses a single camera to photograph in a straight line from one side of the paper to the other side, and then analyzes the image features to lay the foundation for subsequent image stitching and paper counting. S2: Determine the extraction algorithm of the splicing feature points of the stacked paper images; by analyzing the relationship between the inner points and the outer points corresponding to the paper stripe skeleton, improve the accuracy of the RANSAC algorithm to estimate the spatial transformation model; in the process of extracting feature points, first use dynamic threshold segmentation to process the image, divide the grayscale image into a binary image, and then use the method of mathematical morphology to process the image; specifically, use the opening operation to smooth the target contour and eliminate noise, use the closing operation to fill holes and connect narrow gaps, and then use the maximum disk method to achieve image refinement to obtain the skeleton features of the paper stripes, and finally extract the endpoints of the skeleton as potential feature points. By analyzing the distribution law between the inner points and outer points in the potential feature points and the corresponding skeleton length, set the skeleton length threshold, and eliminate some potential feature points with smaller skeleton lengths, thereby increasing the proportion of inner points; finally, construct a feature vector, analyze the distribution of feature point matching pairs in the two images with a translation relationship, process the feature vector with the improved DBSCAN clustering algorithm, and achieve image splicing through the RANSAC algorithm; S3: Establish a relationship model between paper thickness and pressure, and combine the model with the grayscale projection method to achieve paper counting; specifically, use the horizontal integral grayscale projection method to obtain the grayscale projection curve of the paper stacking image, and then combine the paper thickness model with the grayscale projection curve to achieve paper counting.

[0007] A system for counting paper using machine vision, comprising: The image acquisition and data analysis module is composed of an industrial camera, image acquisition card, image data cable, lighting fixture, power supply and detection end computer responsible for paper image acquisition and analysis. By applying multiple algorithms, a hardware and software test platform is established to detect the number of paper sheets. The data transmission module is composed of switches, network ports and network cables responsible for information sharing and transmission of all systems; it is used to subdivide the total amount of paper grain inspection into preparatory processing, grain inspection and other links; The signal transmission module is composed of a signal generating device, a signal I / O card and a signal coaxial cable; it is used to generate, push and receive signals required for network detection, thereby completing the communication between the computer and the industrial camera; it completes the motion control of the industrial camera and the collection of basic parameters according to the mobile phone software operation panel; The server module, consisting of a server computer and an alarm device, is responsible for processing, displaying, and storing detection results and warning of error information.

[0008] The beneficial effects of the present invention are: Machine vision technology uses industrial cameras and image processing algorithms to automatically count paper quickly and accurately, greatly improving work efficiency. Through precise image processing algorithms and high-quality camera equipment, machine vision can ensure high-precision counting and avoid repeated counting or missed counting. Through precise image processing algorithms, counting tasks can be completed accurately and without error, reducing the risk of human error. It can be customized and expanded as needed to accommodate different types and sizes of paper, and the algorithms and software can be adjusted according to actual needs; It can adapt to various complex environments, including light changes, paper stacking, etc., to ensure the accuracy of counting; it can achieve long-term working and automatic detection, eliminating the trouble of manual detection, and improving work efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0010] Figure 1 It is a work flow chart of the present invention; Figure 2 It is a system principle diagram of the present invention. DETAILED DESCRIPTION

[0011] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0012] Reference Figure 1 This embodiment provides a method for counting paper sheets using machine vision, comprising the following steps: S1: An imaging system was built to photograph stacked paper sheets and analyze image features. The imaging system is used to capture images of stacked paper sheets. The system uses a single camera to photograph in a straight line from one side of the paper to the other side, and then analyzes the image features to lay the foundation for subsequent image stitching and paper counting. S2: Determine the extraction algorithm of the splicing feature points of the stacked paper images; by analyzing the relationship between the inner points and the outer points corresponding to the paper stripe skeleton, improve the accuracy of the RANSAC algorithm to estimate the spatial transformation model; in the process of extracting feature points, first use dynamic threshold segmentation to process the image, divide the grayscale image into a binary image, and then use the method of mathematical morphology to process the image; specifically, use the opening operation to smooth the target contour and eliminate noise, use the closing operation to fill holes and connect narrow gaps, and then use the maximum disk method to achieve image refinement to obtain the skeleton features of the paper stripes, and finally extract the endpoints of the skeleton as potential feature points. By analyzing the distribution law between the inner points and outer points in the potential feature points and the corresponding skeleton length, set the skeleton length threshold, and eliminate some potential feature points with smaller skeleton lengths, thereby increasing the proportion of inner points; finally, construct a feature vector, analyze the distribution of feature point matching pairs in the two images with a translation relationship, process the feature vector with the improved DBSCAN clustering algorithm, and achieve image splicing through the RANSAC algorithm; S3: Establish a relationship model between paper thickness and pressure, and combine the model with the grayscale projection method to achieve paper counting; specifically, use the horizontal integral grayscale projection method to obtain the grayscale projection curve of the paper stacking image, and then combine the paper thickness model with the grayscale projection curve to achieve paper counting.

[0013] Reference Figure 2 This embodiment provides a system for counting paper sheets using machine vision, including: The image acquisition and data analysis module is composed of an industrial camera, image acquisition card, image data cable, lighting fixture, power supply and detection end computer responsible for paper image acquisition and analysis. By applying multiple algorithms, a hardware and software test platform is established to detect the number of paper sheets. The data transmission module is composed of switches, network ports and network cables responsible for information sharing and transmission of all systems; it is used to subdivide the total amount of paper grain inspection into preparatory processing, grain inspection and other links; The signal transmission module is composed of a signal generating device, a signal I / O card and a signal coaxial cable; it is used to generate, push and receive signals required for network detection, thereby completing the communication between the computer and the industrial camera; it completes the motion control of the industrial camera and the collection of basic parameters according to the mobile phone software operation panel; The server module, consisting of a server computer and an alarm device, is responsible for processing, displaying, and storing detection results and warning of error information.

[0014] Of course, the above description is not limited to the above examples. Technical features not described in the present invention can be achieved by or by using existing technologies, which will not be described here. The above embodiments and drawings are only used to illustrate the technical scheme of the present invention and are not limitations of the present invention. The present invention is described in detail with reference to the preferred implementation methods. Ordinary technicians in this field should understand that changes, modifications, additions or substitutions made by ordinary technicians in this technical field within the essential scope of the present invention do not depart from the purpose of the present invention, and should also fall within the scope of protection of the claims of the present invention.

Claims

1. A method for counting paper sheets using machine vision, characterized in that: The steps include: S1: An imaging system is built to photograph stacked paper and analyze image features; the imaging system is used to capture images of stacked paper. The system uses a single camera to photograph in a straight line from one side of the paper to the other side, and then analyzes the features of the image; S2: Determine the extraction algorithm of the splicing feature points of the paper stacking images; improve the accuracy of the RANSAC algorithm in estimating the spatial transformation model by analyzing the relationship between the inner points and the outer points corresponding to the paper stripe skeleton; in the process of extracting feature points, first use dynamic threshold segmentation to process the image, divide the grayscale image into a binary image, and then use the mathematical morphology method to process the image; S3: Establish a relationship model between paper thickness and pressure, and combine the model with the grayscale projection method to achieve paper counting.

2. The method for counting paper sheets by machine vision according to claim 1, characterized in that: In S2, opening operation is used to smooth the target contour and eliminate noise, and closing operation is used to fill holes and connect narrow gaps. Then, the maximum disk method is used to achieve image refinement and obtain the skeleton features of paper stripes. Finally, the endpoints of the skeleton are extracted as potential feature points. By analyzing the distribution law between the inner points and outer points in the potential feature points and the corresponding skeleton lengths, the skeleton length threshold is set, and some potential feature points with smaller skeleton lengths are eliminated. Finally, a feature vector is constructed, and the distribution of feature point matching pairs in two images with a translation relationship is analyzed. The feature vector is processed with the improved DBSCAN clustering algorithm, and image stitching is achieved through the RANSAC algorithm.

3. The method for counting paper sheets by machine vision according to claim 1, characterized in that: In S3, the horizontal integral grayscale projection method is used to obtain the grayscale projection curve of the paper stacking image, and then the paper thickness model is combined with the grayscale projection curve to realize paper counting.

4. A system for counting paper using machine vision, characterized in that: include: The image acquisition and data analysis module is composed of an industrial camera responsible for paper image acquisition and analysis, an image acquisition card, an image data information coaxial cable, lighting fixtures, a power supply and a detection end computer; The data transmission module is composed of switches, network ports and network cables responsible for information sharing and transmission of all systems; The signal transmission module is composed of a signal generating device, a signal I / O card and a signal coaxial cable; The network server module is composed of a network server computer and alarm equipment.

Images