CN116863138A

CN116863138A - Verification system and method for material identification result of color sorter

Info

Publication number: CN116863138A
Application number: CN202310822142.5A
Authority: CN
Inventors: 张英; 周星
Original assignee: Lauffer Vision Technology Co ltd
Current assignee: Lauffer Vision Technology Co ltd
Priority date: 2023-07-06
Filing date: 2023-07-06
Publication date: 2023-10-10

Abstract

The invention discloses a verification system and method for a color sorter material identification result, and relates to the technical field of image identification. The invention comprises a color selection device and a PC host; the color selection device comprises an image acquisition device, a processing device and an illumination lamp tube; the image acquisition equipment comprises a first FPGA module and a camera; the camera is used for collecting sample picture information of the materials; the first FPGA is used for sending the sample picture information to the PC host through a UDP protocol; the PC host comprises a second FPGA module and a prototype system positioned on the second FPGA module; the prototype system comprises a picture preprocessing module, a material extraction module, a material identification module, a graphical display interface and a database. According to the invention, through establishing connection communication with the color selector, a sample picture is obtained and is used as a data analysis source, then an analysis algorithm is utilized to simulate a material selection process in a prototype system, further a color selection result is calculated, and finally the result is drawn on a graphical interface and visually displayed, so that the operation and debugging efficiency of the color selector is greatly improved.

Description

Verification system and method for material identification result of color sorter

Technical Field

The invention belongs to the technical field of image recognition, and particularly relates to a verification system and a verification method for a material recognition result of a color selector.

Background

The quality of the processing result of the color selector is firstly determined by whether the materials can be accurately identified according to the requirements, such as authorized, the color judgment and separation method of the color CCD color selector with the publication number of CN103272783B, the color of the materials is rapidly judged by adopting various chromaticity modes, whether the materials are reserved or removed is determined, and the color selector is suitable for color selection of transparent materials and other materials needing front-back combined color selection; multiple separation is judged once, and the color selection process is fast and effective. Although multiple classification can be judged once, the color selection process is improved quickly and effectively, colors cannot be intuitively configured on the color selector, and therefore a lot of manpower and material resources are consumed on the color selector.

The invention aims to intuitively draw the material identification result on the application software, on one hand, the repeated blanking test is not needed to count the color selection result, the manpower and material resources are saved, on the other hand, the result is more intuitively embodied, and meanwhile, the more ideal sorting result can be obtained by quickly adjusting the parameter simulation. Therefore, the overall operation efficiency and the operation accuracy of the color selector can be effectively improved.

Disclosure of Invention

The invention aims to provide a verification system and a verification method for a material identification result of a color selector, wherein a sample picture is obtained by establishing connection communication with color selector equipment and is used as a data analysis source; and then simulating a material selection process in a prototype system by using an analysis algorithm, further calculating a color selection result, and finally drawing the result on a graphical interface for visual display, thereby solving the problems that the conventional color selector needs repeated blanking test to count the color selection result, the operation efficiency of the color selector is low and the accuracy is not enough.

In order to solve the technical problems, the invention is realized by the following technical scheme:

the invention relates to a verification system for a color sorter material identification result, which comprises color sorter equipment and a PC host, wherein the color sorter equipment comprises image acquisition equipment, processing equipment and an illumination lamp tube; the image acquisition equipment comprises a first FPGA module and a camera; the camera is used for collecting sample picture information of materials; the first FPGA is used for sending the sample picture information to the PC host through a UDP protocol; the PC host establishes communication connection with the color selection device through a network; the PC host comprises a second FPGA module and a prototype system positioned on the second FPGA module; the prototype system comprises a picture preprocessing module, a material extraction module, a material identification module, a graphical display interface and a database; the picture preprocessing module is used for performing pixel segmentation and background identification after cutting the image; the material extraction module is used for operating set difference set operation in an available data range after preprocessing the picture to extract the material; the material identification module is used for identifying the materials extracted by the material extraction module; the graphical display interface is used for marking and drawing the materials on the graphical interface by adopting different colors, and simultaneously, counting and analyzing the sorting effect of the components of each material; the database is used for storing sample pictures and identifying the materials of the sample pictures.

As a preferable technical scheme, the graphic display interface supports zooming, moving and framing of pictures, is used for checking and analyzing color selection algorithm results, and can timely adjust algorithm parameters to perform simulation calculation again.

As a preferable technical scheme, the database also supports historical data inquiry and printout, is used for reserving data in a record table for each analysis result, and is ordered according to time sequence, supports annual, month, week and calendar history data inquiry, and supports selecting any data for printout.

As a preferable technical scheme, the prototype system sequentially reads the picture file, simulates a color selection algorithm, marks sorting processing results differently, and simultaneously visually displays the sorting processing results on a graphical interface.

The invention relates to a verification method for a material identification result of a color sorter, which comprises the following steps:

step S1, image preprocessing: cutting the image, segmenting pixels, and recording the user data as a set U;

step S2, background identification: selecting a background area, extracting color characteristic values, identifying a background, and marking the background as a set AO;

step S3, extracting materials: extracting materials by utilizing set difference set operation (U-A0) in the available data range;

s4, material identification: selecting proper color components to identify materials;

step S5, outputting a result: storing the material identification result into a database file, marking and drawing the material identification result on a graphical interface by adopting different colors, and counting the sorting effect of each material component

As a preferred technical solution, in the step S1, the image preprocessing includes the following steps:

step S11: noise and interference eliminating treatment is carried out on the image;

step S12: dividing the image into different areas by using an image dividing algorithm;

step S13: deleting pictures which do not contain materials in the area;

step S14: features are extracted from the segmented image using image analysis techniques.

As a preferred technical solution, in step S12, the image segmentation algorithm specifically includes:

step 21: for an RGB color image, respectively generating a group of hierarchical histograms in an R color plane, a G color plane and a B color plane;

step S22: thresholding the top histogram in each group of hierarchical histograms to finish the initial segmentation of the image and form a plurality of clusters;

step S23: and merging clusters formed by the initial segmentation to finish the final segmentation of the image.

As a preferred embodiment, in step S12, the method for generating a set of hierarchical histograms is as follows:

for one color image I with MxN, according to the formulaGenerating an original histogram at R, G and B color planes respectively, wherein the original histogram is used as a 1 st layer histogram of a hierarchical histogram of each color plane, namely a lowest layer histogram;

the histogram h _i Each bin in (1) is a triplet (i.e., intensity value is 1, and pixel number is count=h) _i (l) The right boundary of the box is right, the right boundary of the box bin of the first layer of histogram is equal to the intensity value corresponding to the box, and l=256 is the intensity range of three color planes.

As a preferred technical solution, in step S22, the following calculation is performed according to the original histogram of the R, G, B color plane, respectively:

the gray formula for calculating R, G, B color plane is as follows, and integrates the threshold w _i ：

As a preferred technical solution, in the step S4, a specific process of selecting a suitable color component to identify the material is as follows:

step S41: firstly, carrying out statistical analysis on the picture in a statistical histogram mode;

step S42: selecting ideal color components close to normal distribution or operation combination of the color components as Key values for material identification through a histogram analysis result, and obtaining threshold values corresponding to the Key values;

step S43: and carrying out cluster analysis by using the K average value to identify different required material components.

The invention has the following beneficial effects:

according to the invention, through establishing connection communication with the color selector, a sample picture is obtained and is used as a data analysis source, then an analysis algorithm is utilized to simulate a material selection process in a prototype system, further a color selection result is calculated, and finally the result is drawn on a graphical interface and visually displayed, so that the operation and debugging efficiency of the color selector is greatly improved.

Of course, it is not necessary for any one product to practice the invention to achieve all of the advantages set forth above at the same time.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of a verification system for identifying material of a color sorter according to the present invention;

FIG. 2 is a flow chart of a method for verifying the identification result of a material for a color sorter according to the present invention;

FIG. 3 is a flow chart of image preprocessing;

FIG. 4 is a flowchart of an image segmentation algorithm;

FIG. 5 is a flow chart for identifying materials by selecting appropriate color components.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Referring to fig. 1, the present invention is a verification system for identifying material in a color sorter, and is a device for automatically sorting out different color particles in a particulate material by using a photoelectric detection technology according to differences of optical characteristics of the material. The color selector is used for detecting and grading bulk materials or packaging industrial products and food quality, and comprises color selecting equipment and a PC host, wherein the color selecting equipment comprises image acquisition equipment, processing equipment and an illumination lamp tube; the image acquisition equipment comprises a first FPGA module and a camera; the camera is used for collecting sample picture information of the materials; the first FPGA is used for sending the sample picture information to the PC host through a UDP protocol; the PC host establishes communication connection with the color selection device through a network; the PC host comprises a second FPGA module and a prototype system positioned on the second FPGA module; the prototype system comprises a picture preprocessing module, a material extraction module, a material identification module, a graphical display interface and a database; the picture preprocessing module is used for performing pixel segmentation and background identification after cutting the image; the material extraction module is used for operating set difference set operation in the available data range after preprocessing the pictures to extract materials; the material identification module is used for identifying the materials extracted by the material extraction module; the graphic display interface is used for drawing on the graphic interface by adopting different color labels, and simultaneously counting and analyzing the sorting effect of each material component; the database is used for storing sample pictures and identifying the materials of the sample pictures.

The PC host is in bidirectional communication connection with the color line equipment through the interface, and the PC host sends an illumination instruction to the illumination lamp tube according to the effect of collecting pictures according to the color selector, so that the shooting effect is in an optimal state.

The graphic display interface supports zooming, moving and framing of pictures, is used for checking and analyzing color selection algorithm results, and can timely adjust algorithm parameters to perform simulation calculation again. The database also supports historical data inquiry and printout, is used for keeping data in a record table for each analysis result, sequencing the data according to time sequence, supporting annual, month, week and calendar history data inquiry, and supporting selecting any data for printout. The prototype system sequentially reads the picture file, simulates a color selection algorithm, marks sorting processing results differently, and simultaneously visually displays the sorting processing results on a graphical interface.

Referring to fig. 2, the invention is a verification method for identifying material of a color sorter, comprising the following steps:

Referring to fig. 3, in step S1, the image preprocessing includes the following steps:

step S13: deleting pictures which do not contain materials in the area;

Referring to fig. 4, in step S12, the image segmentation algorithm specifically includes:

In step S12, the method for generating a set of hierarchical histograms is as follows:

for one color image I with MxN, according to the formulaGenerating original histograms at R, G and B color planes thereof, respectively, the original histograms being taken as the individual color planesThe 1 st layer histogram of the hierarchical histogram, namely the lowest layer histogram;

histogram h _i Each bin in (1) is a triplet (i.e., intensity value is 1, and pixel number is count=h) _i (l) The right boundary of the box is right, the right boundary of the box bin of the first layer of histogram is equal to the intensity value corresponding to the box, and l=256 is the intensity range of three color planes.

In step S22, the following calculation is performed according to the original histogram of the R, G, B color plane, respectively:

Referring to fig. 5, in step S4, a specific process of selecting a suitable color component to identify a material is as follows:

Example 1

In the embodiment, firstly, a sample picture is acquired as a data analysis source by establishing connection communication with color selection equipment; and then simulating a material selection process in a prototype system by using an analysis algorithm, further calculating a color selection result, and finally drawing the result on a graphical interface for visual display.

In order to realize the functions, communication connection is established between the prototype system and the color selection device through a network, a sample picture is transmitted by using a UDP protocol, and the prototype system organizes and manages the prototype system according to a specific rule after receiving the picture and stores the prototype system in a local file. The prototype system sequentially reads the picture files, simulates a color selection algorithm, marks the sorting processing results differently, and simultaneously visually displays the sorting processing results on the graphical interface. The graphic interface supports operations such as zooming, moving, frame selection and the like, can conveniently check and analyze the processing result of the color selection algorithm, can timely adjust related algorithm parameters to simulate calculation again, further can easily obtain an ideal analysis result, and greatly improves the operation and debugging efficiency of the color selection machine. The system also supports historical data inquiry and printout, keeps data in a record table for each analysis result, is arranged according to time sequence, supports annual, month, week and calendar history data inquiry, and can select a certain piece of data printout as an analysis basis.

The prototype system adopts a C/S mode system architecture, uses QT development, and can be laid out on a window system or a Linux system due to the portability of the QT, and the specific implementation steps are as follows:

1. establishing network communication and obtaining a sample picture;

and establishing communication with the color selection equipment through a network, adjusting the surface illumination equipment in the color selection equipment, shooting materials entering the color selection equipment, taking the shot picture as a sample picture, and transmitting the sample picture by using a UDP protocol.

2. Sample picture organization management is carried out and stored locally;

the prototype system organizes and manages the received pictures according to specific rules after receiving the pictures, if the received pictures are named according to the receiving time, folders can be respectively created by the year, month, week and day and stored in the locally corresponding folders.

3. Setting parameters and realizing a color selection algorithm;

setting working parameters of color selection equipment, cutting an image, segmenting pixels, and recording user data as a set U; selecting a background area, extracting color characteristic values, identifying a background, and marking the background as a set AO; and (3) extracting materials by using a set difference set operation (U-A0) in the available data range:

and selecting proper color components to identify materials.

4. Reading a sample picture, and performing simulation color selection calculation;

the prototype system sequentially reads the picture files, simulates a color selection algorithm, marks the sorting processing results differently, and simultaneously visually displays the sorting processing results on the graphical interface. The graphic interface supports operations such as zooming, moving, frame selection and the like, can conveniently check and analyze the processing result of the color selection algorithm, can timely adjust the parameters of the related algorithm to simulate calculation again, further can easily obtain an ideal analysis result, and greatly improves the operation and debugging efficiency of the color selection machine

5. Outputting the result to a graphical interface;

the graphic interface supports operations such as zooming, moving, frame selection and the like, can conveniently check and analyze the processing result of the color selection algorithm, can timely adjust related algorithm parameters to simulate calculation again, further can easily obtain an ideal analysis result, and greatly improves the operation and debugging efficiency of the color selection machine.

6. Saving the result to historical data;

the graphic interface supports operations such as positioning, amplifying, shrinking, moving, selecting frames and the like, and supports coordinate viewing and corresponding position RGB, HSV and other map values;

the historical data is ordered by time, supports viewing by year, month, week and day, and can be selectively printed out.

Example two

The simulation algorithm steps are as follows:

1. and (5) preprocessing an image. And cutting the image, dividing pixels, and improving the usability of the data. The available data is denoted as set U.

2. And (5) background identification. And selecting a background area, extracting color characteristic values, identifying a background, and marking the background as a set A0.

3. And (5) extracting materials. And after image processing and background identification, extracting the materials by using a set difference set operation (U-A0) in the available data range.

4. And (5) material identification. The color selector picture is mainly represented by the synthesized values of four channels N/R/G/B, and the response sensitivity of different materials to different color components is greatly different, so that the selection of proper color components is particularly critical to accurately identifying the materials. According to the method, a statistical histogram is adopted to carry out statistical analysis on a picture, and then an ideal color component close to normal distribution or an operation combination of the color components is selected as a Key value for material identification according to a histogram analysis result, and a threshold value corresponding to the Key is obtained. And then carrying out cluster analysis by using the K average value to identify different material components such as good materials, bad materials, waste materials and the like.

5. And outputting a result. Storing the material identification result into a specific database file, reading the database file, drawing the database file on a graphical interface by adopting different color labels, and simultaneously, statistically analyzing the sorting effect of each material component. The form of the material and the material identification result can be visually seen from the graphical interface, and the situation that whether the material is identified by mistake or not is checked by the characteristic value can also be checked. The material form has a considerable influence on the extraction of the characteristics in the color selection process, so that the judgment of the material form can be fed back to the scientific rationality of the mechanical mechanism design. And whether the color selection result meets the standard can also be directly judged from the result of the statistical analysis. If the current color selection scheme of the color selector is not up to the standard, the material identification algorithm in the step 4 can be adjusted, the analysis is re-identified until the ideal target is achieved, and meanwhile, whether the current color selection scheme of the color selector is available or not is fed back, and whether the adjustment of a structure (influencing the material shape), a light source and the like is needed or not is carried out.

It should be noted that, in the above system embodiment, each unit included is only divided according to the functional logic, but not limited to the above division, so long as the corresponding function can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.

In addition, those skilled in the art will appreciate that all or part of the steps in implementing the methods of the embodiments described above may be implemented by a program to instruct related hardware, and the corresponding program may be stored in a computer readable storage medium.

The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.

Claims

1. The verification system for the material identification result of the color sorter comprises color sorter and a PC host, wherein the color sorter comprises image acquisition equipment, processing equipment and an illumination lamp tube; the image acquisition equipment comprises a first FPGA module and a camera; the camera is used for collecting sample picture information of materials; the first FPGA is used for sending sample picture information to the PC host through a UDP protocol, and is characterized in that:

the PC host establishes communication connection with the color selection device through a network;

the PC host comprises a second FPGA module and a prototype system positioned on the second FPGA module; the prototype system comprises a picture preprocessing module, a material extraction module, a material identification module, a graphical display interface and a database; the picture preprocessing module is used for performing pixel segmentation and background identification after cutting the image; the material extraction module is used for operating set difference set operation in an available data range after preprocessing the picture to extract the material; the material identification module is used for identifying the materials extracted by the material extraction module; the graphical display interface is used for marking and drawing the materials on the graphical interface by adopting different colors, and simultaneously, counting and analyzing the sorting effect of the components of each material; the database is used for storing sample pictures and identifying the materials of the sample pictures.

2. The verification system for color sorter material recognition results according to claim 1, wherein the graphical display interface supports zooming, moving and framing of pictures for viewing and analyzing color sorter algorithm results, and simultaneously can adjust algorithm parameters in time for analog calculation again.

3. A verification system for identification of materials in a color selector as defined in claim 1 wherein the database further supports historical data querying and printout for maintaining data in a log table for each analysis and ordering in time sequence, supporting year, month, week, calendar history data querying and selecting any data for printout.

4. The verification system for material identification results of a color sorter according to claim 1, wherein the prototype system sequentially reads a picture file, simulates a color sorting algorithm, marks sorting results differently, and simultaneously visually displays the sorting results on a graphical interface.

5. A method of validating a validation system for a material identification result of a color sorter as claimed in any one of claims 1 to 4 comprising the steps of:

step S5, outputting a result: storing the material identification result into a database file, marking and drawing the material identification result on a graphical interface by adopting different colors, and counting the sorting effect of each material component.

6. The authentication method according to claim 5, wherein in the step S1, the image preprocessing includes the steps of:

step S13: deleting pictures which do not contain materials in the area;

7. The method according to claim 6, wherein in step S12, the image segmentation algorithm specifically includes:

8. The method of verifying as defined in claim 7, wherein the step S12 is performed by generating a set of hierarchical histograms as follows:

9. The method according to claim 7, wherein in the step S22, the following calculation is performed according to the original histogram of the R, G, B color plane:

10. The method according to claim 4, wherein in the step S4, the specific process of selecting the appropriate color component to identify the material is as follows: