CN111062379A - Identification error-proofing recognition method, device, storage medium and system - Google Patents
Identification error-proofing recognition method, device, storage medium and system Download PDFInfo
- Publication number
- CN111062379A CN111062379A CN201811201575.4A CN201811201575A CN111062379A CN 111062379 A CN111062379 A CN 111062379A CN 201811201575 A CN201811201575 A CN 201811201575A CN 111062379 A CN111062379 A CN 111062379A
- Authority
- CN
- China
- Prior art keywords
- image
- target image
- identification
- target
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The application relates to an identification error-proofing identification method, device, storage medium and system, which are used for acquiring a target image acquired by a target object; analyzing and processing the target image, and extracting to obtain a foreground image in the target image; and when the identification information is extracted from the foreground image, comparing and identifying the identification information with a preset labeling identification template to obtain an identification result. Through carrying out analysis processes to the target image who obtains, extract the identification information who obtains in the prospect image, can high-efficiently realize the mistake proofing discernment based on preset subsides mark template compares, can effectively avoid the mistake that the sign pasted the in-process and appear to paste the scheduling problem, can reduce printed matter sign and paste the defective rate, promote product quality, improve production efficiency.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a storage medium, and a system for identifying an identifier with error protection.
Background
With the continuous development and improvement of computer technology, electromechanical control technology, intelligent detection technology and digital image processing technology, people begin to combine the intelligent abstract capability of human vision with the high speed, high precision and high reliability of processors.
In modern industrial production, many industries put higher demands on detection. In the process of sticking the printed product identification, the problems of multiple sticking, reverse sticking, skew sticking, wrong sticking and the like of the identification often occur, a labeler does not find the identification in time in the self-checking process, the shutdown is caused, the package is returned, the production is seriously influenced, and the production efficiency is low.
Disclosure of Invention
Therefore, it is necessary to provide a method, an apparatus, a storage medium, and a system for identifying an identifier with error proofing, which effectively improve the production efficiency, in order to solve the technical problem of low production efficiency caused by manual detection in the conventional identifier pasting process.
An identification error-proofing recognition method, the method comprising:
acquiring a target image acquired from a target object;
analyzing and processing the target image, and extracting to obtain a foreground image in the target image;
and when the identification information is extracted from the foreground image, comparing and identifying the identification information with a preset labeling identification template to obtain an identification result.
In one embodiment, the step of analyzing the target image and extracting a foreground image in the target image includes:
processing the target image to obtain color information and position information of the target image;
and extracting to obtain a foreground image in the target image according to the color information and the position information of the target image and a preset segmentation threshold value.
In one embodiment, before the step of processing the target image to obtain the color information and the position information of the target image, the method further includes:
and adjusting the size of the target image according to a preset size, and correcting the position of the target image according to a preset standard coordinate system.
In one embodiment, after the step of obtaining a foreground image in the target image according to the color information and the position information of the target image and a preset segmentation threshold, the method further includes:
and smoothing the foreground image according to preset image smoothing data.
In one embodiment, before the step of acquiring the target image acquired from the target object, the method further includes:
and establishing a labeling identification template.
In one embodiment, after the step of obtaining the identification result by comparing and identifying the identification information with a preset labeling identification template when the identification information is extracted from the foreground image, the method further includes:
and outputting corresponding prompt information according to the identification result.
In one embodiment, after the step of analyzing the target image and extracting a foreground image in the target image, the method further includes:
and when the identification information is not extracted from the foreground image, outputting a recognition result.
An identification error-proofing recognition device, the device comprising:
the target image acquisition module is used for acquiring a target image acquired by a target object;
the foreground image extraction module is used for analyzing and processing the target image and extracting a foreground image in the target image;
and the identification module is used for comparing and identifying the identification information with a preset labeling identification template to obtain an identification result when the identification information is extracted from the foreground image.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring a target image acquired from a target object;
analyzing and processing the target image, and extracting to obtain a foreground image in the target image;
and extracting identification information from the foreground image, and comparing and identifying the identification information with a preset labeling identification template to obtain an identification result.
An identification error-proofing recognition system comprises an optical acquisition device and a processor, wherein the optical acquisition device is connected with the processor,
the optical acquisition equipment is used for acquiring an image of a target object and sending the image to the processor;
the processor is used for executing the steps to obtain the identification result.
The identification error-proofing identification method, the identification error-proofing identification device, the storage medium and the identification error-proofing identification system acquire a target image acquired by a target object; analyzing and processing the target image, and extracting to obtain a foreground image in the target image; when the identification information is extracted from the foreground image, the identification result is obtained by comparing and identifying the identification information with a preset labeling identification template. Through carrying out analysis processes to the target image who obtains, extract the identification information who obtains in the prospect image, can high-efficiently realize the mistake proofing discernment based on preset subsides mark template compares, can effectively avoid the mistake that the sign pasted the in-process and appear to paste the scheduling problem, can reduce printed matter sign and paste the defective rate, promote product quality, improve production efficiency.
Drawings
FIG. 1 is a flow diagram of a method for identifying error-proofing identification in one embodiment;
FIG. 2 is a flow diagram of a method for identifying error-proofing identification in another embodiment;
FIG. 3 is a flow chart of a method for identifying error-proofing identification in yet another embodiment;
FIG. 4 is a flow chart of a method for identifying error-proofing identification in yet another embodiment;
FIG. 5 is a flow chart of a method for identifying error-proofing identification in yet another embodiment;
FIG. 6 is a flow chart of a method for identifying error proofing identification in yet another embodiment;
FIG. 7 is a flow chart of a method for identifying error proofing identification in yet another embodiment;
FIG. 8 is a diagram of an embodiment of a structure of an identification error proofing recognition apparatus;
FIG. 9 is a diagram of an identification error proofing identification system architecture in one embodiment;
FIG. 10 is a block diagram of an identification error proofing recognition system in accordance with another embodiment;
FIG. 11 is a diagram illustrating an application environment and operational flow of an identification error protection recognition system in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In one embodiment, as shown in fig. 1, there is provided an identification error-proofing recognition method, which is described by taking the method as an example applied to a processor, and includes the following steps:
step S110: and acquiring a target image acquired by the target object.
Specifically, by using optical acquisition equipment, such as an industrial camera, a light source, a matched image acquisition card and other hardware, and based on a visual detection technology, an image of a target object at an acquisition position is acquired through a machine vision product, the target object is converted into a picture form and sent to a processor, a material is provided for subsequent analysis and processing, and the optical acquisition equipment is equivalent to an eye for manual detection.
Step S120: and analyzing the target image, and extracting to obtain a foreground image in the target image.
Specifically, the target image includes a background image and a foreground image. And segmenting the target image, segmenting the foreground image and the background image, and extracting to obtain the foreground image. The processor processes the target image, converts the target image into a digital signal according to information such as pixel distribution, brightness and color of the target image, and performs image processing operation on the signal to extract the characteristics of the target image.
Step S130: when the identification information is extracted from the foreground image, the identification result is obtained by comparing and identifying the identification information with a preset labeling identification template.
Specifically, when the target object is pasted with the mark, the foreground image contains the mark information, the mark information is extracted from the foreground image and is the mark image, the problems of askew pasting, multiple pasting, reverse pasting, wrong pasting and the like of the mark can be identified and obtained by comparing the mark information with a preset labeling mark template, and then the operation of on-site equipment is controlled according to the judgment result, so that the abnormal part is automatically identified.
According to the identification error-proofing identification method, the obtained target image is analyzed, the identification information in the foreground image is extracted, the identification information is compared based on the preset labeling identification template, error-proofing identification can be efficiently realized, the problems of error labeling and the like in the identification pasting process can be effectively avoided, the printed product identification pasting reject ratio can be reduced, the product quality is improved, and the production efficiency is improved.
In one embodiment, as shown in FIG. 2, step S120 includes step S122 and step S124.
Step S122: and processing the target image to obtain the color information and the position information of the target image.
Specifically, the target image is processed in a form that color information and position information can be conveniently obtained, in this embodiment, the target image is specifically subjected to binarization processing, image binarization (image binarization) is a process in which a gray value of a pixel point on the image is set to 0 or 255, that is, the whole image exhibits an obvious black-and-white effect, and the binarization of the image greatly reduces the data amount in the image, so that the outline of the target image can be highlighted. And after the target image is subjected to binarization processing, color information and position information of the target image are obtained.
Step S124: and extracting to obtain a foreground image in the target image according to the color information and the position information of the target image and a preset segmentation threshold value.
Specifically, each frame of image is composed of image elements, and the segmentation process for decomposing the target object in the scene is a decision process, and the substantial algorithms thereof are divided into two types, namely a pixel technology and a region technology.
The image point technology is to compare and classify each image point by using a preset segmentation threshold and a gray level method of the image point, the gray level values of pixels of a background image and a foreground image are different, a critical point is found out by analyzing the gray level value difference of the pixels, and the critical point is set as the threshold. In this embodiment, a K-means algorithm is used to realize segmentation of a foreground image and a background image, the K-means algorithm is an unsupervised cluster learning algorithm, natural classes of sample data are tried to be found, the classification K is defined by a user, and under the condition that the K mean value does not need any other prior knowledge, the samples are divided into K classes according to an iteration rule of the algorithm, wherein the classification is classification of gray values of the foreground image and the background image. Before the K-means algorithm is carried out, a target image is read in, the target image is converted into a gray image, two-dimensional data is converted into one-dimensional data of a long strip or a long chain, the clustering of the gray image is a feature, and if the clustering is color image clustering, three channels of rgb are converted into one dimension respectively.
The area technology is edge detection, and an edge refers to a set of pixels with a step change or a roof change in the gray level of surrounding pixels, and a sudden change of information such as the gray level or the structure becomes an edge. Based on the boundary technology, the edge is detected by utilizing the catastrophe property of the image edge, and the edge is detected by calculating the gradient value of the image by using an edge detection operator based on a first derivative.
For the detected object, a threshold segmentation technology is utilized to separate the foreground image into a target image, threshold segmentation firstly determines a certain gray value of each pixel point in the target image within a gray range, the obtained gray value of each pixel in the target image is compared with a preset segmentation threshold value, so that the image is segmented, binarization algorithm processing is carried out, and proper threshold value is selected to reduce illumination influence caused by the environment. Namely, a certain image extracted from the target image segmentation is given a corresponding identity. And classifying by using a decision theory and a structural method according to the gray information (the brightness of the image and the shade degree of the color) of the target image and the contour analysis of the foreground image.
In one embodiment, as shown in fig. 3, before step S122, step S121 is further included: and adjusting the size of the target image according to a preset size, and correcting the position of the target image according to a preset standard coordinate system.
Specifically, after the target image is obtained, the target image needs to be preprocessed, the size of the cut target image is adjusted according to a preset size, and the target image is rotationally corrected according to a preset standard coordinate system, so that subsequent analysis and processing are facilitated.
In one embodiment, as shown in FIG. 4, step S124 is followed by step S126.
Step S126: and smoothing the foreground image according to preset image smoothing data.
Specifically, in the process of detecting a target object, for an optical acquisition device in a complex environment, due to the problems of illumination change, scene and the like, the quality of an image is reduced by the acquired target image information, so that noise points inevitably exist in the extracted foreground image, after the foreground image is extracted, data needs to be smoothed by a preset image, the unnecessary small noise points are removed by using a corrosion algorithm in morphology, in order to better identify the object, the foreground image is extracted by using a morphological flood filling algorithm, the gray value and the brightness of the target image jump, a discontinuous line of a first derivative is represented in a mathematical model, and the edge of the foreground image can be obtained by using a gradient function of the target image.
In one embodiment, as shown in fig. 5, before step S110, step S100 is further included.
Step S100: and establishing a labeling identification template.
Specifically, an optical acquisition device is used for acquiring a target image acquired by a target object, the target image is transmitted to a processor through a visual detection technology and is pushed to be a modeling plate to be displayed on a field billboard computer, a label template, namely a labeling identification template, is established through a man-machine interaction mode and is then pushed to the processor, so that the establishment of the labeling identification template is completed, and the quality detection of subsequent labels is carried out. The specific front end process for establishing the labeling mark comprises the following steps: each standard part corresponds to a material code, if the input material code is not stored in a warehouse, no modeling is performed, the employee inputs the material code, the material code is photographed through a camera and presented at the front end, the material code is determined to be the first part, and modeling is completed.
In one embodiment, as shown in FIG. 6, after step S130, step S140 is included.
Step S140: and outputting corresponding prompt information according to the recognition result.
Specifically, the recognition result comprises normal recognition and abnormal recognition, the specific embodiment form of the prompt information is not limited and can be voice prompt, text prompt and the like, the detection and recognition result can be presented in real time through a machine vision detection and recognition technology and accompanied by sound prompt, the detection and recognition result is stored by using a database and can be presented on a display, the abnormal part is prompted by alarming, the number and the abnormal reason of the abnormal part appearing in a batch of objects are analyzed and predicted through data, and some attention items of workers in the labeling process are pertinently provided so as to reduce the labeling abnormal rate and play a role in preventing from being neglected.
In one embodiment, as shown in fig. 7, after step S120, step S150 is further included.
Step S150: and when the identification information is not extracted from the foreground image, outputting a recognition result.
Specifically, when the identification information is not extracted from the foreground image, it is indicated that no identification exists on the target object, that is, the label is missed, and the identification result is output to prompt the labeler to miss the label.
The above-mentioned identification error-proofing recognition method can be applied to a plurality of aspects, for example: monitoring spare and accessory parts on an industrial production line, detecting product package printing, detecting defects of a printed circuit board and the like. The method is based on modeling standard parts, a panel labeling quality inspection system is developed, the system is provided with an image acquisition system and an integrated image operation analysis storage background, namely a processor, a front-end interface, namely a display device, automatically presents detection results through software program operation, alarms and prompts abnormal parts, and meanwhile detected data are stored in a database, so that subsequent searching and analysis are facilitated. The problem of labeller in the subsides mark in-process, the hourglass that the sign appears pastes, askew subsides etc is solved, on the one hand, can replace the mode of artifical detection, and on the other hand, the post that reduces unusual label spare as far as possible flows, can reduce printed matter sign and paste the defective rate, promotes product quality, improves production efficiency.
It should be understood that although the various steps in the flow charts of fig. 1-7 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-7 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 8, there is provided an identification error-proofing recognition apparatus, which includes a target image acquisition module 110, a foreground image extraction module 120 and a recognition module 130, wherein:
a target image obtaining module 110, configured to obtain a target image acquired by a target object; the foreground image extraction module 120 is configured to analyze the target image and extract a foreground image in the target image; the identification module 130 is configured to, when the identification information is extracted from the foreground image, compare the identification information with a preset labeling identification template to obtain an identification result.
In one embodiment, the foreground image extraction module comprises an image processing unit and an extraction unit, wherein the image processing unit is used for processing the target image to obtain color information and position information of the target image; the extraction unit is used for extracting and obtaining a foreground image in the target image according to the color information and the position information of the target image and a preset segmentation threshold value.
In one embodiment, the image processing unit may be preceded by an adjustment correction unit for adjusting a size of the target image according to a preset size and correcting a position of the target image according to a preset standard coordinate system.
In one embodiment, after the extracting unit, a smoothing unit is further included, and the smoothing unit is configured to smooth the foreground image according to preset image smoothing data.
In one embodiment, the target image acquisition module previously includes a template creation module for creating a qualified label identification template.
In one embodiment, the recognition module comprises a prompt module, and the prompt module is used for outputting corresponding prompt information according to the recognition result.
In another embodiment, the foreground image extraction module comprises a recognition module after the foreground image extraction module, and the recognition module is used for outputting a recognition result when the identification information is not extracted from the foreground image.
Above-mentioned sign mistake proofing recognition device, based on the mark piece of modelling, development panel pastes mark quality testing system, this system possesses image acquisition system, integration image operation analysis storage backstage promptly the treater, through software program operation, front end interface promptly display device will automatic present the testing result to report to the police the suggestion to unusual piece, simultaneously, will save the data that detect in the database, make things convenient for follow-up searching and analyzing. The problem of labeller in the subsides mark in-process, the hourglass that the sign appears pastes, askew subsides etc is solved, on the one hand, can replace the mode of artifical detection, and on the other hand, the post that reduces unusual label spare as far as possible flows, can reduce printed matter sign and paste the defective rate, promotes product quality, improves production efficiency.
For specific limitations of the identification error-proofing recognition device, reference may be made to the above limitations of the identification error-proofing recognition method, which are not described herein again. The modules in the above-mentioned identification error-proofing recognition device can be implemented wholly or partially by software, hardware and their combination. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring a target image acquired from a target object; analyzing and processing the target image, and extracting to obtain a foreground image in the target image; and when the identification information is extracted from the foreground image, comparing and identifying the identification information with a preset labeling identification template to obtain an identification result.
In one embodiment, the step of analyzing the target image and extracting the foreground image in the target image when the computer program is executed by the processor includes: processing the target image to obtain color information and position information of the target image; and extracting to obtain a foreground image in the target image according to the color information and the position information of the target image and a preset segmentation threshold value.
In one embodiment, the computer program, when executed by the processor, further comprises, before the step of processing the target image to obtain color information and position information of the target image: and adjusting the size of the target image according to a preset size, and correcting the position of the target image according to a preset standard coordinate system.
In one embodiment, after the step of obtaining the foreground image in the target image according to the color information, the position information and the preset segmentation threshold of the target image when the computer program is executed by the processor, the method further includes: and smoothing the foreground image according to preset image smoothing data.
In one embodiment, the computer program, when executed by the processor, further comprises, before the step of acquiring a target image of the target object, the step of: and establishing a labeling identification template.
In one embodiment, after the steps of extracting identification information from the foreground image and comparing and recognizing the identification information with a preset labeling identification template to obtain a recognition result when the computer program is executed by the processor, the method further includes: and outputting corresponding prompt information according to the recognition result.
In one embodiment, the computer program, when executed by the processor, further performs analysis processing on the target image, and after the step of extracting the foreground image in the target image, the method further includes: and when the identification information is not extracted from the foreground image, outputting a recognition result.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
In one embodiment, as shown in fig. 9, an identification error-proofing recognition system includes an optical acquisition device 220 and a processor 210, wherein the optical acquisition device 220 is connected to the processor 210, and the optical acquisition device 220 is used for acquiring an image of a target and sending the image to the processor; the processor 210 is configured to acquire a target image acquired from a target object; analyzing and processing the target image, and extracting to obtain a foreground image in the target image; and when the identification information is extracted from the foreground image, comparing and identifying the identification information with a preset labeling identification template to obtain an identification result.
Specifically, in this embodiment, the optical acquisition device is hardware such as an industrial camera, a light source, and a matching image acquisition card, and the processor is an algorithm server.
In one embodiment, as shown in fig. 10, the identification error-proofing recognition system further includes a display device 230, the display device 230 being connected to the processor 210; the processor 210 is configured to send the recognition result to the display device 230; the display device 230 is used for receiving and displaying the recognition result.
Specifically, the display device displays the identification result, so that a labeler can conveniently check whether labeling is abnormal or not in real time, convenience is improved, the reject ratio of labeling printed products is reduced, and production quality is improved.
In one embodiment, the identification error-proofing recognition system further comprises a prompting device 240, the prompting device 240 is connected to the processor, and the processor 210 is configured to send the recognition result to the prompting device 240; the prompting device 240 is configured to output corresponding prompting information according to the received recognition result.
Specifically, the prompt information may be embodied in various forms, such as a voice prompt, an LED light prompt, a buzzer alarm prompt, and the like.
Further, an application scenario and an operation flowchart of the identification error-proofing recognition system, that is, the panel labeling quality inspection system are shown in fig. 11.
For specific limitations of the identification error-proofing recognition system, reference may be made to the above limitations of the identification error-proofing recognition method, which are not described herein again.
Above-mentioned sign mistake proofing identification system, based on the mark piece of modelling, development panel pastes mark quality testing system, this system possesses image acquisition system, integration image operation analysis storage backstage promptly the treater, through software program operation, front end interface promptly display device will automatic present the testing result to report to the police the suggestion to unusual piece, simultaneously, will save the data that detect in the database, make things convenient for follow-up searching and analyzing. The problem of labeller in the subsides mark in-process, the hourglass that the sign appears pastes, askew subsides etc is solved, on the one hand, can replace the mode of artifical detection, and on the other hand, the post that reduces unusual label spare as far as possible flows, can reduce printed matter sign and paste the defective rate, promotes product quality, improves production efficiency.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An identification error-proofing recognition method, the method comprising:
acquiring a target image acquired from a target object;
analyzing and processing the target image, and extracting to obtain a foreground image in the target image;
and when the identification information is extracted from the foreground image, comparing and identifying the identification information with a preset labeling identification template to obtain an identification result.
2. The method according to claim 1, wherein the step of analyzing the target image and extracting a foreground image in the target image comprises:
processing the target image to obtain color information and position information of the target image;
and extracting to obtain a foreground image in the target image according to the color information and the position information of the target image and a preset segmentation threshold value.
3. The method of claim 2, wherein the step of processing the target image to obtain the color information and the position information of the target image is preceded by the step of:
and adjusting the size of the target image according to a preset size, and correcting the position of the target image according to a preset standard coordinate system.
4. The method according to claim 2, wherein after the step of extracting the foreground image of the target image according to the color information and the position information of the target image and a preset segmentation threshold, the method further comprises:
and smoothing the foreground image according to preset image smoothing data.
5. The method of claim 1, wherein the step of obtaining the target image of the target object further comprises:
and establishing a labeling identification template.
6. The method according to claim 1, wherein after the step of comparing and recognizing the identification information with a preset qualified labeling identification template to obtain a recognition result when the identification information is extracted from the foreground image, the method further comprises:
and outputting corresponding prompt information according to the identification result.
7. The method according to claim 1, wherein after the step of analyzing the target image and extracting a foreground image in the target image, the method further comprises:
and when the identification information is not extracted from the foreground image, outputting a recognition result.
8. An identification error-proofing recognition apparatus, the apparatus comprising:
the target image acquisition module is used for acquiring a target image acquired by a target object;
the foreground image extraction module is used for analyzing and processing the target image and extracting a foreground image in the target image;
and the identification module is used for comparing and identifying the identification information with a preset labeling identification template to obtain an identification result when the identification information is extracted from the foreground image.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of any of claims 1 to 7.
10. An identification mistake-proofing recognition system is characterized by comprising an optical acquisition device and a processor, wherein the optical acquisition device is connected with the processor,
the optical acquisition equipment is used for acquiring an image of a target object and sending the image to the processor;
the processor is used for executing the steps of any one of claims 1 to 7 to obtain the identification result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811201575.4A CN111062379A (en) | 2018-10-16 | 2018-10-16 | Identification error-proofing recognition method, device, storage medium and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811201575.4A CN111062379A (en) | 2018-10-16 | 2018-10-16 | Identification error-proofing recognition method, device, storage medium and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111062379A true CN111062379A (en) | 2020-04-24 |
Family
ID=70296300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811201575.4A Pending CN111062379A (en) | 2018-10-16 | 2018-10-16 | Identification error-proofing recognition method, device, storage medium and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111062379A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950538A (en) * | 2020-06-23 | 2020-11-17 | 合肥联宝信息技术有限公司 | Label detection method and device and computer readable storage medium |
| CN116541895A (en) * | 2023-06-20 | 2023-08-04 | 荣耀终端有限公司 | Circuit board detection method, electronic device and chip system |
| CN117392123A (en) * | 2023-12-07 | 2024-01-12 | 广东新亚光电缆股份有限公司 | Wire and cable sign mistake proofing system based on image recognition |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1945600A (en) * | 2006-08-03 | 2007-04-11 | 珠海格力电器股份有限公司 | Label detecting system and its detecting method |
| CN202383719U (en) * | 2011-11-29 | 2012-08-15 | 上海索广映像有限公司 | ELK product label recognition system |
| CN104899572A (en) * | 2015-06-15 | 2015-09-09 | 三星电子（中国）研发中心 | Content-detecting method and device, and terminal |
-
2018
- 2018-10-16 CN CN201811201575.4A patent/CN111062379A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1945600A (en) * | 2006-08-03 | 2007-04-11 | 珠海格力电器股份有限公司 | Label detecting system and its detecting method |
| CN202383719U (en) * | 2011-11-29 | 2012-08-15 | 上海索广映像有限公司 | ELK product label recognition system |
| CN104899572A (en) * | 2015-06-15 | 2015-09-09 | 三星电子（中国）研发中心 | Content-detecting method and device, and terminal |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950538A (en) * | 2020-06-23 | 2020-11-17 | 合肥联宝信息技术有限公司 | Label detection method and device and computer readable storage medium |
| CN111950538B (en) * | 2020-06-23 | 2022-02-08 | 合肥联宝信息技术有限公司 | Label detection method and device and computer readable storage medium |
| CN116541895A (en) * | 2023-06-20 | 2023-08-04 | 荣耀终端有限公司 | Circuit board detection method, electronic device and chip system |
| CN117392123A (en) * | 2023-12-07 | 2024-01-12 | 广东新亚光电缆股份有限公司 | Wire and cable sign mistake proofing system based on image recognition |
| CN117392123B (en) * | 2023-12-07 | 2024-03-08 | 广东新亚光电缆股份有限公司 | Wire and cable sign mistake proofing system based on image recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111161243B (en) | Industrial product surface defect detection method based on sample enhancement | |
| CN111753692B (en) | Target object extraction method, product detection method, device, computer and medium | |
| CN111310645B (en) | Method, device, equipment and storage medium for warning overflow bin of goods accumulation | |
| US9965695B1 (en) | Document image binarization method based on content type separation | |
| CN111062379A (en) | Identification error-proofing recognition method, device, storage medium and system | |
| TW201514472A (en) | Method of optical defect detection through image analysis and data mining integrated | |
| CN111340796B (en) | Defect detection method and device, electronic equipment and storage medium | |
| CN111861990B (en) | Method, system and storage medium for detecting bad appearance of product | |
| US20190012582A1 (en) | Image processing apparatus, image processing method, and non-transitory computer-readable storage medium | |
| CN112037222B (en) | Automatic updating method and system of neural network model | |
| CN103759644A (en) | Separating and refining type intelligent optical filter surface defect detecting method | |
| CN108460344A (en) | Dynamic area intelligent identifying system in screen and intelligent identification Method | |
| CN112464797A (en) | Smoking behavior detection method and device, storage medium and electronic equipment | |
| CN114445707A (en) | Intelligent visual fine detection method for defects of bottled water labels | |
| CN114359235A (en) | Wood surface defect detection method based on improved YOLOv5l network | |
| CN115302963A (en) | Bar code printing control method, system and medium based on machine vision | |
| CN104657721A (en) | Video OSD (on-screen display) time recognition method based on adaptive templates | |
| CN114332058A (en) | Serum quality identification method, device, equipment and medium based on neural network | |
| CN111126112A (en) | Candidate region determination method and device | |
| CN116664540A (en) | Rubber sealing ring surface defect detection method based on Gaussian line detection | |
| CN110718270B (en) | Method, device, equipment and storage medium for detecting type of gene sequencing result | |
| CN107330470B (en) | Method and device for identifying picture | |
| CN112733722A (en) | Gesture recognition method, device and system and computer readable storage medium | |
| CN112164057A (en) | Qualified label detection method, storage medium and electronic equipment | |
| Stommel et al. | Automatic estimation of the legibility of binarised historic documents for unsupervised parameter tuning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |