CN116612266A - Goods identification quality inspection method and system based on AI technology - Google Patents
Goods identification quality inspection method and system based on AI technology Download PDFInfo
- Publication number
- CN116612266A CN116612266A CN202310435251.1A CN202310435251A CN116612266A CN 116612266 A CN116612266 A CN 116612266A CN 202310435251 A CN202310435251 A CN 202310435251A CN 116612266 A CN116612266 A CN 116612266A
- Authority
- CN
- China
- Prior art keywords
- goods
- identification
- result
- image
- identified
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000005516 engineering process Methods 0.000 title claims abstract description 23
- 230000002159 abnormal effect Effects 0.000 claims abstract description 57
- 238000012545 processing Methods 0.000 claims abstract description 37
- 230000011218 segmentation Effects 0.000 claims abstract description 37
- 238000001514 detection method Methods 0.000 claims description 39
- 238000007781 pre-processing Methods 0.000 claims description 16
- 238000013441 quality evaluation Methods 0.000 claims description 14
- 238000012795 verification Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- 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
- G06T2207/30168—Image quality inspection
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The application discloses an article identification quality inspection method and system based on an AI technology, which are applied to the technical field of data processing, and the method comprises the following steps: and acquiring the goods information of the goods to be identified through acquisition, and acquiring control information based on the matching of the goods information. And positioning the goods to be identified through the auxiliary positioning device. And after the positioning is finished, controlling the image acquisition device to acquire the multi-angle image of the goods to be identified through acquisition control information, so as to obtain an identification image set. And constructing the goods area characteristics according to the goods information, and carrying out area identification segmentation of the identification image set based on the goods area characteristics. And carrying out regional image processing based on the regional identification segmentation result, and carrying out processed image feature identification through a preset abnormal identification feature library to obtain a feature identification result. And outputting the goods identification quality inspection result according to the feature identification result. The technical problems of low quality inspection efficiency and low accuracy of quality inspection in the prior art are solved.
Description
Technical Field
The application relates to the field of data processing, in particular to an article identification quality inspection method and system based on an AI technology.
Background
Artificial intelligence is the development of an intelligent machine that can react in an artificially similar manner. However, in the prior art, the quality inspection of the goods is usually performed manually, and the quality inspection of the goods is finished by manually sampling and detecting the goods, and the quality inspection efficiency is low and the accuracy of the quality inspection is low in the manual quality inspection method.
Therefore, in the prior art, the quality inspection of the goods has the technical problems of lower quality inspection efficiency and low accuracy of quality inspection.
Disclosure of Invention
The application provides an article identification quality inspection method and system based on an AI technology, which solve the technical problems of low quality inspection efficiency and low quality inspection accuracy in the prior art.
The application provides an article identification quality inspection method based on an AI technology, which is applied to an article identification quality inspection system, wherein the article identification quality inspection system is in communication connection with an image acquisition device and an auxiliary positioning device, and the method comprises the following steps: acquiring article information of an article to be identified, and acquiring control information based on the article information in a matching way; positioning and identifying positioning points of the goods to be identified through the auxiliary positioning device, and positioning and processing the goods to be identified through the auxiliary positioning device; after positioning is finished, controlling the image acquisition device to acquire the multi-angle image of the goods to be identified through the acquisition control information to obtain an identification image set; constructing an article region feature according to the article information, and performing region identification segmentation of the identification image set based on the article region feature; performing regional image processing based on the regional recognition segmentation result, and performing processed image feature recognition through a preset abnormal recognition feature library to obtain a feature recognition result; and outputting the goods identification quality inspection result according to the characteristic identification result.
The application also provides an article identification quality inspection system based on AI technology, which is in communication connection with the image acquisition device and the auxiliary positioning device, and comprises: the information acquisition module is used for acquiring goods information of goods to be identified and acquiring control information based on the goods information in a matching way; the goods positioning module is used for positioning and identifying the positioning points of the goods to be identified through the auxiliary positioning device and positioning and processing the goods to be identified through the auxiliary positioning device; the image acquisition module is used for controlling the image acquisition device to acquire the multi-angle image of the goods to be identified through the acquisition control information after the positioning is finished, so as to obtain an identification image set; the identification segmentation module is used for constructing goods area characteristics according to the goods information and carrying out area identification segmentation on the identification image set based on the goods area characteristics; the feature recognition module is used for carrying out regional image processing based on the regional recognition segmentation result, carrying out processed image feature recognition through a preset abnormal recognition feature library, and obtaining a feature recognition result; and the quality inspection result acquisition module is used for outputting the goods identification quality inspection result according to the characteristic identification result.
The application also provides an electronic device, comprising:
a memory for storing executable instructions;
and the processor is used for realizing the goods identification quality inspection method based on the AI technology when executing the executable instructions stored in the memory.
The embodiment of the application provides a computer readable storage medium which stores a computer program, and when the program is executed by a processor, the method for identifying and checking the quality of goods based on the AI technology is realized.
The method and the system for identifying and checking the quality of the goods based on the AI technology are aimed to acquire the goods information of the goods to be identified through acquisition, and acquire control information based on matching of the goods information. And positioning the goods to be identified through the auxiliary positioning device. And after the positioning is finished, controlling the image acquisition device to acquire the multi-angle image of the goods to be identified through acquisition control information, so as to obtain an identification image set. And constructing the goods area characteristics according to the goods information, and carrying out area identification segmentation of the identification image set based on the goods area characteristics. And carrying out regional image processing based on the regional identification segmentation result, and carrying out processed image feature identification through a preset abnormal identification feature library to obtain a feature identification result. And outputting the quality inspection result of the goods identification according to the characteristic identification result, thereby realizing the technical effects of improving the efficiency and the detection accuracy of the quality inspection of the goods. The technical problems of low quality inspection efficiency and low accuracy of quality inspection in the prior art are solved.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly described below. It is apparent that the figures in the following description relate only to some embodiments of the present disclosure and are not limiting of the present disclosure.
Fig. 1 is a schematic flow chart of an article identification quality inspection method based on AI technology according to an embodiment of the present application;
fig. 2 is a schematic flow chart of area image processing according to an AI technology-based method for identifying and inspecting goods according to an embodiment of the present application;
fig. 3 is a schematic flow chart of quality detection optimization constructed by an article identification quality detection method based on AI technology according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a system of an article identification quality inspection method based on AI technology according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a system electronic device of an article identification quality inspection method based on AI technology according to an embodiment of the present application.
Reference numerals illustrate: the system comprises an information acquisition module 11, a goods positioning module 12, an image acquisition module 13, an identification segmentation module 14, a characteristic identification module 15, a quality inspection result acquisition module 16, a processor 31, a memory 32, an input device 33 and an output device 34.
Detailed Description
Example 1
The present application will be further described in detail with reference to the accompanying drawings, for the purpose of making the objects, technical solutions and advantages of the present application more apparent, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.
In the following description, the terms "first", "second", "third" and the like are merely used to distinguish similar objects and do not represent a particular ordering of the objects, it being understood that the "first", "second", "third" may be interchanged with a particular order or sequence, as permitted, to enable embodiments of the application described herein to be practiced otherwise than as illustrated or described herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the application only.
While the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server, the modules are merely illustrative, and different aspects of the system and method may use different modules.
A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
As shown in fig. 1, an embodiment of the present application provides an article identification quality inspection method based on AI technology, where the method is applied to an article identification quality inspection system, and the article identification quality inspection system is communicatively connected with an image acquisition device and an auxiliary positioning device, and the method includes:
s10: acquiring article information of an article to be identified, and acquiring control information based on the article information in a matching way;
s20: positioning and identifying positioning points of the goods to be identified through the auxiliary positioning device, and positioning and processing the goods to be identified through the auxiliary positioning device;
s30: after positioning is finished, controlling the image acquisition device to acquire the multi-angle image of the goods to be identified through the acquisition control information to obtain an identification image set;
specifically, the method comprises the steps of acquiring the goods information of the goods to be identified, wherein the goods information comprises the types of the goods, and acquiring control information based on the matching of the goods information, wherein the acquiring control information comprises specific acquiring positions and acquiring angles of the goods. And then, positioning and identifying the positioning point of the goods to be identified through an auxiliary positioning device, positioning and processing the goods to be identified through the auxiliary positioning device, and determining the positioning position of the goods to be identified. After the positioning of the goods to be identified is completed, the image acquisition device is controlled to acquire multi-angle images of the goods to be identified through acquisition control information, and an identification image set is obtained.
S40: constructing an article region feature according to the article information, and performing region identification segmentation of the identification image set based on the article region feature;
s50: performing regional image processing based on the regional recognition segmentation result, and performing processed image feature recognition through a preset abnormal recognition feature library to obtain a feature recognition result;
s60: and outputting the goods identification quality inspection result according to the characteristic identification result.
Specifically, the method comprises the steps of constructing the characteristic of the article area according to the article information, carrying out area identification segmentation on the identification image set based on the characteristic of the article area, namely carrying out identification and segmentation on the demand area, namely the characteristic of the article area, of the acquired identification image set according to the characteristic of the article area, and removing the part of the identification image set, which is not the demand area. And then, carrying out regional image processing based on a regional recognition segmentation result, carrying out processed image feature recognition through a preset abnormal recognition feature library, and carrying out feature recognition by adopting a feature recognition matching method commonly used in the prior art when carrying out feature recognition to obtain a feature recognition result. And finally, outputting an article identification quality inspection result according to the obtained characteristic identification result to finish the identification quality inspection of the article, wherein the article identification quality inspection result contains specific abnormal characteristics and characteristic quantity. The technical effects of improving the efficiency of the commodity quality detection and the detection accuracy are achieved.
As shown in fig. 2, the method S40 provided by the embodiment of the present application further includes:
s41: acquiring a real area of each acquisition angle of the goods to be identified according to the acquisition control information;
s42: carrying out regional goods characteristic extraction on the real region according to the goods information;
s43: obtaining regional abnormal characteristic frequency of each region according to the preset abnormal identification characteristic library, and generating characteristic association coefficients according to the regional abnormal characteristic frequency;
s44: inputting the preset abnormality identification feature library, the feature association coefficient and the goods feature into an image preprocessing parameter setting model, and outputting preprocessing control data;
s45: and carrying out region image processing on the region identification and segmentation result based on the preprocessing control data and the real region.
Specifically, the real area of each acquisition angle of the goods to be identified is obtained according to the acquisition control information, wherein the real area is a real image of the goods acquired by the acquisition control information. And then carrying out regional goods characteristic extraction according to the real areas of the goods information, when carrying out regional goods characteristic extraction, predicting the goods characteristic extraction for carrying out regional division on the real areas to carry out regional division on the unnecessary image areas, and then completing the extraction of the segmented goods characteristic images because the acquired real images possibly contain parts which are not needed for abnormal characteristic identification. Further, the regional abnormal characteristic frequency of each region is obtained according to a preset abnormal identification characteristic library, and a characteristic association coefficient is generated according to the regional abnormal characteristic frequency. The preset abnormal recognition feature library comprises abnormal features of each article, corresponding abnormal feature values and frequencies of occurrence of the abnormal features, and is updated according to a certain preset period. Inputting the preset abnormal recognition feature library, the feature association coefficient and the goods feature into an image preprocessing parameter setting model, and outputting preprocessing control data. The preprocessing control data comprises specific processing control data, such as resolution of processed images, enlargement and reduction of processed images and the like, so as to ensure uniformity of image specifications and meet corresponding recognition precision requirements when subsequent processing steps are carried out. The image preprocessing parameter setting model takes a preset abnormal recognition feature library, a historical feature association coefficient and historical goods features as training data, takes preprocessing control data as supervision data to be input into the neural network model for supervision training, and finishes training the model when a model output result is obtained and meets a certain preset accuracy, so that the image preprocessing parameter setting model is obtained. And finally, carrying out region image processing on the region identification and segmentation result based on the preprocessing control data and the real region, and completing the image processing on the region identification and segmentation result.
The method S43 provided by the embodiment of the application further comprises the following steps:
s431: obtaining regional abnormal characteristic values of all regions according to the preset abnormal identification characteristic library;
s432: and calculating and obtaining the characteristic association coefficient based on the regional abnormal characteristic value and the regional abnormal characteristic frequency.
Specifically, the regional abnormal characteristic values of each region are obtained according to a preset abnormal identification characteristic library, wherein the abnormal characteristic values are the importance level values of the abnormality, and the higher the importance level values of the abnormality are, the higher the corresponding abnormal characteristic values are. And calculating and obtaining the characteristic association coefficient based on the product of the regional abnormal characteristic value and the regional abnormal characteristic frequency, wherein the higher the characteristic association coefficient is, the higher the corresponding regional abnormal characteristic value and/or regional abnormal characteristic frequency is.
The method S43 provided by the embodiment of the application further comprises the following steps:
s433: acquiring the goods identification requirement information of the goods to be identified;
s434: carrying out demand analysis on the goods identification demand information to obtain the area identification precision of each goods area;
s435: matching a region segmentation grid based on the region identification accuracy;
s436: and carrying out grid division on the region image processing result through a corresponding region division grid, and obtaining the feature recognition result through the grid division result.
Specifically, the method includes the steps of collecting and acquiring the article identification requirement information of the article to be identified, wherein the article identification requirement information comprises identification precision requirements and identification requirements in other aspects. And then, carrying out demand analysis on the goods identification demand information to obtain the area identification precision of each goods area. Further, based on the region recognition accuracy, region segmentation grids are matched, wherein the higher the region recognition accuracy is, the more corresponding segmentation grids are, and the finer the extraction of the region features of the image is. And finally, carrying out grid division on the region image processing result through corresponding region division grids, dividing the region image processing result into a plurality of grids, and obtaining the feature recognition result through the grid division result.
The method S43 provided by the embodiment of the application further comprises the following steps:
s437: generating traversal control data through the characteristic association coefficients;
s438: controlling the preset abnormal recognition feature library to carry out grid-by-grid feature traversal on the area image processing result after grid division through the traversal control data;
s439: and obtaining the feature recognition result based on the traversing result.
Specifically, the traversal control data are generated through the feature association coefficients, wherein the feature association coefficients and the traversal control data have preset corresponding relations, the traversal control data represent specific traversal times, the higher the feature association coefficients are, the more corresponding traversal control data are, and therefore the traversal accuracy of the feature association coefficients is improved. And controlling the preset abnormal recognition feature library to carry out grid-by-grid feature traversal on the area image processing result after grid division through the traversal control data, traversing and matching whether features in the recognition grid are consistent with abnormal features in the preset abnormal recognition feature library, and finally obtaining the feature recognition result based on the traversal recognition result to further finish recognition of the features in the image.
As shown in fig. 3, the method S60 provided by the embodiment of the present application further includes:
s70: setting sample sampling data;
s71: performing quality detection on the goods to be identified through the sample spot check data to obtain a quality verification detection result;
s72: comparing the quality deviation of the goods identification quality inspection result through the quality verification detection result to obtain a comparison result;
s73: and generating feedback quality inspection data through the comparison result, and carrying out quality detection optimization on the goods to be identified based on the feedback quality inspection data.
Specifically, sample sampling data is set, wherein the sample sampling data is the data of a known sample. And carrying out quality detection on the goods to be identified through sample spot check data to obtain a quality verification detection result, wherein the quality verification detection result is standard detection data of samples detected through other quality detection modes. And comparing the quality deviation of the goods identification quality inspection result through the quality verification detection result to obtain a comparison result, and comparing whether the detected abnormal quantity is consistent or not. The goods identification quality inspection result is a detection result obtained through the detection mode provided by the embodiment. And if the obtained comparison result is larger or smaller than the standard detection data, the accuracy of the quality detection method of the goods is lower, feedback quality detection data are generated according to the actual deviation, and the accuracy adjustment of the feedback quality detection data is more accurate when the deviation is larger, so that the optimization of the quality detection method of the goods is completed by adjusting the detection accuracy of the quality detection method of the goods. Therefore, the quality detection of the goods to be identified is adjusted according to the comparison result, and the detection result of the quality detection method of the goods to be identified is more accurate.
The method S60 provided by the embodiment of the application further comprises the following steps:
s74: setting an image acquisition quality constraint threshold;
s75: performing image quality evaluation on the identification image set to obtain an image quality evaluation result;
s76: and when the image quality evaluation result cannot meet the image acquisition quality constraint threshold, carrying out image acquisition of the goods to be identified again.
Specifically, an image acquisition quality constraint threshold is set, and the image acquisition quality constraint threshold is used for constraining the image definition of an acquired image. And performing image quality evaluation on the identification image set to obtain an image quality evaluation result, wherein a specific evaluation mode can be performed by an image quality evaluation method in the prior art to obtain the image quality evaluation result. And when the image quality evaluation result cannot meet the image acquisition quality constraint threshold, re-acquiring the image of the goods to be identified, thereby ensuring that the actually acquired image is clearer and ensuring the detection quality of the quality detection method.
According to the technical scheme provided by the embodiment of the application, the goods information of the goods to be identified is acquired through collection, and the control information is acquired based on the matching of the goods information. And positioning the goods to be identified through the auxiliary positioning device. And after the positioning is finished, controlling the image acquisition device to acquire the multi-angle image of the goods to be identified through acquisition control information, so as to obtain an identification image set. And constructing the goods area characteristics according to the goods information, and carrying out area identification segmentation of the identification image set based on the goods area characteristics. And carrying out regional image processing based on the regional identification segmentation result, and carrying out processed image feature identification through a preset abnormal identification feature library to obtain a feature identification result. And outputting the goods identification quality inspection result according to the feature identification result. The technical problems of low quality inspection efficiency and low accuracy of quality inspection in the prior art are solved. The technical effects of improving the efficiency of the commodity quality detection and the detection accuracy are achieved.
Example two
Based on the same inventive concept as the method for identifying and checking goods based on the AI technology in the foregoing embodiments, the present application also provides a system for identifying and checking goods based on the AI technology, which can be implemented by hardware and/or software, and can be generally integrated in an electronic device, for executing the method provided by any embodiment of the present application. As shown in fig. 4, the system is communicatively connected with the image acquisition device and the auxiliary positioning device, and the system includes:
the information acquisition module 11 is used for acquiring goods information of goods to be identified and acquiring control information based on the matching of the goods information;
the goods positioning module 12 is configured to perform positioning and identification on a positioning point of the goods to be identified by using the auxiliary positioning device, and perform positioning and processing on the goods to be identified by using the auxiliary positioning device;
the image acquisition module 13 is used for controlling the image acquisition device to acquire the multi-angle image of the goods to be identified through the acquisition control information after the positioning is completed, so as to obtain an identification image set;
the identifying and dividing module 14 is configured to construct an article region feature according to the article information, and perform region identifying and dividing on the identifying image set based on the article region feature;
the feature recognition module 15 is configured to perform region image processing based on the region recognition segmentation result, and perform processed image feature recognition through a preset abnormal recognition feature library to obtain a feature recognition result;
and the quality inspection result acquisition module 16 is used for outputting the goods identification quality inspection result according to the characteristic identification result.
Further, the identification and segmentation module 14 is further configured to:
acquiring a real area of each acquisition angle of the goods to be identified according to the acquisition control information;
carrying out regional goods characteristic extraction on the real region according to the goods information;
obtaining regional abnormal characteristic frequency of each region according to the preset abnormal identification characteristic library, and generating characteristic association coefficients according to the regional abnormal characteristic frequency;
inputting the preset abnormality identification feature library, the feature association coefficient and the goods feature into an image preprocessing parameter setting model, and outputting preprocessing control data;
and carrying out region image processing on the region identification and segmentation result based on the preprocessing control data and the real region.
Further, the identification and segmentation module 14 is further configured to:
obtaining regional abnormal characteristic values of all regions according to the preset abnormal identification characteristic library;
and calculating and obtaining the characteristic association coefficient based on the regional abnormal characteristic value and the regional abnormal characteristic frequency.
Further, the identification and segmentation module 14 is further configured to:
acquiring the goods identification requirement information of the goods to be identified;
carrying out demand analysis on the goods identification demand information to obtain the area identification precision of each goods area;
matching a region segmentation grid based on the region identification accuracy;
and carrying out grid division on the region image processing result through a corresponding region division grid, and obtaining the feature recognition result through the grid division result.
Further, the identification and segmentation module 14 is further configured to:
generating traversal control data through the characteristic association coefficients;
controlling the preset abnormal recognition feature library to carry out grid-by-grid feature traversal on the area image processing result after grid division through the traversal control data;
and obtaining the feature recognition result based on the traversing result.
Further, the quality inspection result obtaining module 16 is further configured to:
setting sample sampling data;
performing quality detection on the goods to be identified through the sample spot check data to obtain a quality verification detection result;
comparing the quality deviation of the goods identification quality inspection result through the quality verification detection result to obtain a comparison result;
and generating feedback quality inspection data through the comparison result, and carrying out quality detection optimization on the goods to be identified based on the feedback quality inspection data.
Further, the quality inspection result obtaining module 16 is further configured to:
setting an image acquisition quality constraint threshold;
performing image quality evaluation on the identification image set to obtain an image quality evaluation result;
and when the image quality evaluation result cannot meet the image acquisition quality constraint threshold, carrying out image acquisition of the goods to be identified again.
The included units and modules are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be realized; 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 application.
Example III
Fig. 5 is a schematic structural diagram of an electronic device provided in a third embodiment of the present application, and shows a block diagram of an exemplary electronic device suitable for implementing an embodiment of the present application. The electronic device shown in fig. 5 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present application. As shown in fig. 5, the electronic device includes a processor 31, a memory 32, an input device 33, and an output device 34; the number of processors 31 in the electronic device may be one or more, in fig. 5, one processor 31 is taken as an example, and the processors 31, the memory 32, the input device 33 and the output device 34 in the electronic device may be connected by a bus or other means, in fig. 5, by bus connection is taken as an example.
The memory 32 is used as a computer readable storage medium for storing software programs, computer executable programs and modules, such as program instructions/modules corresponding to an AI-technology-based method for identifying and checking goods in an embodiment of the present application. The processor 31 executes various functional applications of the computer device and data processing by running software programs, instructions and modules stored in the memory 32, i.e., implements an article identification quality inspection method based on AI technology as described above.
Note that the above is only a preferred embodiment of the present application and the technical principle applied. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, while the application has been described in connection with the above embodiments, the application is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the application, which is set forth in the following claims.
Claims (10)
1. The utility model provides an article discernment quality inspection method based on AI technique, its characterized in that, the method is applied to article discernment quality inspection system, article discernment quality inspection system and image acquisition device, auxiliary positioning device communication connection, the method includes:
acquiring article information of an article to be identified, and acquiring control information based on the article information in a matching way;
positioning and identifying positioning points of the goods to be identified through the auxiliary positioning device, and positioning and processing the goods to be identified through the auxiliary positioning device;
after positioning is finished, controlling the image acquisition device to acquire the multi-angle image of the goods to be identified through the acquisition control information to obtain an identification image set;
constructing an article region feature according to the article information, and performing region identification segmentation of the identification image set based on the article region feature;
performing regional image processing based on the regional recognition segmentation result, and performing processed image feature recognition through a preset abnormal recognition feature library to obtain a feature recognition result;
and outputting the goods identification quality inspection result according to the characteristic identification result.
2. The method of claim 1, wherein the method comprises:
acquiring a real area of each acquisition angle of the goods to be identified according to the acquisition control information;
carrying out regional goods characteristic extraction on the real region according to the goods information;
obtaining regional abnormal characteristic frequency of each region according to the preset abnormal identification characteristic library, and generating characteristic association coefficients according to the regional abnormal characteristic frequency;
inputting the preset abnormality identification feature library, the feature association coefficient and the goods feature into an image preprocessing parameter setting model, and outputting preprocessing control data;
and carrying out region image processing on the region identification and segmentation result based on the preprocessing control data and the real region.
3. The method according to claim 2, wherein the method comprises:
obtaining regional abnormal characteristic values of all regions according to the preset abnormal identification characteristic library;
and calculating and obtaining the characteristic association coefficient based on the regional abnormal characteristic value and the regional abnormal characteristic frequency.
4. A method according to claim 3, wherein the method comprises:
acquiring the goods identification requirement information of the goods to be identified;
carrying out demand analysis on the goods identification demand information to obtain the area identification precision of each goods area;
matching a region segmentation grid based on the region identification accuracy;
and carrying out grid division on the region image processing result through a corresponding region division grid, and obtaining the feature recognition result through the grid division result.
5. The method of claim 4, wherein the method comprises:
generating traversal control data through the characteristic association coefficients;
controlling the preset abnormal recognition feature library to carry out grid-by-grid feature traversal on the area image processing result after grid division through the traversal control data;
and obtaining the feature recognition result based on the traversing result.
6. The method of claim 1, wherein the method comprises:
setting sample sampling data;
performing quality detection on the goods to be identified through the sample spot check data to obtain a quality verification detection result;
comparing the quality deviation of the goods identification quality inspection result through the quality verification detection result to obtain a comparison result;
and generating feedback quality inspection data through the comparison result, and carrying out quality detection optimization on the goods to be identified based on the feedback quality inspection data.
7. The method of claim 1, wherein the method comprises:
setting an image acquisition quality constraint threshold;
performing image quality evaluation on the identification image set to obtain an image quality evaluation result;
and when the image quality evaluation result cannot meet the image acquisition quality constraint threshold, carrying out image acquisition of the goods to be identified again.
8. An article identification quality inspection system based on AI technology, characterized in that the system is in communication connection with an image acquisition device and an auxiliary positioning device, and the system comprises:
the information acquisition module is used for acquiring goods information of goods to be identified and acquiring control information based on the goods information in a matching way;
the goods positioning module is used for positioning and identifying the positioning points of the goods to be identified through the auxiliary positioning device and positioning and processing the goods to be identified through the auxiliary positioning device;
the image acquisition module is used for controlling the image acquisition device to acquire the multi-angle image of the goods to be identified through the acquisition control information after the positioning is finished, so as to obtain an identification image set;
the identification segmentation module is used for constructing goods area characteristics according to the goods information and carrying out area identification segmentation on the identification image set based on the goods area characteristics;
the feature recognition module is used for carrying out regional image processing based on the regional recognition segmentation result, carrying out processed image feature recognition through a preset abnormal recognition feature library, and obtaining a feature recognition result;
and the quality inspection result acquisition module is used for outputting the goods identification quality inspection result according to the characteristic identification result.
9. An electronic device, the electronic device comprising:
a memory for storing executable instructions;
a processor for implementing an AI technology-based item identification quality inspection method as set forth in any one of claims 1 to 7 when executing executable instructions stored in the memory.
10. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements an AI-technology based item identification quality inspection method as claimed in any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310435251.1A CN116612266A (en) | 2023-04-21 | 2023-04-21 | Goods identification quality inspection method and system based on AI technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310435251.1A CN116612266A (en) | 2023-04-21 | 2023-04-21 | Goods identification quality inspection method and system based on AI technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116612266A true CN116612266A (en) | 2023-08-18 |
Family
ID=87682644
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310435251.1A Pending CN116612266A (en) | 2023-04-21 | 2023-04-21 | Goods identification quality inspection method and system based on AI technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116612266A (en) |
-
2023
- 2023-04-21 CN CN202310435251.1A patent/CN116612266A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112383891B (en) | Equipment registration method and device based on object model automatic matching | |
| CN105930257B (en) | A kind of method and device of determining target detection use-case | |
| CN114706358B (en) | Method and system for processing welding process information of straight welded pipe | |
| CN111027343A (en) | Bar code area positioning method and device | |
| CN113222057A (en) | Data prediction model training method, data prediction device, data prediction equipment and data prediction medium | |
| CN109242165A (en) | A kind of model training and prediction technique and device based on model training | |
| CN117029968A (en) | Traffic data diagnosis method, system, storage medium and electronic equipment | |
| CN111738348A (en) | Power data anomaly detection method and device | |
| CN113723467A (en) | Sample collection method, device and equipment for defect detection | |
| CN110287114B (en) | Method and device for testing performance of database script | |
| CN116883184A (en) | Financial tax intelligent analysis method based on big data | |
| CN117056722A (en) | Prediction method and system for population quantity of planned land parcel | |
| CN116612266A (en) | Goods identification quality inspection method and system based on AI technology | |
| CN106651803A (en) | House type data identification method and device | |
| CN116956189A (en) | Current abnormality detection system, method, electronic equipment and medium | |
| CN116485552A (en) | Fund investment wind control method, device, medium and terminal | |
| CN115344495A (en) | Data analysis method and device for batch task test, computer equipment and medium | |
| CN115577424A (en) | Method, device, equipment and storage medium for calculating construction engineering quantity | |
| CN115565115A (en) | Outfitting intelligent identification method and computer equipment | |
| CN113779391A (en) | Intelligent lock unlocking recommendation method, system and device based on modeling and storage medium | |
| CN114493234A (en) | Method for identifying key pressure control points of water supply pipe network | |
| CN110458383B (en) | Method and device for realizing demand processing servitization, computer equipment and storage medium | |
| EP3861420A1 (en) | Computer vision systems and methods for identifying anomalies in building models | |
| CN113724881B (en) | Meta analysis automatic data preprocessing and parameter setting software and application thereof | |
| CN114580982B (en) | Method, device and equipment for evaluating data quality of industrial equipment |
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 |