CN113256570A - Visual information processing method, device, equipment and medium based on artificial intelligence - Google Patents
Visual information processing method, device, equipment and medium based on artificial intelligence Download PDFInfo
- Publication number
- CN113256570A CN113256570A CN202110507672.1A CN202110507672A CN113256570A CN 113256570 A CN113256570 A CN 113256570A CN 202110507672 A CN202110507672 A CN 202110507672A CN 113256570 A CN113256570 A CN 113256570A
- Authority
- CN
- China
- Prior art keywords
- image
- frame
- frame image
- determining
- images
- 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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 47
- 230000000007 visual effect Effects 0.000 title claims abstract description 47
- 230000010365 information processing Effects 0.000 title claims abstract description 45
- 238000003672 processing method Methods 0.000 title claims abstract description 30
- 239000013598 vector Substances 0.000 claims abstract description 35
- 230000002159 abnormal effect Effects 0.000 claims abstract description 32
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 238000003860 storage Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims description 21
- 238000012986 modification Methods 0.000 claims description 5
- 230000004048 modification Effects 0.000 claims description 5
- 238000001514 detection method Methods 0.000 abstract description 44
- 230000000694 effects Effects 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 10
- 238000003708 edge detection Methods 0.000 description 7
- 230000007547 defect Effects 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
Abstract
The invention is suitable for the technical field of machine vision detection, and provides a visual information processing method, a system, a device and a storage medium based on artificial intelligence, wherein the method comprises the following steps: acquiring an original video; preprocessing the original video to obtain a multi-frame gray image; determining at least one reference frame image meeting preset conditions; comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information; and carrying out classification and identification on the description vectors according to a pre-trained classification and identification model to obtain the class attribute of the gray level image. The visual information processing method based on artificial intelligence provided by the embodiment of the invention can effectively identify the appearance quality of a target product, and can effectively solve the problems of low detection efficiency and poor effect caused by that the appearance quality detection of products in the current automation industry is mainly manual detection and contact detection.
Description
Technical Field
The invention belongs to the technical field of machine vision detection, and particularly relates to a visual information processing method and device based on artificial intelligence, computer equipment and a storage medium.
Background
In recent years, artificial intelligence has been rapidly developed, and machine vision is one of them. Pedestrian detection is an important problem in machine vision, and is widely applied to the fields of security monitoring, intelligent driving, intelligent robots and the like. At present, a method based on machine learning is the mainstream of a pedestrian detection algorithm, and the method is mainly realized by combining artificial features and a classifier.
Machine vision can improve the flexibility and degree of automation of production. In some dangerous working environments which are not suitable for manual operation or occasions where manual vision is difficult to meet the requirements, machine vision is often used to replace the manual vision. The main functions of machine vision are four, namely guiding and positioning, appearance detection, high-precision monitoring and identification. The guiding and positioning can be applied to three-dimensional and two-dimensional conditions, static and dynamic targets of a positioning production line can be positioned, and the visual positioning requirements under different conditions can be met.
With the development of the automation industry, the quality requirement on the product is higher and higher, so that the appearance quality detection of the product is more and more important; at present, the appearance quality detection of products in the automation industry is mainly based on manual detection and contact detection, and the two detection modes have defects respectively; the human eyes are easy to fatigue and easy to misjudge and miss judge when the human eyes work under a high light source for a long time through manual detection; moreover, the subjective judgment standards are different due to different recognition degrees and understanding degrees of each person on the standards; the detection workload is large, the repeatability is high, and the damage to human eyes is serious; the contact detection is mainly measured by instruments such as a measuring instrument joint arm, a three-coordinate instrument and the like, firstly, the instruments cannot accurately measure products with irregular anisotropy, and secondly, the contact measurement mode is point-by-point measurement, and the measurement speed is low.
Disclosure of Invention
The embodiment of the invention aims to provide a visual information processing method and device based on artificial intelligence, computer equipment and a storage medium, and aims to solve the problems that the appearance quality detection of products in the current automation industry is mainly manual detection and contact detection, and the detection efficiency is low and the effect is poor. The embodiment of the invention is realized as follows:
in one embodiment of the present invention, there is provided an artificial intelligence based visual information processing method, including the steps of:
acquiring an original video;
preprocessing the original video to obtain a multi-frame gray image;
determining at least one reference frame image meeting preset conditions;
comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information;
and carrying out classification and identification on the description vectors according to a pre-trained classification and identification model to obtain the class attribute of the gray level image.
As a further limitation of the technical solution of the preferred embodiment of the present invention, the step of preprocessing the original video specifically includes:
extracting a frame image set of the original video, and determining a product image of each frame image;
and carrying out gray level processing on a plurality of frame images containing preset images in the frame image set.
As a further limitation of the technical solution of the preferred embodiment of the present invention, the step of determining the product image of each frame of image specifically includes:
determining edge pixel points of a target product in the frame image according to the gray value of each pixel point in the frame image;
determining the edge of the target product in the frame image according to the edge pixel points of the target product in the frame image;
and determining a product image of the current frame image according to the edge of the target product.
As a further limitation of the technical solution of the preferred embodiment of the present invention, after the step of performing classification and identification on the description vector according to the pre-trained classification and identification model, the method further includes: and modifying and optimizing the classification recognition model according to the classification recognition result.
In another embodiment of the present invention, there is provided an artificial intelligence based visual information processing apparatus including:
the video shooting unit is used for acquiring an original video;
the video processing unit is used for preprocessing the original video to obtain a multi-frame gray image;
the frame image determining unit is used for determining at least one frame of reference frame image meeting preset conditions;
the image comparison unit is used for comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information;
and the type identification unit is used for carrying out classification identification on the description vector according to a pre-trained classification identification model to obtain the class attribute of the gray level image.
As a further limitation of the technical solution of the preferred embodiment of the present invention, the video processing unit includes:
the product image acquisition module is used for extracting the frame image set of the original video and determining a product image of each frame image;
and the image processing module is used for carrying out gray processing on a plurality of frame images which contain preset images in the frame image set.
As a further limitation of the technical solution of the preferred embodiment of the present invention, the product image acquisition module specifically includes:
the edge pixel point determining submodule is used for determining edge pixel points of a target product in the frame image according to the gray value of each pixel point in the frame image;
the product edge determining submodule is used for determining the edge of the target product in the frame image according to the edge pixel points of the target product in the frame image;
and the product image determining submodule is used for determining the product image of the current frame image according to the edge of the target product.
As a further limitation of the technical solution of the preferred embodiment of the present invention, the apparatus further comprises:
and the model modification module is used for modifying and optimizing the classification recognition model according to the classification recognition result.
In another embodiment of the present invention, a computer device is provided, which includes a memory and a processor, wherein the memory stores computer readable instructions, and the processor implements the steps of the artificial intelligence based visual information processing method when executing the computer readable instructions:
acquiring an original video;
preprocessing the original video to obtain a multi-frame gray image;
determining at least one reference frame image meeting preset conditions;
comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information;
and carrying out classification and identification on the description vectors according to a pre-trained classification and identification model to obtain the class attribute of the gray level image.
In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions: the computer readable storage medium stores computer readable instructions, and the computer readable instructions, when executed by the processor, implement the steps of the artificial intelligence based visual information processing method described above:
acquiring an original video;
preprocessing the original video to obtain a multi-frame gray image;
determining at least one reference frame image meeting preset conditions;
comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information;
and carrying out classification and identification on the description vectors according to a pre-trained classification and identification model to obtain the class attribute of the gray level image.
Compared with the prior art, the embodiment of the invention mainly has the following beneficial effects: the visual information processing method based on artificial intelligence provided by the embodiment of the invention obtains an original video; preprocessing the original video to obtain a multi-frame gray image; determining at least one reference frame image meeting preset conditions; comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information; and carrying out classification and identification on the description vectors according to a pre-trained classification and identification model to obtain the class attribute of the gray level image. The embodiment of the invention can detect the appearance of the target product in the original video, classify the appearance defects of the target product according to the detection result, and effectively solve the problems of low detection efficiency and poor effect caused by the fact that the detection of the appearance quality of the product in the automatic industry is mainly manual detection and contact detection at present.
Drawings
Fig. 1 is a system architecture diagram of a visual information processing method based on artificial intelligence according to an embodiment of the present invention;
FIG. 2 is a flowchart of an implementation of a visual information processing method based on artificial intelligence according to an embodiment of the present invention;
FIG. 3 is a sub-flowchart of a method for processing visual information based on artificial intelligence according to an embodiment of the present invention;
FIG. 4 is another sub-flowchart of a method for artificial intelligence based visual information processing according to an embodiment of the present invention;
FIG. 5 is a block diagram of an artificial intelligence based visual information processing apparatus according to an embodiment of the present invention;
FIG. 6 is a block diagram of a video processing unit in an artificial intelligence based visual information processing apparatus according to an embodiment of the present invention;
FIG. 7 is a block diagram of a product image capture module in an artificial intelligence based visual information processing apparatus according to an embodiment of the present invention;
fig. 8 is a block diagram of a computer device for an artificial intelligence based visual information processing method according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
At present, with the development of the automation industry, the quality requirement on products is higher and higher, so that the appearance quality detection of the products is more and more important; at present, the appearance quality detection of products in the automation industry is mainly based on manual detection and contact detection, and the two detection modes have defects respectively; the human eyes are easy to fatigue and easy to misjudge and miss judge when the human eyes work under a high light source for a long time through manual detection; moreover, the subjective judgment standards are different due to different recognition degrees and understanding degrees of each person on the standards; the detection workload is large, the repeatability is high, and the damage to human eyes is serious; the contact detection is mainly measured by instruments such as a measuring instrument joint arm, a three-coordinate instrument and the like, firstly, the instruments cannot accurately measure products with irregular anisotropy, and secondly, the contact measurement mode is point-by-point measurement, and the measurement speed is low.
In order to solve the above problems, the visual information processing method based on artificial intelligence provided by the embodiment of the present invention obtains an original video; preprocessing the original video to obtain a multi-frame gray image; determining at least one reference frame image meeting preset conditions; comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information; and carrying out classification and identification on the description vectors according to a pre-trained classification and identification model to obtain the class attribute of the gray level image. The embodiment of the invention can detect the appearance of the target product in the original video, classify the appearance defects of the target product according to the detection result, and effectively solve the problems of low detection efficiency and poor effect caused by the fact that the detection of the appearance quality of the product in the automatic industry is mainly manual detection and contact detection at present.
The following describes a specific implementation of the artificial intelligence based visual information processing method according to the embodiment of the present invention in detail with reference to specific embodiments.
In a typical configuration of the present application, the terminal, the device serving the network, and the computing device include one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data.
Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory computer readable media (transient media), such as modulated data signals and carrier waves.
Fig. 1 is a system architecture diagram of a visual information processing method based on artificial intelligence according to an embodiment of the present invention;
in the embodiment of the present invention, a visual information processing method based on artificial intelligence is performed in a system, wherein, as shown in fig. 1, the system 100 includes a camera module 101, a control module 102, and a computing module 103 connected to the control module 10 through a high-speed data bus, and the camera module 101 includes one or more cameras for capturing original videos containing target products.
Specifically, as shown in fig. 2, fig. 2 is a flowchart illustrating an implementation of a visual information processing method based on artificial intelligence according to an embodiment of the present invention;
in one example of the present invention, the method 200 comprises the following steps:
step S201: acquiring an original video;
it can be understood that, in the step of acquiring the original video provided by the preferred embodiment of the present invention, the camera module 101 is used to take a picture of the target area, where the target area contains the target product; the method comprises the following steps that a plurality of cameras can be used for shooting different angles of a target product to obtain an original video with richer content information;
step S202: preprocessing the original video to obtain a multi-frame gray image;
specifically, in the specific implementation of step S202 provided by the present invention, first, a frame image set of the original video is extracted, and a product image of each frame image is determined; and carrying out gray level processing on a plurality of frame images containing preset images in the frame image set.
In the determining of the product image of each frame of image, an image color difference mode or an edge detection mode can be adopted, and preferably, the product image of each frame of image is determined by adopting the edge detection mode; specifically, the edge detection method includes: determining edge pixel points of a target product in the frame image according to the gray value of each pixel point in the frame image; determining the edge of the target product in the frame image according to the edge pixel points of the target product in the frame image; and determining a product image of the current frame image according to the edge of the target product.
Step S203: determining at least one reference frame image meeting preset conditions;
in step S203 provided in the embodiment of the present invention, a preset condition, that is, an image having a qualified product image is used as a reference frame image.
Step S204: comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information;
step S205: and carrying out classification and identification on the description vectors according to a pre-trained classification and identification model to obtain the class attribute of the gray level image.
Specifically, in the embodiment of the present invention, the category attribute may be a qualified product or an unqualified product, and when the product is determined as an unqualified product, the appearance defect of the unqualified product is specifically subdivided, for example, the product image is incomplete, such as the product edge is missing.
Further, in another preferred embodiment provided by the present invention, after the step of performing classification recognition on the description vector according to a pre-trained classification recognition model, the method further includes: and according to the classification recognition result, modifying and optimizing the classification recognition model to obtain a more accurate classification recognition model.
FIG. 3 is a sub-flowchart of a method for artificial intelligence based visual information processing according to an embodiment of the present invention; further, in a preferred embodiment provided by the present invention, the step S202 of preprocessing the original video specifically includes:
step S2021: extracting a frame image set of the original video, and determining a product image of each frame image;
step S2022: and carrying out gray level processing on a plurality of frame images containing preset images in the frame image set.
FIG. 4 is another sub-flowchart of a method for artificial intelligence based visual information processing according to an embodiment of the present invention;
further, in a preferred embodiment of the present invention, the step S2021 of determining the product image of each frame of image specifically includes:
step S20211: determining edge pixel points of a target product in the frame image according to the gray value of each pixel point in the frame image;
step S20212: determining the edge of the target product in the frame image according to the edge pixel points of the target product in the frame image;
step S20213: and determining a product image of the current frame image according to the edge of the target product.
In the preferred embodiment provided by the present invention, to determine the product image of the current frame image, the image of the product to be detected may also be directly obtained by using an image color difference method, for example, in the image color difference method, the target product may be placed in a background having a color obviously different from that of the product, so that the image of the target product may be directly and rapidly obtained according to a huge contrast with the color of the target product and the color of the background in the image, and it can be understood that, in the image color difference method, the contrast effect of the colors of the target product and the background may meet a certain requirement, and if the color contrast effect is not obvious, the image color method may not accurately determine the product image of the current frame;
in addition, an edge detection mode can be adopted, and edge pixel points of a target product in the frame image are determined according to the gray value of each pixel point in the frame image; determining the edge of the target product in the frame image according to the edge pixel points of the target product in the frame image; determining a product image of the current frame image according to the edge of the target product; in this way, the essence is to process the edge of the image of the target product by using the gradient according to the characteristic that the gray scale of the edge of the object in the image is discontinuous, so as to further determine the image of the target product, for example, the edge detection is implemented by using Roberts edge operator or Sobel edge detection operator, and compared with the foregoing way of using image color difference, the way of using edge detection in the preferred embodiment of the present invention has no requirement for color contrast, i.e., has lower requirement for the target image.
FIG. 5 is a block diagram of an artificial intelligence based visual information processing apparatus according to an embodiment of the present invention;
further, in a preferred embodiment provided by the present invention, there is also provided an artificial intelligence based visual information processing apparatus, the apparatus 300 including:
a video camera unit 301 for acquiring an original video;
the video processing unit 302 is configured to pre-process the original video to obtain a multi-frame grayscale image;
a frame image determining unit 303, configured to determine at least one frame of reference frame image that meets a preset condition;
the image comparison unit 304 is configured to compare the multiple frames of grayscale images with the reference frame images one by one, so as to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information;
and the type identification unit 305 is configured to perform classification and identification on the description vector according to a pre-trained classification and identification model, so as to obtain a category attribute of the grayscale image.
FIG. 6 is a block diagram of a video processing unit in an artificial intelligence based visual information processing apparatus according to an embodiment of the present invention;
further, in a preferred embodiment provided by the present invention, the video processing unit 302 includes:
a product image obtaining module 3021, configured to extract a frame image set of the original video, and determine a product image of each frame image;
an image processing module 3022, configured to perform gray scale processing on a plurality of frames of images in the frame image set, where the plurality of frames of images include a preset image.
FIG. 7 is a block diagram of a product image capture module in an artificial intelligence based visual information processing apparatus according to an embodiment of the present invention;
further, in a preferred embodiment provided by the present invention, the product image acquiring module 3021 specifically includes:
an edge pixel point determining submodule 30211, configured to determine an edge pixel point of a target product in the frame image according to a gray value of each pixel point in the frame image;
the product edge determining submodule 30212 is configured to determine an edge of a target product in the frame image according to an edge pixel point of the target product in the frame image;
a product image determining sub-module 30213, configured to determine a product image of the current frame image according to the edge of the target product.
Further, in a preferred embodiment provided by the present invention, the apparatus further includes: and the model modification module is used for modifying and optimizing the classification recognition model according to the classification recognition result.
In summary, the visual information processing method based on artificial intelligence provided by the embodiment of the present invention obtains an original video; preprocessing the original video to obtain a multi-frame gray image; determining at least one reference frame image meeting preset conditions; comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information; and carrying out classification and identification on the description vectors according to a pre-trained classification and identification model to obtain the class attribute of the gray level image. The embodiment of the invention can detect the appearance of the target product in the original video, classify the appearance defects of the target product according to the detection result, and effectively solve the problems of low detection efficiency and poor effect caused by the fact that the detection of the appearance quality of the product in the automatic industry is mainly manual detection and contact detection at present.
Fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present invention. The computer device provided by the embodiment of the present invention may execute the processing flow provided by the embodiment of the artificial intelligence based visual information processing method, as shown in fig. 5, the computer device 400 includes a memory 401, a processor 402, and a computer program; therein, a computer program is stored in the memory 401 and is configured to execute an artificial intelligence based visual information processing method by the processor 402.
Wherein, in the embodiment provided by the present invention, the artificial intelligence based visual information processing method configured to be executed by the processor 402 comprises the following steps:
acquiring an original video; preprocessing the original video to obtain a multi-frame gray image; determining at least one reference frame image meeting preset conditions; comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information; and carrying out classification and identification on the description vectors according to a pre-trained classification and identification model to obtain the class attribute of the gray level image.
Furthermore, the computer device 400 may also have a communication interface 403 for receiving control instructions.
The computer device of the embodiment shown in fig. 8 may be used to implement the technical solution of the above method embodiment, and the implementation principle and technical effect are similar, which are not described herein again.
In addition, the present embodiment also provides a computer-readable storage medium, which may be a non-transitory computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the artificial intelligence based visual information processing method.
Wherein the artificial intelligence based visual information processing method executed by the processor includes: acquiring an original video; preprocessing the original video to obtain a multi-frame gray image; determining at least one reference frame image meeting preset conditions; comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information; and carrying out classification and identification on the description vectors according to a pre-trained classification and identification model to obtain the class attribute of the gray level image.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: u disk, mobile hard disk, Read-only memory (Read)
An Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like.
It is obvious to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to perform all or part of the above described functions. For the specific working process of the device described above, reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.
The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. The embodiments of the disclosure are intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A visual information processing method based on artificial intelligence, characterized in that the method comprises:
acquiring an original video;
preprocessing the original video to obtain a multi-frame gray image;
determining at least one reference frame image meeting preset conditions;
comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information;
and carrying out classification and identification on the description vectors according to a pre-trained classification and identification model to obtain the class attribute of the gray level image.
2. The artificial intelligence based visual information processing method of claim 1, wherein the step of preprocessing the original video specifically comprises:
extracting a frame image set of the original video, and determining a product image of each frame image;
and carrying out gray level processing on a plurality of frame images containing preset images in the frame image set.
3. The artificial intelligence based visual information processing method of claim 2, wherein the step of determining the product image for each frame of image specifically comprises:
determining edge pixel points of a target product in the frame image according to the gray value of each pixel point in the frame image;
determining the edge of the target product in the frame image according to the edge pixel points of the target product in the frame image;
and determining a product image of the current frame image according to the edge of the target product.
4. The artificial intelligence based visual information processing method according to claim 2 or 3, wherein after the step of performing the classification recognition on the description vector according to the pre-trained classification recognition model, the method further comprises: and modifying and optimizing the classification recognition model according to the classification recognition result.
5. An artificial intelligence based visual information processing apparatus, characterized in that the apparatus comprises:
the video shooting unit is used for acquiring an original video;
the video processing unit is used for preprocessing the original video to obtain a multi-frame gray image;
the frame image determining unit is used for determining at least one frame of reference frame image meeting preset conditions;
the image comparison unit is used for comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information;
and the type identification unit is used for carrying out classification identification on the description vector according to a pre-trained classification identification model to obtain the class attribute of the gray level image.
6. An artificial intelligence based visual information processing apparatus as claimed in claim 5, wherein said video processing unit comprises:
the product image acquisition module is used for extracting the frame image set of the original video and determining a product image of each frame image;
and the image processing module is used for carrying out gray processing on a plurality of frame images which contain preset images in the frame image set.
7. The artificial intelligence based visual information processing apparatus of claim 6, wherein the product image acquisition module specifically comprises:
the edge pixel point determining submodule is used for determining edge pixel points of a target product in the frame image according to the gray value of each pixel point in the frame image;
the product edge determining submodule is used for determining the edge of the target product in the frame image according to the edge pixel points of the target product in the frame image;
and the product image determining submodule is used for determining the product image of the current frame image according to the edge of the target product.
8. An artificial intelligence based visual information processing apparatus as claimed in claim 7, further comprising:
and the model modification module is used for modifying and optimizing the classification recognition model according to the classification recognition result.
9. A computer device comprising a memory and a processor, the memory having computer-readable instructions stored therein, the processor when executing the computer-readable instructions implementing the artificial intelligence based visual information processing method of any one of claims 1-4, comprising:
acquiring an original video;
preprocessing the original video to obtain a multi-frame gray image;
determining at least one reference frame image meeting preset conditions;
comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information;
and carrying out classification and identification on the description vectors according to a pre-trained classification and identification model to obtain the class attribute of the gray level image.
10. A computer-readable storage medium, having computer-readable instructions stored thereon, which, when executed by a processor, implement the steps of the artificial intelligence based visual information processing method of any one of claims 1-4:
acquiring an original video;
preprocessing the original video to obtain a multi-frame gray image;
determining at least one reference frame image meeting preset conditions;
comparing the multi-frame gray level images with the reference frame images one by one to obtain abnormal frame images; extracting characteristic information in an abnormal frame image, and generating a description vector from the characteristic information;
and carrying out classification and identification on the description vectors according to a pre-trained classification and identification model to obtain the class attribute of the gray level image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110507672.1A CN113256570A (en) | 2021-05-10 | 2021-05-10 | Visual information processing method, device, equipment and medium based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110507672.1A CN113256570A (en) | 2021-05-10 | 2021-05-10 | Visual information processing method, device, equipment and medium based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113256570A true CN113256570A (en) | 2021-08-13 |
Family
ID=77222437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110507672.1A Pending CN113256570A (en) | 2021-05-10 | 2021-05-10 | Visual information processing method, device, equipment and medium based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113256570A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113884504A (en) * | 2021-08-24 | 2022-01-04 | 湖南云眼智能装备有限公司 | Capacitor appearance detection control method and device |
| CN116597127A (en) * | 2023-07-12 | 2023-08-15 | 山东辰欣佛都药业股份有限公司 | Sterile eye cream packaging integrity image recognition system |
| CN117357928A (en) * | 2023-12-08 | 2024-01-09 | 广州泽力医药科技有限公司 | Plant extraction method and system based on Internet of things |
| CN117710901A (en) * | 2024-02-02 | 2024-03-15 | 鲁能泰山曲阜电缆有限公司 | Cable manufacture abnormality detection system based on machine vision |
| CN117710901B (en) * | 2024-02-02 | 2024-04-26 | 鲁能泰山曲阜电缆有限公司 | Cable manufacture abnormality detection system based on machine vision |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104992449A (en) * | 2015-08-06 | 2015-10-21 | 西安冉科信息技术有限公司 | Information identification and surface defect on-line detection method based on machine visual sense |
| CN107389701A (en) * | 2017-08-22 | 2017-11-24 | 西北工业大学 | A kind of PCB visual defects automatic checkout system and method based on image |
| CN108090897A (en) * | 2017-12-18 | 2018-05-29 | 川亿电脑(深圳)有限公司 | Detection method, detection device and the storage medium of printed wire board defect |
| CN109977808A (en) * | 2019-03-11 | 2019-07-05 | 北京工业大学 | A kind of wafer surface defects mode detection and analysis method |
| WO2020007118A1 (en) * | 2018-07-02 | 2020-01-09 | 北京百度网讯科技有限公司 | Display screen peripheral circuit detection method and device, electronic equipment and storage medium |
| CN112017172A (en) * | 2020-08-31 | 2020-12-01 | 佛山科学技术学院 | System and method for detecting defects of deep learning product based on raspberry group |
-
2021
- 2021-05-10 CN CN202110507672.1A patent/CN113256570A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104992449A (en) * | 2015-08-06 | 2015-10-21 | 西安冉科信息技术有限公司 | Information identification and surface defect on-line detection method based on machine visual sense |
| CN107389701A (en) * | 2017-08-22 | 2017-11-24 | 西北工业大学 | A kind of PCB visual defects automatic checkout system and method based on image |
| CN108090897A (en) * | 2017-12-18 | 2018-05-29 | 川亿电脑(深圳)有限公司 | Detection method, detection device and the storage medium of printed wire board defect |
| WO2020007118A1 (en) * | 2018-07-02 | 2020-01-09 | 北京百度网讯科技有限公司 | Display screen peripheral circuit detection method and device, electronic equipment and storage medium |
| CN109977808A (en) * | 2019-03-11 | 2019-07-05 | 北京工业大学 | A kind of wafer surface defects mode detection and analysis method |
| CN112017172A (en) * | 2020-08-31 | 2020-12-01 | 佛山科学技术学院 | System and method for detecting defects of deep learning product based on raspberry group |
Non-Patent Citations (1)
| Title |
|---|
| 王海波 等: "改进灰度共生矩阵的印刷品表面缺陷检测方法", 《包装工程》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113884504A (en) * | 2021-08-24 | 2022-01-04 | 湖南云眼智能装备有限公司 | Capacitor appearance detection control method and device |
| CN116597127A (en) * | 2023-07-12 | 2023-08-15 | 山东辰欣佛都药业股份有限公司 | Sterile eye cream packaging integrity image recognition system |
| CN116597127B (en) * | 2023-07-12 | 2024-01-12 | 山东辰欣佛都药业股份有限公司 | Sterile eye cream packaging integrity image recognition system |
| CN117357928A (en) * | 2023-12-08 | 2024-01-09 | 广州泽力医药科技有限公司 | Plant extraction method and system based on Internet of things |
| CN117357928B (en) * | 2023-12-08 | 2024-04-12 | 广州泽力医药科技有限公司 | Plant extraction method and system based on Internet of things |
| CN117710901A (en) * | 2024-02-02 | 2024-03-15 | 鲁能泰山曲阜电缆有限公司 | Cable manufacture abnormality detection system based on machine vision |
| CN117710901B (en) * | 2024-02-02 | 2024-04-26 | 鲁能泰山曲阜电缆有限公司 | Cable manufacture abnormality detection system based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113256570A (en) | Visual information processing method, device, equipment and medium based on artificial intelligence | |
| Zambal et al. | Accurate fibre orientation measurement for carbon fibre surfaces | |
| CN104597057B (en) | A kind of column Diode facets defect detecting device based on machine vision | |
| CN104634242A (en) | Point adding system and method of probe | |
| CN111507976A (en) | Defect detection method and system based on multi-angle imaging | |
| CN110084258A (en) | Face preferred method, equipment and storage medium based on video human face identification | |
| CN109283182A (en) | A kind of detection method of battery welding point defect, apparatus and system | |
| CN109540902A (en) | A kind of polaroid Defect Detection system and its detection method | |
| CN111239684A (en) | Binocular fast distance measurement method based on YoloV3 deep learning | |
| WO2024002187A1 (en) | Defect detection method, defect detection device, and storage medium | |
| CN113902641A (en) | Data center hot area distinguishing method and system based on infrared image | |
| CN113822882A (en) | Circuit board surface defect detection method and device based on deep learning | |
| CN113780484B (en) | Industrial product defect detection method and device | |
| CN114821274A (en) | Method and device for identifying state of split and combined indicator | |
| CN111738963B (en) | Tobacco bale package appearance detection method based on deep self-learning | |
| CN116503414B (en) | Screen defect detection method, device, computer equipment and storage medium | |
| CN115880365A (en) | Double-station automatic screw screwing detection method, system and device | |
| Prabha et al. | Defect detection of industrial products using image segmentation and saliency | |
| Niskanen et al. | Experiments with SOM based inspection of wood | |
| CN111524102B (en) | Screen dirt detection method and device of liquid crystal display | |
| CN113688819A (en) | Target object expected point tracking matching method based on mark points | |
| Tang et al. | Industrial Defect Detection Through Computer Vision: A Survey | |
| Qiao et al. | A Chip Defect Detection System Based on Machine Vision | |
| Wei et al. | Research on Abnormal Target Recognition of Full Information Mobile Monitoring Based on Machine Vision | |
| TWI712991B (en) | Defect detection method and device with both automatic optical detection and artificial intelligence detection functions |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210813 |
|
| RJ01 | Rejection of invention patent application after publication |