CN111047550A - Product abnormity detection method, device and equipment based on machine vision - Google Patents
Product abnormity detection method, device and equipment based on machine vision Download PDFInfo
- Publication number
- CN111047550A CN111047550A CN201911064971.1A CN201911064971A CN111047550A CN 111047550 A CN111047550 A CN 111047550A CN 201911064971 A CN201911064971 A CN 201911064971A CN 111047550 A CN111047550 A CN 111047550A
- Authority
- CN
- China
- Prior art keywords
- product
- image
- neural network
- convolutional neural
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- 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
- G01N2021/8883—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 involving the calculation of gauges, generating models
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Evolutionary Computation (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
Abstract
The application relates to the technical field of product detection, in particular to a method, a device and equipment for detecting product abnormity based on machine vision. Wherein the method comprises the following steps: inputting a product image of a product to be detected into a pre-trained convolutional neural network model so that the convolutional neural network model extracts product characteristic data from the product image and reconstructs a reconstructed image of the product to be detected according to the product characteristic data; judging whether the difference value between the reconstructed image and the product image is smaller than a set threshold value, and if so, determining that the product to be detected is a good product; otherwise, determining that the product to be detected is a defective product. The embodiment of the invention can automatically detect whether the product is good or defective based on the convolutional neural network model, reduces the dependence on manpower, can automatically distinguish the good from the defective only by training on good data in the training process of the convolutional neural network model, and has high detection speed and high identification precision.
Description
Technical Field
The application relates to the technical field of product detection, in particular to a method, a device and equipment for detecting product abnormity based on machine vision.
Background
Along with the continuous improvement of industrial production level, the product of output is more and more, and in the face of the product that increases daily, how select the yields fast, filter the defective substandard product, become the problem that needs to solve urgently.
The prior art mainly has two methods for detecting the defects of products: one is to find out the defective products with defects, stains, irregularities, blurs, etc. by visual observation of the inspection worker. Because the number and the variety of the produced products are various, the manual detection not only wastes time and labor, but also increases the product cost; the other detection mode is to divide the product into two types of good products and defective products, train a two-classification model by using an algorithm, and detect the product based on the two-classification model. However, in industrial production, the number of good products is large, the number of defective products is small and few, and collecting sample data of defective products is time-consuming and labor-consuming when training the two-class model.
Disclosure of Invention
In order to solve the technical problem or at least partially solve the technical problem, the application provides a method, a device and equipment for detecting product abnormity based on machine vision.
In a first aspect, an embodiment of the present invention provides a product anomaly detection method based on machine vision, including:
inputting a product image of a product to be detected into a pre-trained convolutional neural network model so that the convolutional neural network model extracts product characteristic data from the product image and reconstructs a reconstructed image of the product to be detected according to the product characteristic data;
judging whether the difference value between the reconstructed image and the product image is smaller than a set threshold value, and if so, determining that the product to be detected is a good product; otherwise, determining that the product to be detected is a defective product.
Optionally, the method further includes:
taking a product image of a sample product as a training sample, and constructing the convolutional neural network model based on the training sample; and the sample products are the same products of the products to be detected and are all good products.
Optionally, the convolutional neural network model includes: a feature extraction submodel for extracting product feature data from the product image and an image reconstruction submodel for reconstructing the product image from the product feature data.
Optionally, the training of the convolutional neural network model includes:
calculating the mean square error loss between a reconstructed image output by the image reconstruction sub-model and a product image input by the feature extraction sub-model;
and reducing the gradient of the mean square error loss by adopting a back propagation algorithm so as to train and update the image reconstruction sub-model and the feature extraction sub-model.
Optionally, the following formula is adopted to calculate the mean square error loss between the reconstructed image output by the image reconstruction sub-model and the product image input by the feature extraction sub-model:
where x represents the original image, y represents the input product image, a represents the output reconstructed image, and n represents the total number of samples.
In a second aspect, an embodiment of the present invention provides a product abnormality detection apparatus based on machine vision, including:
the neural network module is used for inputting a product image of a product to be detected into a pre-trained convolutional neural network model so that the convolutional neural network model extracts product characteristic data from the product image and reconstructs a reconstructed image of the product to be detected according to the product characteristic data;
the judging module is used for judging whether the difference value between the reconstructed image and the product image is smaller than a set threshold value or not, and if the difference value is smaller than the set threshold value, determining that the product to be detected is a good product; otherwise, determining that the product to be detected is a defective product.
Optionally, the apparatus further comprises:
the model building module is used for taking a product image of a sample product as a training sample and building the convolutional neural network model based on the training sample; and the sample products are the same products of the products to be detected and are all good products.
Optionally, the convolutional neural network model includes: a feature extraction submodel for extracting product feature data from the product image and an image reconstruction submodel for reconstructing the product image from the product feature data.
Optionally, the model building module in the process of training the convolutional neural network model includes:
calculating the mean square error loss between a reconstructed image output by the image reconstruction sub-model and a product image input by the feature extraction sub-model;
and reducing the gradient of the mean square error loss by adopting a back propagation algorithm so as to train and update the image reconstruction sub-model and the feature extraction sub-model.
In a third aspect, an embodiment of the present invention provides a product abnormality detection apparatus based on machine vision, including: a memory, a processor, wherein:
the memory is configured to store one or more computer instructions that, when executed by the processor, implement the machine vision-based product anomaly detection method described above.
In a fourth aspect, an embodiment of the present invention provides a computer storage medium for storing a computer program, where the computer program is used to enable a computer to implement the above-mentioned machine vision-based product abnormality detection method when executed.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:
according to the product abnormity detection scheme provided by the embodiment of the invention, the product image of the product to be detected is acquired, the product characteristic data is extracted from the product image based on the pre-trained convolutional neural network model, the product image is reconstructed according to the product characteristic data, the reconstructed image is compared with the input product image, and whether the product to be detected is an inferior product or not is determined according to the comparison result. Compared with the prior art, the convolutional neural network model based on the embodiment of the invention can automatically detect whether the product is good or defective, reduces the dependence on manpower, can automatically distinguish good from defective only by training on good data in the training process, and has high detection speed and high identification precision.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
FIG. 1 is a flow chart of a method for detecting product anomalies based on machine vision in accordance with an embodiment of the present invention;
FIG. 2 is a flowchart of a second method for detecting product anomalies based on machine vision according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a product abnormality detection apparatus based on machine vision according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a device corresponding to the apparatus shown in fig. 3.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and "a plurality" typically includes at least two.
In order to solve the problems that manual detection of products is time-consuming, labor-consuming and high in cost and a two-classification method is adopted to construct a model in the prior art, the embodiment of the invention provides a product abnormity detection method based on machine vision, wherein after a product image is collected, whether the product is a good product or a defective product can be automatically detected based on a convolutional neural network model, and manual participation is not needed; and the convolutional neural network can be trained by only using good sample data, the modeling process is simple and convenient, the detection speed is high, and the identification precision is high.
The method for detecting product abnormality based on machine vision according to the embodiment of the present invention will be described in detail below with reference to the accompanying drawings.
Fig. 1 is a flowchart of a method for detecting product anomalies based on machine vision according to an embodiment of the present invention. As shown in fig. 1, the processing steps of the method include:
step S101: and inputting the product image of the product to be detected into a pre-trained convolutional neural network model so that the convolutional neural network model extracts product characteristic data from the product image and reconstructs a reconstructed image of the product to be detected according to the product characteristic data.
In the embodiment of the invention, when detecting whether the product is a defective product, the original image of the product to be detected can be automatically acquired based on the camera, preferably, the original image of the product to be detected is acquired and then preprocessed to obtain the product image, and the product image is input into a pre-trained convolutional neural network model. The preprocessing of the original image comprises intercepting the identification area, correcting the identification area and the like.
After the product image is input into a pre-trained convolutional neural network model, the convolutional neural network extracts product characteristic data from the product image, and a reconstructed image of the product to be detected is obtained based on the extracted product characteristic data.
Step S102: and judging whether the difference value between the reconstructed image and the product image is smaller than a set threshold value.
Step S103: if the difference value between the reconstructed image and the product image is smaller than a set threshold value, determining that the product to be detected is a good product; otherwise, determining that the product to be detected is a defective product.
In the scheme of the embodiment of the invention, the convolutional neural network model can be trained on good products only, and the model learns the characteristic data of the good products, so that a product image can be reconstructed better when the product to be detected is a good product, and the difference between the reconstructed image and the input image is lower.
Optionally, when the difference between the reconstructed image and the product image is calculated, the mean square error between the reconstructed image and the product image may be calculated, and if the calculated mean square error is smaller than a set threshold, the product to be detected is determined to be a good product, otherwise, the product to be detected is a defective product.
The method provided by the embodiment of the invention is used for detecting the product, has high identification precision and high speed, is suitable for various scenes, and has strong practicability.
In the embodiment of the invention, the constructed convolutional neural network model comprises a feature extraction submodel for extracting product feature data from a product image and an image reconstruction submodel for reconstructing the product image according to the product feature data.
Further, when a convolutional neural network model is constructed, taking a product image of a sample product as a training sample, and constructing the convolutional neural network model based on the training sample; the sample products are the same products of the to-be-detected products and are all good products, the constructed convolutional neural network model learns the data characteristics of the good products, product images can be reconstructed well during product detection, if the to-be-detected products are good products, the error value between the reconstructed images and the input product images is low, and if the to-be-detected products are inferior products, the error value between the reconstructed images and the input product images is higher because the algorithm does not learn the inferior product characteristics.
Fig. 2 is a flowchart of a product anomaly detection method based on machine vision according to a second embodiment of the present invention. As shown in fig. 2, the method will explain the specific steps of constructing the convolutional neural network model and the process of performing product detection based on the constructed convolutional neural network model, including:
step S201: and acquiring an original image of the good product, and preprocessing the original image to obtain a sample image used as input data.
Step S202: and extracting the product characteristic data of the sample image by using the characteristic extraction sub-model. Wherein, the feature extraction submodel may be an encoder convolutional neural network.
Step S203: and constructing a reconstructed image by using the extracted product characteristic data by using the image reconstruction sub-model. Wherein, the image reconstruction submodel may be a decoder convolutional neural network.
Step S204: and calculating the mean square error loss between the reconstructed image output by the image reconstruction sub-model and the product image input by the feature extraction sub-model.
Step S205: and reducing the gradient of the mean square error loss by adopting a back propagation algorithm so as to train and update the image reconstruction sub-model and the feature extraction sub-model.
In the embodiment of the invention, the following formula can be adopted to calculate the mean square error loss between the reconstructed image output by the image reconstruction sub-model and the product image input by the feature extraction sub-model:
where x represents the original image, y represents the input product image, a represents the output reconstructed image, and n represents the total number of samples.
Step S206: when product detection is carried out, the collected product image of the product to be detected is input into the convolutional neural network model and operates forward propagation to obtain a reconstructed image.
Wherein the step of inputting the collected product image of the product to be detected into the convolutional neural network model for forward propagation comprises the following steps: the encoder convolutional neural network extracts product characteristic data from the input product image, and the decoder convolutional neural network constructs a reconstructed image by using the extracted product characteristic data.
Step S207: and judging whether the product is good or not according to the mean square error between the output reconstructed image and the input product image, wherein the product to be detected is good when the calculated mean square error is smaller than a set threshold value, and otherwise, the product is defective.
The above describes the processing flow of the product abnormality detection method based on machine vision according to the embodiment of the present invention, and the machine abnormality detection apparatus based on machine vision according to one or more embodiments of the present invention will be described in detail below. Those skilled in the art will appreciate that the apparatus may be configured using commercially available hardware components through the steps taught in this scenario.
Fig. 3 is a schematic structural diagram of a product abnormality detection apparatus based on machine vision according to an embodiment of the present invention, as shown in fig. 3, the apparatus includes: a neural network module 11 and a judgment module 12, wherein:
the neural network module 11 is configured to input a product image of a product to be detected into a pre-trained convolutional neural network model, so that the convolutional neural network model extracts product characteristic data from the product image and reconstructs a reconstructed image of the product to be detected according to the product characteristic data;
a judging module 12, configured to judge whether a difference between the reconstructed image and the product image is smaller than a set threshold, and if the difference is smaller than the set threshold, determine that the product to be tested is a good product; otherwise, determining that the product to be detected is a defective product.
In one possible design, the apparatus further includes: the model building module 13 is configured to use a product image of a sample product as a training sample, and build the convolutional neural network model based on the training sample; and the sample products are the same products of the products to be detected and are all good products.
In one possible design, the convolutional neural network model includes: a feature extraction submodel for extracting product feature data from the product image and an image reconstruction submodel for reconstructing the product image from the product feature data.
In one possible design, the model building module 13 includes, in training the convolutional neural network model: calculating the mean square error loss between a reconstructed image output by the image reconstruction sub-model and a product image input by the feature extraction sub-model; and reducing the gradient of the mean square error loss by adopting a back propagation algorithm so as to train and update the image reconstruction sub-model and the feature extraction sub-model.
The product abnormality detection device based on machine vision in the embodiment of the invention is used for realizing the product abnormality detection method in the embodiment of the invention, and reference is made to the method embodiment for details. The implementation process and technical effect of the technical solution refer to the description in the above-mentioned embodiment of the method, and are not described herein again.
The internal functions and structures of the machine vision based product abnormality detection apparatus are described above, and in one possible design, the structure of the machine vision based product abnormality detection apparatus may be implemented in a device, such as a computer, a server, etc., as shown in fig. 4, and the device may include: a processor 21 and a memory 22. Wherein the memory 22 is used for storing a program for supporting the apparatus to execute the machine vision based product abnormality detection method in the above method embodiment, and the processor 21 is configured to execute the program stored in the memory 22. The structure of the device may further include a communication interface 23, which is used for the device to communicate with other devices, such as a camera for capturing an original image of a product or a terminal device for receiving a product detection result.
In addition, an embodiment of the present invention provides a computer storage medium for storing computer software instructions for the processing device, which includes a program for executing the method for detecting product abnormality based on machine vision in the method embodiment.
The above-described embodiments of the apparatus are merely illustrative, and 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 modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A product abnormity detection method based on machine vision is characterized by comprising the following steps:
inputting a product image of a product to be detected into a pre-trained convolutional neural network model so that the convolutional neural network model extracts product characteristic data from the product image and reconstructs a reconstructed image of the product to be detected according to the product characteristic data;
judging whether the difference value between the reconstructed image and the product image is smaller than a set threshold value, and if so, determining that the product to be detected is a good product; otherwise, determining that the product to be detected is a defective product.
2. The method of claim 1, further comprising:
taking a product image of a sample product as a training sample, and constructing the convolutional neural network model based on the training sample; and the sample products are the same products of the products to be detected and are all good products.
3. The method of claim 1 or 2, wherein the convolutional neural network model comprises: a feature extraction submodel for extracting product feature data from the product image and an image reconstruction submodel for reconstructing the product image from the product feature data.
4. The method of claim 3, wherein training the convolutional neural network model comprises:
calculating the mean square error loss between a reconstructed image output by the image reconstruction sub-model and a product image input by the feature extraction sub-model;
and reducing the gradient of the mean square error loss by adopting a back propagation algorithm so as to train and update the image reconstruction sub-model and the feature extraction sub-model.
5. The method of claim 4, wherein the mean square error loss between the reconstructed image output by the image reconstruction sub-model and the product image input by the feature extraction sub-model is calculated using the following formula:
where x represents the original image, y represents the input product image, a represents the output reconstructed image, and n represents the total number of samples.
6. A machine vision-based product anomaly detection device, comprising:
the neural network module is used for inputting a product image of a product to be detected into a pre-trained convolutional neural network model so that the convolutional neural network model extracts product characteristic data from the product image and reconstructs a reconstructed image of the product to be detected according to the product characteristic data;
the judging module is used for judging whether the difference value between the reconstructed image and the product image is smaller than a set threshold value or not, and if the difference value is smaller than the set threshold value, determining that the product to be detected is a good product; otherwise, determining that the product to be detected is a defective product.
7. The apparatus of claim 6, further comprising:
the model building module is used for taking a product image of a sample product as a training sample and building the convolutional neural network model based on the training sample; and the sample products are the same products of the products to be detected and are all good products.
8. The apparatus of claim 6 or 7, wherein the convolutional neural network model comprises: a feature extraction submodel for extracting product feature data from the product image and an image reconstruction submodel for reconstructing the product image from the product feature data.
9. The apparatus of claim 8, wherein the model building module, in training the convolutional neural network model, comprises:
calculating the mean square error loss between a reconstructed image output by the image reconstruction sub-model and a product image input by the feature extraction sub-model;
and reducing the gradient of the mean square error loss by adopting a back propagation algorithm so as to train and update the image reconstruction sub-model and the feature extraction sub-model.
10. A machine vision based product anomaly detection apparatus, comprising: a memory, a processor, wherein:
the memory is configured to store one or more computer instructions that, when executed by the processor, implement the machine vision-based product anomaly detection method described above.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911064971.1A CN111047550A (en) | 2019-11-04 | 2019-11-04 | Product abnormity detection method, device and equipment based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911064971.1A CN111047550A (en) | 2019-11-04 | 2019-11-04 | Product abnormity detection method, device and equipment based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111047550A true CN111047550A (en) | 2020-04-21 |
Family
ID=70232757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911064971.1A Pending CN111047550A (en) | 2019-11-04 | 2019-11-04 | Product abnormity detection method, device and equipment based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111047550A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112150466A (en) * | 2020-11-26 | 2020-12-29 | 北京小蝇科技有限责任公司 | Method and system for detecting abnormality of white blood cell scatter diagram |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016201947A1 (en) * | 2015-06-16 | 2016-12-22 | 华南理工大学 | Method for automated detection of defects in cast wheel products |
| CN109615604A (en) * | 2018-10-30 | 2019-04-12 | 中国科学院自动化研究所 | Accessory appearance flaw detection method based on image reconstruction convolutional neural networks |
| CN109872313A (en) * | 2019-02-15 | 2019-06-11 | 苏州晓创光电科技有限公司 | A kind of method for detecting surface defects of products based on depth convolution self-encoding encoder |
| CN110211114A (en) * | 2019-06-03 | 2019-09-06 | 浙江大学 | A kind of scarce visible detection method of the vanning based on deep learning |
-
2019
- 2019-11-04 CN CN201911064971.1A patent/CN111047550A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016201947A1 (en) * | 2015-06-16 | 2016-12-22 | 华南理工大学 | Method for automated detection of defects in cast wheel products |
| CN109615604A (en) * | 2018-10-30 | 2019-04-12 | 中国科学院自动化研究所 | Accessory appearance flaw detection method based on image reconstruction convolutional neural networks |
| CN109872313A (en) * | 2019-02-15 | 2019-06-11 | 苏州晓创光电科技有限公司 | A kind of method for detecting surface defects of products based on depth convolution self-encoding encoder |
| CN110211114A (en) * | 2019-06-03 | 2019-09-06 | 浙江大学 | A kind of scarce visible detection method of the vanning based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 龚文引: "《智能算法在高光谱遥感数据处理中的应用》", 30 November 2014 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112150466A (en) * | 2020-11-26 | 2020-12-29 | 北京小蝇科技有限责任公司 | Method and system for detecting abnormality of white blood cell scatter diagram |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109613002B (en) | Glass defect detection method and device and storage medium | |
| WO2019214309A1 (en) | Model test method and device | |
| KR20230124713A (en) | Fault detection methods, devices and systems | |
| CN111091109B (en) | Method, system and equipment for predicting age and gender based on face image | |
| CN109685097B (en) | Image detection method and device based on GAN | |
| CN113469074B (en) | Remote sensing image change detection method and system based on twin attention fusion network | |
| CN112200011B (en) | Aeration tank state detection method, system, electronic equipment and storage medium | |
| CN113012157B (en) | Visual detection method and system for equipment defects | |
| CN108846842A (en) | A kind of picture noise detection method, device and electronic equipment | |
| CN108921840A (en) | Display screen peripheral circuit detection method, device, electronic equipment and storage medium | |
| CN111597933A (en) | Face recognition method and device | |
| CN111415339A (en) | Image defect detection method for complex texture industrial product | |
| CN110334775B (en) | Unmanned aerial vehicle line fault identification method and device based on width learning | |
| CN113780484B (en) | Industrial product defect detection method and device | |
| CN114078127A (en) | Object defect detection and counting method, device, equipment and storage medium | |
| CN111047550A (en) | Product abnormity detection method, device and equipment based on machine vision | |
| CN113034359A (en) | Intelligent diagnosis method and device for generator set stator and rotor defects, computer equipment and storage medium | |
| CN113139507B (en) | Automatic capturing method and system for drainage pipeline defect photos | |
| CN112598646B (en) | Capacitance defect detection method and device, electronic equipment and storage medium | |
| CN107123105A (en) | Images match defect inspection method based on FAST algorithms | |
| CN110634124A (en) | Method and equipment for area detection | |
| CN111127327B (en) | Picture inclination detection method and device | |
| CN111191593A (en) | Image target detection method and device, storage medium and sewage pipeline detection device | |
| CN113516328A (en) | Data processing method, service providing method, device, equipment and storage medium | |
| CN113838053B (en) | Screen defect detection method, device, equipment and storage medium |
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 |