CN111311544B - Floor defect detection method based on deep learning - Google Patents
Floor defect detection method based on deep learning Download PDFInfo
- Publication number
- CN111311544B CN111311544B CN202010058893.0A CN202010058893A CN111311544B CN 111311544 B CN111311544 B CN 111311544B CN 202010058893 A CN202010058893 A CN 202010058893A CN 111311544 B CN111311544 B CN 111311544B
- Authority
- CN
- China
- Prior art keywords
- image
- floor
- deep learning
- defect
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a floor defect detection method based on deep learning, which comprises the following steps: 1) Collecting high-resolution images of the floor by using an industrial camera to establish a floor detection image library; 2) Manually marking the defect area of each defect image in the floor detection image library in the step 1) to form a floor detection image label library; 3) Establishing a semantic segmentation model and an image classification model based on deep learning; 4) Expanding the floor detection image library acquired in the step 1) by adopting a data enhancement technology; 5) Performing deep learning training on the floor defect semantic segmentation model and the floor defect classification model of the image library expanded in the step 4); 6) And acquiring the floor surface image on line and detecting the defects of the floor surface based on the trained floor defect classification model. The invention can achieve the precision of manual screening without manual intervention, reduce the production cost and promote the intellectualization of the floor industry.
Description
Technical field:
the invention relates to the technical field of floor defect detection, in particular to a floor defect detection method based on deep learning.
The background technology is as follows:
The defect detection of the floor is a key link of quality control in the production process. The existing defect detection mode is mainly completed through manual naked eye screening, and the existing method has the following defects: the detection speed is low, the detection result is greatly influenced by the experience of quality inspection workers, the detection precision is uncontrollable, the cost of the quality inspection workers is high, and the like. With the advent and development of computer technology, artificial intelligence and other scientific technologies, object surface defect detection technology based on machine vision technology has developed, so that object surface defect detection effect and object surface defect detection rate are improved to a great extent, and meanwhile, the influence of factors such as scene conditions, subjective judgment and the like on the accuracy of defect detection results is avoided.
Detection techniques based on conventional image processing recognition techniques still require manual extraction of features, which require a great deal of prior knowledge and experience in their design. In the flooring industry, the surface of products is dominated by irregular textures and is of numerous categories, and traditional image algorithms do not perform satisfactorily in this case. The deep learning is used as an emerging research field, and has the advantages of capability of automatically learning useful characteristics, strong anti-interference capability and higher robustness. The deep learning technology is applied to floor defect detection, so that the existing pain point problem can be well solved.
The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person of ordinary skill in the art.
The invention comprises the following steps:
The invention aims to provide a floor defect detection method based on deep learning, so as to overcome the defects in the prior art.
In order to achieve the above object, the present invention provides a floor defect detection method based on deep learning, comprising the steps of:
1) Collecting high-resolution images of the floor by using an industrial camera to establish a floor detection image library;
2) Manually marking the defect area of each defect image in the floor detection image library in the step 1) to form a floor detection image label library;
3) Establishing a semantic segmentation model and an image classification model based on deep learning;
4) Expanding the floor detection image library acquired in the step 1) by adopting a data enhancement technology;
5) Performing deep learning training on the floor defect semantic segmentation model and the floor defect classification model of the image library expanded in the step 4);
6) And acquiring floor surface images on line, detecting defects on the floor surface based on the trained floor defect classification model, and if the defects exist, positioning the specific positions of the floor defects by using the floor defect semantic segmentation model.
The floor detection image library in the step 1) consists of high-resolution images acquired by an industrial camera, the resolution is 1024 x 1024 or more, the ratio of the number of normal image samples to the number of flaw image samples in the image library is close to 1:1, and the total number of samples in the image library is N, N >1000.
The semantic segmentation model in the step 3) is composed of an encoder Encoder and a Decoder, wherein the encoder Encoder is a basic network and comprises a convolution layer, a batch standardization layer, a pooling layer and a linear activation layer, and is used for automatically extracting depth features of an input image and outputting a group of feature images; the Decoder comprises a convolution layer and an up-sampling layer, and is used for screening the feature images and outputting the result images, wherein the resolution of the result images is the same as that of the input images.
The image classification model and the semantic segmentation model in the step 3) share parameters of an encoder Encoder, and a convolution layer and a full connection layer are added on the basis of the encoder Encoder to form the image classification model.
The data enhancement method in the step 4) comprises image horizontal overturn, image vertical overturn, image random brightness adjustment, random Gaussian noise disturbance and image random rotation, wherein the image random rotation angle range is [ -10 degrees to 10 degrees ].
When the defect detection is carried out on the floor surface in the step 6), cutting the floor surface image into a plurality of images with 1024 x 1024 resolution ratio, inputting the images into the deep learning image classification model in the step 3), and judging that the whole image is a defect image if one slice is the defect image; and 3) inputting the floor surface image, namely directly inputting the whole image when the semantic segmentation model is subjected to deep learning.
When the defect detection is carried out on the floor surface in the step 6), the floor surface image is firstly classified by a floor defect classification model trained by deep learning, if the floor surface image is not defective, the floor surface image is judged to be a normal product, and if the floor surface image is defective, the floor surface image is positioned to be a specific defect position by a floor semantic segmentation model trained by deep learning.
The step 5) floor defect semantic segmentation model and floor defect classification model deep learning training are carried out according to the following steps:
S1: randomly sampling the image library enhanced in the step 4) according to the ratio of 4:1 to divide the image library into a training set and a verification set;
S2: iterating the deep learning semantic segmentation model in the step 3) on a training set for a maximum of 150 rounds, stopping training if the loss value is converged in the training process, and selecting the model with the best performance on a verification set as a final semantic segmentation model;
s3: and 3) reading part of parameters of the trained deep learning semantic segmentation model encoder Encoder by the deep learning image classification model, freezing the part of parameters, iterating on a training set, performing fine adjustment on a convolution layer and a full connection layer except Encoder in the image classification model for the maximum 150 rounds, stopping training if the loss value is converged in the training process, and selecting the model with the best performance on a verification set as a final classification model.
The enhanced image in step 4) in S1) is cut into a plurality of 1024 x 1024 resolution image inputs.
During training, the deep learning semantic segmentation model takes DICELoss as an optimization target; during training, the deep learning classification model aims at CrossEntropyLoss at optimizing.
The trained floor defect classification model in the step 6 and the floor defect semantic segmentation model are pth files obtained by solidifying the trained model in the step 5.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, a floor defect classification model and a floor defect semantic segmentation model are trained by adopting an image classification technology and a semantic segmentation technology based on deep learning, and newly acquired images are detected in real time by taking the model as a basis, so that high-precision defect classification and defect positioning can be performed on the floor in real time; compared with the traditional image recognition method, the method automatically extracts key features in the floor image, omits a complicated manual feature extraction link, and can improve the detection speed and precision; the invention can achieve the precision of manual screening without manual intervention, reduce the production cost and promote the intellectualization of the floor industry.
Description of the drawings:
FIG. 1 is a schematic diagram of a floor defect detection method based on deep learning according to the present invention;
the specific embodiment is as follows:
The following detailed description of specific embodiments of the invention is, but it should be understood that the invention is not limited to specific embodiments.
Throughout the specification and claims, unless explicitly stated otherwise, the term "comprise" or variations thereof such as "comprises" or "comprising", etc. will be understood to include the stated element or component without excluding other elements or components.
As shown in fig. 1, a floor defect detection method based on deep learning comprises the following steps:
1) Collecting high-resolution images of the floor by using an industrial camera to establish a floor detection image library;
2) Manually marking the defect area of each defect image in the floor detection image library in the step 1) to form a floor detection image label library;
3) Establishing a semantic segmentation model and an image classification model based on deep learning;
4) Expanding the floor detection image library acquired in the step 1) by adopting a data enhancement technology;
5) Performing deep learning training on the floor defect semantic segmentation model and the floor defect classification model of the image library expanded in the step 4);
6) And acquiring floor surface images on line, detecting defects on the floor surface based on the trained floor defect classification model, and if the defects exist, positioning the specific positions of the floor defects by using the floor defect semantic segmentation model.
The floor detection image library in the step 1) consists of high-resolution images acquired by an industrial camera, the resolution is 1024 x 1024 or more, the ratio of the number of normal image samples to the number of flaw image samples in the image library is close to 1:1, and the total number of samples in the image library is N, N >1000.
The semantic segmentation model in the step 3) is composed of an encoder Encoder and a Decoder, wherein the encoder Encoder is a basic network and comprises a convolution layer, a batch standardization layer, a pooling layer and a linear activation layer, and is used for automatically extracting depth features of an input image and outputting a group of feature images; the Decoder comprises a convolution layer and an up-sampling layer, and is used for screening the feature images and outputting the result images, wherein the resolution of the result images is the same as that of the input images.
The image classification model and the semantic segmentation model in the step 3) share parameters of an encoder Encoder, and a convolution layer and a full connection layer are added on the basis of the encoder Encoder to form the image classification model.
The data enhancement method in the step 4) comprises image horizontal overturn, image vertical overturn, image random brightness adjustment, random Gaussian noise disturbance and image random rotation, wherein the image random rotation angle range is [ -10 degrees to 10 degrees ].
When the defect detection is carried out on the floor surface in the step 6), cutting the floor surface image into a plurality of images with 1024 x 1024 resolution ratio, inputting the images into the deep learning image classification model in the step 3), and judging that the whole image is a defect image if one slice is the defect image; and 3) inputting the floor surface image, namely directly inputting the whole image when the semantic segmentation model is subjected to deep learning.
When the defect detection is carried out on the floor surface in the step 6), the floor surface image is firstly classified by a floor defect classification model trained by deep learning, if the floor surface image is not defective, the floor surface image is judged to be a normal product, and if the floor surface image is defective, the floor surface image is positioned to be a specific defect position by a floor semantic segmentation model trained by deep learning.
The step 5) floor defect semantic segmentation model and floor defect classification model deep learning training are carried out according to the following steps:
S1: randomly sampling the image library enhanced in the step 4) according to the ratio of 4:1 to divide the image library into a training set and a verification set;
S2: iterating the deep learning semantic segmentation model in the step 3) on a training set for a maximum of 150 rounds, stopping training if the loss value is converged in the training process, and selecting the model with the best performance on a verification set as a final semantic segmentation model;
s3: and 3) reading part of parameters of the trained deep learning semantic segmentation model encoder Encoder by the deep learning image classification model, freezing the part of parameters, iterating on a training set, performing fine adjustment on a convolution layer and a full connection layer except Encoder in the image classification model for the maximum 150 rounds, stopping training if the loss value is converged in the training process, and selecting the model with the best performance on a verification set as a final classification model.
The enhanced image in step 4) in S1) is cut into a plurality of 1024 x 1024 resolution image inputs.
During training, the deep learning semantic segmentation model takes DICELoss as an optimization target; during training, the deep learning classification model aims at CrossEntropyLoss at optimizing.
The trained floor defect classification model in the step 6 and the floor defect semantic segmentation model are pth files obtained by solidifying the trained model in the step 5.
In the training process, only data in the training set can execute data enhancement operation during iteration, the verification set does not execute data enhancement, a loss value of a model on the verification set can be calculated after each iteration is finished, and the model with the minimum loss value is stored as Pytorch pth files. The initialization parameters used by the model during training are model parameters obtained by training on an ImageNet classification data set; the parameter updating mode during training is Adam, the initial learning rate is 0.001, and the batch size is 8.
According to the invention, a floor defect classification model and a floor defect semantic segmentation model are trained by adopting an image classification technology and a semantic segmentation technology based on deep learning, and newly acquired images are detected in real time by taking the model as a basis, so that high-precision defect classification and defect positioning can be performed on the floor in real time; compared with the traditional image recognition method, the method automatically extracts key features in the floor image, omits a complicated manual feature extraction link, and can improve the detection speed and precision; the invention can achieve the precision of manual screening without manual intervention, reduce the production cost and promote the intellectualization of the floor industry.
The foregoing descriptions of specific exemplary embodiments of the present invention are presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain the specific principles of the invention and its practical application to thereby enable one skilled in the art to make and utilize the invention in various exemplary embodiments and with various modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.
Claims (7)
1. A floor defect detection method based on deep learning is characterized in that: the method comprises the following steps:
1) Collecting high-resolution images of the floor by using an industrial camera to establish a floor detection image library;
2) Manually marking the defect area of each defect image in the floor detection image library in the step 1) to form a floor detection image label library;
3) Establishing a semantic segmentation model and an image classification model based on deep learning;
4) Expanding the floor detection image library acquired in the step 1) by adopting a data enhancement technology;
5) Performing deep learning training on the floor defect semantic segmentation model and the floor defect classification model of the image library expanded in the step 4);
6) Acquiring floor surface images on line, detecting defects on the floor surface based on a trained floor defect classification model, and if the defects exist, positioning the specific positions of the floor defects by utilizing a floor defect semantic segmentation model;
When the defect detection is carried out on the floor surface in the step 6), cutting the floor surface image into a plurality of images with 1024 x 1024 resolution ratio, inputting the images into the deep learning image classification model in the step 3), and judging that the whole image is a defect image if one slice is the defect image; the floor surface image is input, namely the whole image is directly input when the deep learning semantic segmentation model is input in the step 3);
When the defect detection is carried out on the floor surface in the step 6), the floor surface image is firstly classified by a floor defect classification model trained by deep learning, if the floor surface image is not defective, the floor surface image is judged to be a normal product, and if the floor surface image is defective, the specific defect position is positioned by a floor semantic segmentation model trained by deep learning;
the step 5) floor defect semantic segmentation model and floor defect classification model deep learning training are carried out according to the following steps:
S1: randomly sampling the image library enhanced in the step 4) according to the ratio of 4:1 to divide the image library into a training set and a verification set;
S2: iterating the deep learning semantic segmentation model in the step 3) on a training set for a maximum of 150 rounds, stopping training if the loss value is converged in the training process, and selecting the model with the best performance on a verification set as a final semantic segmentation model;
S3: step 3), the deep learning image classification model reads part of parameters of a trained deep learning semantic segmentation model encoder Encoder and freezes the part of parameters, iterates on a training set, and only fine-tunes a convolution layer and a full connection layer except Encoder in the image classification model for the maximum 150 rounds, stops training if a loss value is converged in the training process, and selects a model with the best performance on a verification set as a final classification model;
In the training process, only data in the training set can execute data enhancement operation during iteration, the verification set does not execute data enhancement, the loss value of the model on the verification set can be calculated after each iteration, the model with the minimum loss value is stored as Pytorch pth files, the initialization parameters used by the model during training are model parameters obtained by training on the Imagenet classified data set, the parameter updating mode during training is Adam, the initial learning rate is 0.001, and the batch size is 8.
2. The floor defect detection method based on deep learning as claimed in claim 1, wherein: the floor detection image library in the step 1) consists of high-resolution images acquired by an industrial camera, the resolution is 1024 x 1024 or more, the ratio of the number of normal image samples to the number of flaw image samples in the image library is close to 1:1, and the total number of samples in the image library is N, N >1000.
3. The floor defect detection method based on deep learning as claimed in claim 1, wherein: the semantic segmentation model in the step 3) is composed of an encoder Encoder and a Decoder, wherein the encoder Encoder is a basic network and comprises a convolution layer, a batch standardization layer, a pooling layer and a linear activation layer, and is used for automatically extracting depth features of an input image and outputting a group of feature images; the Decoder comprises a convolution layer and an up-sampling layer, and is used for screening the feature images and outputting the result images, wherein the resolution of the result images is the same as that of the input images.
4. The floor defect detection method based on deep learning as claimed in claim 1, wherein: the image classification model and the semantic segmentation model in the step 3) share parameters of an encoder Encoder, and a convolution layer and a full connection layer are added on the basis of the encoder Encoder to form the image classification model.
5. The floor defect detection method based on deep learning as claimed in claim 1, wherein: the data enhancement method in the step 4) comprises image horizontal overturn, image vertical overturn, image random brightness adjustment, random Gaussian noise disturbance and image random rotation, wherein the image random rotation angle range is [ -10 degrees to 10 degrees ].
6. The floor defect detection method based on deep learning as claimed in claim 1, wherein: the enhanced image of the step 4) is cut into a plurality of 1024 x 1024 resolution image inputs.
7. The floor defect detection method based on deep learning as claimed in claim 1, wherein: during training, the deep learning semantic segmentation model takes DICELoss as an optimization target; during training, the deep learning classification model aims at CrossEntropyLoss at optimizing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010058893.0A CN111311544B (en) | 2020-01-19 | 2020-01-19 | Floor defect detection method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010058893.0A CN111311544B (en) | 2020-01-19 | 2020-01-19 | Floor defect detection method based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111311544A CN111311544A (en) | 2020-06-19 |
| CN111311544B true CN111311544B (en) | 2024-04-26 |
Family
ID=71158236
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010058893.0A Active CN111311544B (en) | 2020-01-19 | 2020-01-19 | Floor defect detection method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111311544B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113837209A (en) * | 2020-06-23 | 2021-12-24 | 乐达创意科技股份有限公司 | Methods and systems for improving machine learning using data for training |
| CN112132784A (en) * | 2020-08-22 | 2020-12-25 | 安徽大学 | Method for classifying and segmenting industrial magnetic tile defect image based on small sample deep convolution neural network |
| CN111986199B (en) * | 2020-09-11 | 2024-04-16 | 征图新视(江苏)科技股份有限公司 | Method for detecting surface flaws of wood floor based on unsupervised deep learning |
| CN112365443B (en) * | 2020-10-16 | 2021-10-12 | 珠海市奥德维科技有限公司 | Hexahedron defect detection method and medium based on deep learning |
| CN112990392A (en) * | 2021-05-20 | 2021-06-18 | 四川大学 | New material floor defect target detection system based on improved YOLOv5 algorithm |
| CN113283541B (en) * | 2021-06-15 | 2022-07-22 | 无锡锤头鲨智能科技有限公司 | A kind of floor automatic sorting method |
| CN113344888A (en) * | 2021-06-17 | 2021-09-03 | 四川启睿克科技有限公司 | Surface defect detection method and device based on combined model |
| CN113627315B (en) * | 2021-08-06 | 2024-04-30 | 上海华测导航技术股份有限公司 | Method for preprocessing process data from edge camera to algorithm reasoning |
| CN113781430B (en) * | 2021-09-09 | 2023-08-25 | 北京云屿科技有限公司 | Glove surface defect detection method and system based on deep learning |
| CN113822867A (en) * | 2021-09-24 | 2021-12-21 | 东莞市诺丽电子科技有限公司 | A kind of train appearance abnormality detection method and train appearance abnormality detection system |
| CN114066856A (en) * | 2021-11-18 | 2022-02-18 | 深圳市商汤科技有限公司 | Model training method and device, electronic equipment and storage medium |
| CN114565587A (en) * | 2022-03-03 | 2022-05-31 | 北京好运达智创科技有限公司 | Nondestructive testing device and method for box girder grouting |
| CN115240031B (en) * | 2022-07-21 | 2023-10-27 | 无锡锤头鲨智能科技有限公司 | Board surface defect generation method and system based on generation countermeasure network |
| CN117132605A (en) * | 2023-08-29 | 2023-11-28 | 江苏集萃中科先进光电技术研究所有限公司 | Large model image segmentation method for surface defect detection in industrial fields |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110175988A (en) * | 2019-04-25 | 2019-08-27 | 南京邮电大学 | Cloth defect inspection method based on deep learning |
| CN110458814A (en) * | 2019-07-29 | 2019-11-15 | 山东艾雷维特智能科技有限公司 | A kind of detection method of wood single-plate defect, apparatus and system |
| CN110473173A (en) * | 2019-07-24 | 2019-11-19 | 熵智科技(深圳)有限公司 | A kind of defect inspection method based on deep learning semantic segmentation |
| CN110554052A (en) * | 2019-10-12 | 2019-12-10 | 南宁市威锐康商贸有限公司 | artificial board surface defect detection method and system |
| WO2019233166A1 (en) * | 2018-06-04 | 2019-12-12 | 杭州海康威视数字技术股份有限公司 | Surface defect detection method and apparatus, and electronic device |
-
2020
- 2020-01-19 CN CN202010058893.0A patent/CN111311544B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019233166A1 (en) * | 2018-06-04 | 2019-12-12 | 杭州海康威视数字技术股份有限公司 | Surface defect detection method and apparatus, and electronic device |
| CN110175988A (en) * | 2019-04-25 | 2019-08-27 | 南京邮电大学 | Cloth defect inspection method based on deep learning |
| CN110473173A (en) * | 2019-07-24 | 2019-11-19 | 熵智科技(深圳)有限公司 | A kind of defect inspection method based on deep learning semantic segmentation |
| CN110458814A (en) * | 2019-07-29 | 2019-11-15 | 山东艾雷维特智能科技有限公司 | A kind of detection method of wood single-plate defect, apparatus and system |
| CN110554052A (en) * | 2019-10-12 | 2019-12-10 | 南宁市威锐康商贸有限公司 | artificial board surface defect detection method and system |
Non-Patent Citations (1)
| Title |
|---|
| 基于深度学习的织物缺陷在线检测算法;王理顺，钟勇，李振东，贺宜龙;计算机应用;20190710;第39卷(第7期);2125-2128 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111311544A (en) | 2020-06-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111311544B (en) | Floor defect detection method based on deep learning | |
| CN113239930B (en) | Glass paper defect identification method, system, device and storage medium | |
| CN108961217B (en) | Surface defect detection method based on regular training | |
| CN107392896B (en) | A wood defect detection method and system based on deep learning | |
| CN109191459B (en) | Automatic identification and grading method of center segregation defect in low magnification structure of continuous casting slab | |
| CN113298757A (en) | Metal surface defect detection method based on U-NET convolutional neural network | |
| CN115018790A (en) | Workpiece surface defect detection method based on anomaly detection | |
| CN108961246B (en) | An artificial intelligence-based method for pore recognition in scanning electron microscope images | |
| CN114743102B (en) | Flaw detection method, system and device for furniture plate | |
| CN119941726B (en) | A circuit board surface defect detection method and system | |
| CN112767369A (en) | Defect identification and detection method and device for small hardware and computer readable storage medium | |
| CN110766664B (en) | Method for detecting appearance defective products of electronic components based on deep learning | |
| CN115797314B (en) | Method, system, equipment and storage medium for detecting surface defects of parts | |
| CN103175844A (en) | Detection method for scratches and defects on surfaces of metal components | |
| CN115587989A (en) | A method and system for detection and segmentation of workpiece CT image defects | |
| CN108921201A (en) | Recognition and Classification of Dam Defects Based on Feature Combination and CNN | |
| CN112907561A (en) | Notebook appearance flaw detection method based on deep learning | |
| CN111127454A (en) | Method and system for generating industrial defect sample based on deep learning | |
| CN107194432B (en) | Refrigerator door body identification method and system based on deep convolutional neural network | |
| CN117522778A (en) | A hollow brick defect detection system | |
| CN120009281A (en) | A system, method, storage medium and computer program product for automobile engine cylinder head appearance inspection and defect determination based on machine vision | |
| CN117723564B (en) | Packaging bag printing quality detection method and system based on image transmission | |
| CN115861220A (en) | Cold-rolled strip steel surface defect detection method and system based on improved SSD algorithm | |
| CN118967474A (en) | A defect image enhancement method based on traditional data enhancement | |
| CN112598646B (en) | Capacitance defect detection method and device, electronic 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |