CN116071348A - Workpiece surface detection method and related device based on visual detection - Google Patents
Workpiece surface detection method and related device based on visual detection Download PDFInfo
- Publication number
- CN116071348A CN116071348A CN202310192847.3A CN202310192847A CN116071348A CN 116071348 A CN116071348 A CN 116071348A CN 202310192847 A CN202310192847 A CN 202310192847A CN 116071348 A CN116071348 A CN 116071348A
- Authority
- CN
- China
- Prior art keywords
- polishing
- image
- workpiece
- grinding
- outer curved
- 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.)
- Granted
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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]
-
- 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
- G06T2207/20112—Image segmentation details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Constituent Portions Of Griding Lathes, Driving, Sensing And Control (AREA)
Abstract
The invention relates to the field of image processing, and discloses a workpiece surface detection method based on visual detection and a related device, which are used for improving the accuracy of polishing detection of a target workpiece. The method comprises the following steps: model training is carried out on the first training model according to the side grinding training set to obtain a side grinding detection model, and training is carried out on the second training model according to the outer curved surface grinding training set to obtain an outer curved surface grinding detection model; acquiring an original polishing image of a target workpiece, and inputting the original polishing image into a side polishing detection model for detection to obtain a side polishing quality detection result; inputting the original grinding image into an outer curved surface grinding detection model for detection to obtain an outer curved surface grinding quality detection result; and according to the outer curved surface polishing quality detection result and the side surface polishing quality detection result, performing equipment parameter adjustment on workpiece polishing equipment, and performing next polishing on the target workpiece by adopting the workpiece polishing equipment with the adjusted parameters.
Description
Technical Field
The invention relates to the field of image processing, in particular to a workpiece surface detection method based on visual detection and a related device.
Background
At present, the workpiece processing equipment can realize 3D profiling processing, can polish positions such as wire drawing product side, cambered surface, and the like, is internally provided with polishing automatic spray circulation filtering facilities, and is efficient and environment-friendly, and the full-automatic polishing of two to four sides grinding heads is realized according to the product polishing process requirements.
The workpiece is required to be detected after polishing, and the traditional polishing quality detection still relies on manual detection to a large extent, namely, the polishing quality detection is finished through manual comparison, so that the quality detection accuracy is low, and the product quality cannot be guaranteed.
Disclosure of Invention
The invention provides a workpiece surface detection method based on visual detection and a related device, which are used for improving the accuracy of polishing detection of a target workpiece.
The first aspect of the invention provides a workpiece surface detection method based on visual detection, which comprises the following steps:
acquiring a plurality of sample polishing images, respectively marking side polishing areas in each sample polishing image to obtain a side polishing training set, and respectively marking outer curved surface polishing areas in each sample polishing image to obtain an outer curved surface polishing training set;
Model training is carried out on a preset first training model according to the side grinding training set to obtain a side grinding detection model, and training is carried out on a preset second training model according to the outer curved surface grinding training set to obtain an outer curved surface grinding detection model;
acquiring an original polishing image of a target workpiece based on an image acquisition terminal in workpiece polishing equipment, and inputting the original polishing image into the side polishing detection model for detection to obtain a side polishing quality detection result;
inputting the original grinding image into the outer curved surface grinding detection model for detection to obtain an outer curved surface grinding quality detection result;
according to the outer curved surface polishing quality detection result and the side surface polishing quality detection result, adjusting equipment parameters of the workpiece polishing equipment;
and (3) polishing the target workpiece for the next round by adopting workpiece polishing equipment with the parameters adjusted until the target workpiece meets the preset polishing standard.
Optionally, in a first implementation manner of the first aspect of the present invention, the obtaining a plurality of sample polishing images, and labeling a side polishing area in each sample polishing image to obtain a side polishing training set, and labeling an outer curved polishing area in each sample polishing image to obtain an outer curved polishing training set, respectively, includes:
Acquiring a plurality of sample polishing images, classifying and labeling the sample polishing images to obtain an image label of each sample polishing image;
marking the side grinding areas in each sample grinding image according to the image labels of each sample grinding image to obtain a side grinding training set;
and marking the outer curved surface polishing areas in each sample polishing image respectively to obtain an outer curved surface polishing training set.
Optionally, in a second implementation manner of the first aspect of the present invention, the training a preset first training model according to the side grinding training set to obtain a side grinding detection model includes:
inputting the side grinding training set into a preset first training model, wherein the first training model comprises: a double-layer convolution network, a batch normalization layer, a feature fusion layer and a classification network;
performing feature extraction and pixel point prediction on the side grinding training set through the first training model to obtain a first prediction result;
and optimizing parameters of the first training model according to the first prediction result until the first training model converges to obtain a side grinding detection model.
Optionally, in a third implementation manner of the first aspect of the present invention, the acquiring, based on an image acquisition terminal in a workpiece polishing device, an original polishing image of a target workpiece, and inputting the original polishing image into the side polishing detection model for detection, to obtain a side polishing quality detection result, includes:
acquiring an original polishing image of a target workpiece based on an image acquisition terminal in workpiece polishing equipment;
inputting the original polished image into the side polishing detection model, and extracting features of the original polished image through the double-layer convolution network to obtain a first feature map;
inputting the first feature map into the batch normalization layer for normalization processing to obtain a normalized feature map;
inputting the normalized feature map into the feature fusion layer to perform feature fusion processing to obtain a second feature map;
and inputting the second feature map into the classification network, predicting a plurality of pixel points in the second feature map through the classification network, and generating a side grinding quality detection result corresponding to the original grinding image.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the performing, according to the outer curved surface polishing quality detection result and the side polishing quality detection result, device parameter adjustment on the workpiece polishing device includes:
Marking polishing defect point positions of the original polishing image according to the polishing quality detection result of the outer curved surface and the polishing quality detection result of the side surface to obtain polishing defect point position information;
determining a polishing control area of the workpiece polishing equipment according to the polishing defect point position information;
and adjusting the equipment polishing force parameters of the polishing control area.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the method for detecting a surface of a workpiece based on visual detection further includes:
inquiring a standard target workpiece image of the target workpiece from a preset database;
extracting a side polishing area of the standard target workpiece image to obtain a standard side polishing area;
extracting an outer curved surface polishing area from the standard target workpiece image to obtain a standard outer curved surface polishing area;
and constructing a workpiece template image of the target workpiece based on the standard target workpiece image, the standard side polishing area and the standard outer curved polishing area.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the performing, with the workpiece polishing device after the parameter adjustment, next polishing on the target workpiece until the target workpiece meets a preset polishing standard includes:
Performing next polishing on the target workpiece by adopting workpiece polishing equipment with adjusted parameters, and collecting real-time polishing images of the target workpiece;
extracting characteristic detection points in the real-time polished image;
performing feature point matching on the feature detection points and the workpiece template image to obtain feature point matching results;
and generating a polishing detection result corresponding to the original polishing image according to the characteristic point matching result.
A second aspect of the present invention provides a workpiece surface inspection apparatus based on visual inspection, the workpiece surface inspection apparatus based on visual inspection comprising:
the labeling module is used for acquiring a plurality of sample polishing images, labeling side polishing areas in each sample polishing image respectively to obtain a side polishing training set, and labeling outer curved surface polishing areas in each sample polishing image respectively to obtain an outer curved surface polishing training set;
the training module is used for carrying out model training on a preset first training model according to the side surface grinding training set to obtain a side surface grinding detection model, and carrying out training on a preset second training model according to the outer curved surface grinding training set to obtain an outer curved surface grinding detection model;
The first detection module is used for acquiring an original polishing image of a target workpiece based on an image acquisition terminal in workpiece polishing equipment, inputting the original polishing image into the side polishing detection model for detection, and obtaining a side polishing quality detection result;
the second detection module is used for inputting the original grinding image into the outer curved surface grinding detection model for detection to obtain an outer curved surface grinding quality detection result;
the adjusting module is used for adjusting equipment parameters of the workpiece polishing equipment according to the outer curved surface polishing quality detection result and the side surface polishing quality detection result;
and the processing module is used for polishing the target workpiece in the next round by adopting the workpiece polishing equipment with the parameters adjusted until the target workpiece meets the preset polishing standard.
Optionally, in a first implementation manner of the second aspect of the present invention, the labeling module is specifically configured to:
acquiring a plurality of sample polishing images, classifying and labeling the sample polishing images to obtain an image label of each sample polishing image;
marking the side grinding areas in each sample grinding image according to the image labels of each sample grinding image to obtain a side grinding training set;
And marking the outer curved surface polishing areas in each sample polishing image respectively to obtain an outer curved surface polishing training set.
Optionally, in a second implementation manner of the second aspect of the present invention, the training module is specifically configured to:
inputting the side grinding training set into a preset first training model, wherein the first training model comprises: a double-layer convolution network, a batch normalization layer, a feature fusion layer and a classification network;
performing feature extraction and pixel point prediction on the side grinding training set through the first training model to obtain a first prediction result;
and optimizing parameters of the first training model according to the first prediction result until the first training model converges to obtain a side grinding detection model.
Optionally, in a third implementation manner of the second aspect of the present invention, the first detection module is specifically configured to:
acquiring an original polishing image of a target workpiece based on an image acquisition terminal in workpiece polishing equipment;
inputting the original polished image into the side polishing detection model, and extracting features of the original polished image through the double-layer convolution network to obtain a first feature map;
Inputting the first feature map into the batch normalization layer for normalization processing to obtain a normalized feature map;
inputting the normalized feature map into the feature fusion layer to perform feature fusion processing to obtain a second feature map;
and inputting the second feature map into the classification network, predicting a plurality of pixel points in the second feature map through the classification network, and generating a side grinding quality detection result corresponding to the original grinding image.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the adjusting module is specifically configured to:
marking polishing defect point positions of the original polishing image according to the polishing quality detection result of the outer curved surface and the polishing quality detection result of the side surface to obtain polishing defect point position information;
determining a polishing control area of the workpiece polishing equipment according to the polishing defect point position information;
and adjusting the equipment polishing force parameters of the polishing control area.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the workpiece surface detection device based on visual detection further includes:
the construction module is used for inquiring a standard target workpiece image of the target workpiece from a preset database; extracting a side polishing area of the standard target workpiece image to obtain a standard side polishing area; extracting an outer curved surface polishing area from the standard target workpiece image to obtain a standard outer curved surface polishing area; and constructing a workpiece template image of the target workpiece based on the standard target workpiece image, the standard side polishing area and the standard outer curved polishing area.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the processing module is specifically configured to:
performing next polishing on the target workpiece by adopting workpiece polishing equipment with adjusted parameters, and collecting real-time polishing images of the target workpiece;
extracting characteristic detection points in the real-time polished image;
performing feature point matching on the feature detection points and the workpiece template image to obtain feature point matching results;
and generating a polishing detection result corresponding to the original polishing image according to the characteristic point matching result.
A third aspect of the present invention provides a workpiece surface inspection apparatus based on visual inspection, comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the vision-based workpiece surface inspection apparatus to perform the vision-based workpiece surface inspection method described above.
A fourth aspect of the present invention provides a computer readable storage medium having instructions stored therein which, when run on a computer, cause the computer to perform the above-described visual inspection-based workpiece surface inspection method.
According to the technical scheme, the first training model is subjected to model training according to the side grinding training set to obtain a side grinding detection model, and the second training model is subjected to training according to the outer curved surface grinding training set to obtain an outer curved surface grinding detection model; acquiring an original polishing image of a target workpiece, and inputting the original polishing image into a side polishing detection model for detection to obtain a side polishing quality detection result; inputting the original grinding image into an outer curved surface grinding detection model for detection to obtain an outer curved surface grinding quality detection result; according to the detection result of the polishing quality of the outer curved surface and the detection result of the polishing quality of the side surface, the workpiece polishing equipment is subjected to equipment parameter adjustment, and the workpiece polishing equipment with the parameter adjustment is used for polishing the target workpiece in the next round.
Drawings
FIG. 1 is a schematic view of one embodiment of a method for detecting a surface of a workpiece based on visual detection in an embodiment of the invention;
FIG. 2 is a schematic diagram of another embodiment of a method for detecting a surface of a workpiece based on visual detection in an embodiment of the invention;
FIG. 3 is a schematic view of an embodiment of a workpiece surface inspection apparatus based on visual inspection in accordance with an embodiment of the invention;
FIG. 4 is a schematic view of another embodiment of a workpiece surface inspection apparatus based on visual inspection in accordance with an embodiment of the invention;
FIG. 5 is a schematic diagram of an embodiment of a workpiece surface inspection apparatus based on visual inspection in an embodiment of the invention.
Detailed Description
The embodiment of the invention provides a workpiece surface detection method based on visual detection and a related device, which are used for improving the accuracy of polishing detection of a target workpiece. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For ease of understanding, a specific flow of an embodiment of the present invention is described below with reference to fig. 1, where an embodiment of a method for detecting a surface of a workpiece based on visual detection in the embodiment of the present invention includes:
101. acquiring a plurality of sample polishing images, respectively marking side polishing areas in each sample polishing image to obtain a side polishing training set, and respectively marking outer curved surface polishing areas in each sample polishing image to obtain an outer curved surface polishing training set;
it will be appreciated that the execution subject of the present invention may be a workpiece surface detection device based on visual detection, and may also be a terminal or a server, and is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.
Specifically, the server inputs a plurality of sample polishing images into a polishing area analysis model respectively to obtain a plurality of area prediction results, integrates the plurality of area prediction results to obtain a total area prediction result, obtains each area to be polished in the picture according to the total area prediction result, marks the side polishing area in each sample polishing image respectively to obtain a side polishing training set, marks the outer curved polishing area in each sample polishing image respectively to obtain an outer curved polishing training set.
102. Model training is carried out on a preset first training model according to the side grinding training set to obtain a side grinding detection model, and training is carried out on a preset second training model according to the outer curved surface grinding training set to obtain an outer curved surface grinding detection model;
specifically, the server performs standardization processing on data in a training data set corresponding to each data in the side polishing training set by acquiring the side polishing data set corresponding to each data in the side polishing training set, so as to obtain a standardized training data set corresponding to the side polishing data set, performs model training on a preset first training model through back propagation training by adopting the standardized training data set corresponding to the side polishing data set until a loss function reaches a minimum value, so as to obtain a side polishing detection model, and performs training on a preset second training model according to the outer curved polishing training set, so as to obtain an outer curved polishing detection model.
103. Acquiring an original polishing image of a target workpiece based on an image acquisition terminal in workpiece polishing equipment, and inputting the original polishing image into a side polishing detection model for detection to obtain a side polishing quality detection result;
Specifically, the server acquires an original polishing image of a target workpiece based on an image acquisition terminal in workpiece polishing equipment, the server inputs the original polishing image into a side polishing detection model to perform feature extraction to obtain a corresponding first feature image, the server performs normalization processing on the first feature image to obtain a corresponding normalized feature image, and further, the server detects the original polishing image through the normalized feature image and a feature fusion layer of the side polishing model to obtain a side polishing quality detection result.
104. Inputting the original grinding image into an outer curved surface grinding detection model for detection to obtain an outer curved surface grinding quality detection result;
the server inputs the original polished image into the outer curved surface polishing detection model to extract image features to obtain corresponding polished image features, then the server performs pixel point analysis on the original polished image through the polished image features to determine a corresponding pixel point analysis result, and finally the server detects the original polished image through the pixel point analysis result to obtain a corresponding outer curved surface polishing quality detection result.
105. According to the outer curved surface polishing quality detection result and the side surface polishing quality detection result, adjusting equipment parameters of workpiece polishing equipment;
specifically, the server analyzes the defect point positions of the original polished image according to the detection result of the polishing quality of the outer curved surface and the detection result of the polishing quality of the side surface, and determines corresponding defect point position information.
106. And (3) adopting workpiece polishing equipment with parameters adjusted to polish the target workpiece in the next round until the target workpiece meets the preset polishing standard.
In the embodiment of the invention, a first training model is subjected to model training according to a side grinding training set to obtain a side grinding detection model, and a second training model is subjected to training according to an outer curved surface grinding training set to obtain an outer curved surface grinding detection model; acquiring an original polishing image of a target workpiece, and inputting the original polishing image into a side polishing detection model for detection to obtain a side polishing quality detection result; inputting the original grinding image into an outer curved surface grinding detection model for detection to obtain an outer curved surface grinding quality detection result; according to the detection result of the polishing quality of the outer curved surface and the detection result of the polishing quality of the side surface, the workpiece polishing equipment is subjected to equipment parameter adjustment, and the workpiece polishing equipment with the parameter adjustment is used for polishing the target workpiece in the next round.
Referring to fig. 2, another embodiment of a method for detecting a surface of a workpiece based on visual detection according to an embodiment of the invention includes:
201. acquiring a plurality of sample polishing images, respectively marking side polishing areas in each sample polishing image to obtain a side polishing training set, and respectively marking outer curved surface polishing areas in each sample polishing image to obtain an outer curved surface polishing training set;
specifically, a plurality of sample polishing images are obtained, and the sample polishing images are classified and labeled to obtain an image label of each sample polishing image; marking the side grinding areas in each sample grinding image according to the image labels of each sample grinding image to obtain a side grinding training set; and marking the outer curved surface polishing areas in each sample polishing image respectively to obtain an outer curved surface polishing training set.
The method comprises the steps that a plurality of sample polishing images are obtained by a server, the plurality of sample polishing images are further classified and labeled by the server, the plurality of sample polishing images are labeled and classified by the server through a preset target image labeling model, corresponding image sample sets are output, image labeling and classification are sequentially carried out on the image sample sets output by a previous target image labeling model through the rest unselected image labeling models, image samples inconsistent with target classification types are removed from a current classification result until images generated by labeling classification of the current target image labeling model meet the preset image labeling quantity, image labels of each sample polishing image are obtained, side polishing areas in each sample polishing image are labeled according to the image labels of each sample polishing image, side polishing training sets are obtained, and outer curved surface polishing areas in each sample polishing image are labeled to obtain outer curved surface polishing training sets.
202. Model training is carried out on a preset first training model according to the side grinding training set to obtain a side grinding detection model, and training is carried out on a preset second training model according to the outer curved surface grinding training set to obtain an outer curved surface grinding detection model;
specifically, the side grinding training set is input into a preset first training model, wherein the first training model comprises: a double-layer convolution network, a batch normalization layer, a feature fusion layer and a classification network; feature extraction and pixel point prediction are carried out on the side grinding training set through a first training model, and a first prediction result is obtained; and optimizing parameters of the first training model according to the first prediction result until the first training model converges to obtain a side grinding detection model.
The method comprises the steps of inputting a side grinding training set into a preset first training model, wherein the first training model comprises: a double-layer convolution network, a batch normalization layer, a feature fusion layer and a classification network; and carrying out feature extraction and pixel prediction on the side grinding training set through a first training model, wherein the server processes the side grinding training set, carries out segmentation processing on a gray level change feature map in the side grinding training set according to an image segmentation threshold value, carries out multiple screening on pixels contained in the side grinding training set to obtain a target defect significance feature map and a defect subgraph of the side grinding training set, simultaneously carries out pixel prediction on the side grinding training set to obtain a first prediction result, and finally optimizes parameters of the first training model according to the first prediction result until the first training model converges to obtain a side grinding detection model.
203. Acquiring an original polishing image of a target workpiece based on an image acquisition terminal in workpiece polishing equipment, and inputting the original polishing image into a side polishing detection model for detection to obtain a side polishing quality detection result;
specifically, acquiring an original polishing image of a target workpiece based on an image acquisition terminal in workpiece polishing equipment; inputting an original polished image into a side polishing detection model, and extracting features of the original polished image through a double-layer convolution network to obtain a first feature map; inputting the first feature map into a batch normalization layer for normalization processing to obtain a normalized feature map; inputting the normalized feature map into a feature fusion layer to perform feature fusion processing to obtain a second feature map; inputting the second feature map into a classification network, predicting a plurality of pixel points in the second feature map through the classification network, and generating a side grinding quality detection result corresponding to the original grinding image.
The method comprises the steps of acquiring an original polishing image of a target workpiece based on an image acquisition terminal in workpiece polishing equipment; inputting an original polished image into a side polished detection model, and extracting features of the original polished image through a double-layer convolution network to obtain a first feature image, wherein a server acquires the original polished image, divides the original polished image into a plurality of sub polished images, normalizes the sub polished images through a plurality of normalization modes, and obtains a reference result corresponding to each sub polished image; and obtaining a normalized feature map according to the reference result, inputting the normalized feature map into a feature fusion layer for feature fusion processing to obtain a second feature map, inputting the second feature map into a classification network, predicting a plurality of pixel points in the second feature map through the classification network, and generating a side grinding quality detection result corresponding to the original grinding image.
204. Inputting the original grinding image into an outer curved surface grinding detection model for detection to obtain an outer curved surface grinding quality detection result;
205. marking polishing defect point positions of the original polishing image according to the polishing quality detection result of the outer curved surface and the polishing quality detection result of the side surface, and obtaining polishing defect point position information;
206. determining a polishing control area of workpiece polishing equipment according to polishing defect point position information;
207. adjusting equipment polishing force parameters of the polishing control area;
the method comprises the steps of inputting an original grinding image into an outer curved surface grinding detection model to detect, obtaining an outer curved surface grinding quality detection result, marking grinding defect point positions of the original grinding image according to the outer curved surface grinding quality detection result and the side surface grinding quality detection result, obtaining grinding defect point position information, determining a grinding control area of workpiece grinding equipment according to the grinding defect point position information, classifying the grinding defect point position information by a server, marking a data sample containing a target to be detected according to the grinding defect type, preprocessing the original grinding image, converting the format, analyzing the grinding control area of the original grinding image after converting the format, outputting a reaching control area of the workpiece grinding equipment, and adjusting equipment grinding force parameters of the grinding control area.
208. And (3) adopting workpiece polishing equipment with parameters adjusted to polish the target workpiece in the next round until the target workpiece meets the preset polishing standard.
Optionally, querying a standard target workpiece image of the target workpiece from a preset database; extracting a side polishing area of the standard target workpiece image to obtain a standard side polishing area; extracting an outer curved surface polishing area of the standard target workpiece image to obtain a standard outer curved surface polishing area; and constructing a workpiece template image of the target workpiece based on the standard target workpiece image, the standard side polishing area and the standard outer curved polishing area. And extracting characteristic points from the standard target workpiece image, the standard side grinding area and the standard outer curved surface grinding area, and constructing a workpiece template image of the target workpiece according to the extracted characteristic points.
Specifically, a workpiece polishing device with adjusted parameters is adopted to polish a target workpiece for the next round, and a real-time polishing image of the target workpiece is acquired; extracting characteristic detection points in the real-time polished image; performing feature point matching on the feature detection points and the workpiece template image to obtain feature point matching results; and generating a polishing detection result corresponding to the original polishing image according to the characteristic point matching result. And judging whether the hit rate of the feature points exceeds a preset threshold, if so, generating a polishing detection result to be qualified, and if not, judging the polishing detection result to be unqualified. And generating a polishing detection result corresponding to the target workpiece according to the size of the hit rate, wherein the size threshold of the hit rate is set to be 99.9999%.
In the embodiment of the invention, a first training model is subjected to model training according to a side grinding training set to obtain a side grinding detection model, and a second training model is subjected to training according to an outer curved surface grinding training set to obtain an outer curved surface grinding detection model; acquiring an original polishing image of a target workpiece, and inputting the original polishing image into a side polishing detection model for detection to obtain a side polishing quality detection result; inputting the original grinding image into an outer curved surface grinding detection model for detection to obtain an outer curved surface grinding quality detection result; according to the detection result of the polishing quality of the outer curved surface and the detection result of the polishing quality of the side surface, the workpiece polishing equipment is subjected to equipment parameter adjustment, and the workpiece polishing equipment with the parameter adjustment is used for polishing the target workpiece in the next round.
The method for detecting the surface of the workpiece based on visual detection in the embodiment of the invention is described above, and the device for detecting the surface of the workpiece based on visual detection in the embodiment of the invention is described below, referring to fig. 3, one embodiment of the device for detecting the surface of the workpiece based on visual detection in the embodiment of the invention includes:
the labeling module 301 is configured to obtain a plurality of sample polishing images, label side polishing areas in each sample polishing image respectively to obtain a side polishing training set, and label outer curved polishing areas in each sample polishing image respectively to obtain an outer curved polishing training set;
the training module 302 is configured to perform model training on a preset first training model according to the side surface grinding training set to obtain a side surface grinding detection model, and perform training on a preset second training model according to the outer curved surface grinding training set to obtain an outer curved surface grinding detection model;
the first detection module 303 is configured to obtain an original polishing image of a target workpiece based on an image acquisition terminal in the workpiece polishing device, and input the original polishing image into the side polishing detection model for detection, so as to obtain a side polishing quality detection result;
The second detection module 304 is configured to input the original polishing image into the outer curved polishing detection model for detection, so as to obtain a polishing quality detection result of the outer curved surface;
the adjusting module 305 is configured to adjust equipment parameters of the workpiece polishing equipment according to the outer curved surface polishing quality detection result and the side polishing quality detection result;
and the processing module 306 is used for polishing the target workpiece in the next round by adopting the workpiece polishing equipment with the parameters adjusted until the target workpiece meets the preset polishing standard.
In the embodiment of the invention, a first training model is subjected to model training according to a side grinding training set to obtain a side grinding detection model, and a second training model is subjected to training according to an outer curved surface grinding training set to obtain an outer curved surface grinding detection model; acquiring an original polishing image of a target workpiece, and inputting the original polishing image into a side polishing detection model for detection to obtain a side polishing quality detection result; inputting the original grinding image into an outer curved surface grinding detection model for detection to obtain an outer curved surface grinding quality detection result; according to the detection result of the polishing quality of the outer curved surface and the detection result of the polishing quality of the side surface, the workpiece polishing equipment is subjected to equipment parameter adjustment, and the workpiece polishing equipment with the parameter adjustment is used for polishing the target workpiece in the next round.
Referring to fig. 4, another embodiment of a workpiece surface inspection apparatus based on visual inspection according to an embodiment of the present invention includes:
the labeling module 301 is configured to obtain a plurality of sample polishing images, label side polishing areas in each sample polishing image respectively to obtain a side polishing training set, and label outer curved polishing areas in each sample polishing image respectively to obtain an outer curved polishing training set;
the training module 302 is configured to perform model training on a preset first training model according to the side surface grinding training set to obtain a side surface grinding detection model, and perform training on a preset second training model according to the outer curved surface grinding training set to obtain an outer curved surface grinding detection model;
the first detection module 303 is configured to obtain an original polishing image of a target workpiece based on an image acquisition terminal in the workpiece polishing device, and input the original polishing image into the side polishing detection model for detection, so as to obtain a side polishing quality detection result;
the second detection module 304 is configured to input the original polishing image into the outer curved polishing detection model for detection, so as to obtain a polishing quality detection result of the outer curved surface;
The adjusting module 305 is configured to adjust equipment parameters of the workpiece polishing equipment according to the outer curved surface polishing quality detection result and the side polishing quality detection result;
and the processing module 306 is used for polishing the target workpiece in the next round by adopting the workpiece polishing equipment with the parameters adjusted until the target workpiece meets the preset polishing standard.
Optionally, the labeling module 301 is specifically configured to:
acquiring a plurality of sample polishing images, classifying and labeling the sample polishing images to obtain an image label of each sample polishing image;
marking the side grinding areas in each sample grinding image according to the image labels of each sample grinding image to obtain a side grinding training set;
and marking the outer curved surface polishing areas in each sample polishing image respectively to obtain an outer curved surface polishing training set.
Optionally, the training module 302 is specifically configured to:
inputting the side grinding training set into a preset first training model, wherein the first training model comprises: a double-layer convolution network, a batch normalization layer, a feature fusion layer and a classification network;
performing feature extraction and pixel point prediction on the side grinding training set through the first training model to obtain a first prediction result;
And optimizing parameters of the first training model according to the first prediction result until the first training model converges to obtain a side grinding detection model.
Optionally, the first detection module 303 is specifically configured to:
acquiring an original polishing image of a target workpiece based on an image acquisition terminal in workpiece polishing equipment;
inputting the original polished image into the side polishing detection model, and extracting features of the original polished image through the double-layer convolution network to obtain a first feature map;
inputting the first feature map into the batch normalization layer for normalization processing to obtain a normalized feature map;
inputting the normalized feature map into the feature fusion layer to perform feature fusion processing to obtain a second feature map;
and inputting the second feature map into the classification network, predicting a plurality of pixel points in the second feature map through the classification network, and generating a side grinding quality detection result corresponding to the original grinding image.
Optionally, the adjusting module 305 is specifically configured to:
marking polishing defect point positions of the original polishing image according to the polishing quality detection result of the outer curved surface and the polishing quality detection result of the side surface to obtain polishing defect point position information;
Determining a polishing control area of the workpiece polishing equipment according to the polishing defect point position information;
and adjusting the equipment polishing force parameters of the polishing control area.
Optionally, the workpiece surface detection device based on visual detection further comprises:
a construction module 307, configured to query a preset database for a standard target workpiece image of the target workpiece; extracting a side polishing area of the standard target workpiece image to obtain a standard side polishing area; extracting an outer curved surface polishing area from the standard target workpiece image to obtain a standard outer curved surface polishing area; and constructing a workpiece template image of the target workpiece based on the standard target workpiece image, the standard side polishing area and the standard outer curved polishing area.
Optionally, the processing module 306 is specifically configured to:
performing next polishing on the target workpiece by adopting workpiece polishing equipment with adjusted parameters, and collecting real-time polishing images of the target workpiece;
extracting characteristic detection points in the real-time polished image;
performing feature point matching on the feature detection points and the workpiece template image to obtain feature point matching results;
And generating a polishing detection result corresponding to the original polishing image according to the characteristic point matching result.
In the embodiment of the invention, a first training model is subjected to model training according to a side grinding training set to obtain a side grinding detection model, and a second training model is subjected to training according to an outer curved surface grinding training set to obtain an outer curved surface grinding detection model; acquiring an original polishing image of a target workpiece, and inputting the original polishing image into a side polishing detection model for detection to obtain a side polishing quality detection result; inputting the original grinding image into an outer curved surface grinding detection model for detection to obtain an outer curved surface grinding quality detection result; according to the detection result of the polishing quality of the outer curved surface and the detection result of the polishing quality of the side surface, the workpiece polishing equipment is subjected to equipment parameter adjustment, and the workpiece polishing equipment with the parameter adjustment is used for polishing the target workpiece in the next round.
The workpiece surface inspection device based on visual inspection in the embodiment of the present invention is described in detail above in terms of modularized functional entities in fig. 3 and 4, and the workpiece surface inspection apparatus based on visual inspection in the embodiment of the present invention is described in detail below in terms of hardware processing.
Fig. 5 is a schematic structural diagram of a workpiece surface inspection apparatus based on visual inspection, where the workpiece surface inspection apparatus 500 may be relatively different due to configuration or performance, and may include one or more processors (central processing units, CPU) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) storing applications 533 or data 532. Wherein memory 520 and storage medium 530 may be transitory or persistent storage. The program stored in the storage medium 530 may include one or more modules (not shown), each of which may include a series of instruction operations for the visual inspection-based workpiece surface inspection apparatus 500. Still further, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the visual inspection-based workpiece surface inspection apparatus 500.
The visual inspection-based workpiece surface inspection apparatus 500 can also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input/output interfaces 560, and/or one or more operating systems 531, such as Windows Serve, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the visual inspection-based workpiece surface inspection apparatus configuration illustrated in fig. 5 is not limiting of the visual inspection-based workpiece surface inspection apparatus and may include more or fewer components than illustrated, or may be combined with certain components, or may be arranged in a different arrangement of components.
The present invention also provides a workpiece surface inspection apparatus based on visual inspection, which includes a memory and a processor, wherein the memory stores computer readable instructions that, when executed by the processor, cause the processor to execute the steps of the workpiece surface inspection method based on visual inspection in the above embodiments.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, when the instructions are executed on a computer, cause the computer to perform the steps of the method for detecting a surface of a workpiece based on visual inspection.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created from the use of blockchain nodes, and the like.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for detecting a surface of a workpiece based on visual detection, the method comprising:
acquiring a plurality of sample polishing images, respectively marking side polishing areas in each sample polishing image to obtain a side polishing training set, and respectively marking outer curved surface polishing areas in each sample polishing image to obtain an outer curved surface polishing training set;
model training is carried out on a preset first training model according to the side grinding training set to obtain a side grinding detection model, and training is carried out on a preset second training model according to the outer curved surface grinding training set to obtain an outer curved surface grinding detection model;
Acquiring an original polishing image of a target workpiece based on an image acquisition terminal in workpiece polishing equipment, and inputting the original polishing image into the side polishing detection model for detection to obtain a side polishing quality detection result;
inputting the original grinding image into the outer curved surface grinding detection model for detection to obtain an outer curved surface grinding quality detection result;
according to the outer curved surface polishing quality detection result and the side surface polishing quality detection result, adjusting equipment parameters of the workpiece polishing equipment;
and (3) polishing the target workpiece for the next round by adopting workpiece polishing equipment with the parameters adjusted until the target workpiece meets the preset polishing standard.
2. The method for detecting the surface of the workpiece based on visual detection according to claim 1, wherein the steps of obtaining a plurality of sample polishing images, respectively labeling side polishing areas in each sample polishing image to obtain a side polishing training set, respectively labeling outer curved polishing areas in each sample polishing image to obtain an outer curved polishing training set, comprise:
acquiring a plurality of sample polishing images, classifying and labeling the sample polishing images to obtain an image label of each sample polishing image;
Marking the side grinding areas in each sample grinding image according to the image labels of each sample grinding image to obtain a side grinding training set;
and marking the outer curved surface polishing areas in each sample polishing image respectively to obtain an outer curved surface polishing training set.
3. The method for detecting the surface of the workpiece based on visual detection according to claim 1, wherein the model training is performed on a preset first training model according to the side grinding training set to obtain a side grinding detection model, and the method comprises the following steps:
inputting the side grinding training set into a preset first training model, wherein the first training model comprises: a double-layer convolution network, a batch normalization layer, a feature fusion layer and a classification network;
performing feature extraction and pixel point prediction on the side grinding training set through the first training model to obtain a first prediction result;
and optimizing parameters of the first training model according to the first prediction result until the first training model converges to obtain a side grinding detection model.
4. The visual inspection-based workpiece surface inspection method as claimed in claim 3, wherein the acquiring an original grinding image of a target workpiece based on an image acquisition terminal in a workpiece grinding device, and inputting the original grinding image into the side grinding inspection model for inspection, to obtain a side grinding quality inspection result, comprises:
Acquiring an original polishing image of a target workpiece based on an image acquisition terminal in workpiece polishing equipment;
inputting the original polished image into the side polishing detection model, and extracting features of the original polished image through the double-layer convolution network to obtain a first feature map;
inputting the first feature map into the batch normalization layer for normalization processing to obtain a normalized feature map;
inputting the normalized feature map into the feature fusion layer to perform feature fusion processing to obtain a second feature map;
and inputting the second feature map into the classification network, predicting a plurality of pixel points in the second feature map through the classification network, and generating a side grinding quality detection result corresponding to the original grinding image.
5. The visual inspection-based workpiece surface inspection method according to claim 1, wherein the performing equipment parameter adjustment on the workpiece polishing equipment according to the outer curved polishing quality inspection result and the side polishing quality inspection result comprises:
marking polishing defect point positions of the original polishing image according to the polishing quality detection result of the outer curved surface and the polishing quality detection result of the side surface to obtain polishing defect point position information;
Determining a polishing control area of the workpiece polishing equipment according to the polishing defect point position information;
and adjusting the equipment polishing force parameters of the polishing control area.
6. The visual inspection-based workpiece surface inspection method of claim 1, further comprising:
inquiring a standard target workpiece image of the target workpiece from a preset database;
extracting a side polishing area of the standard target workpiece image to obtain a standard side polishing area;
extracting an outer curved surface polishing area from the standard target workpiece image to obtain a standard outer curved surface polishing area;
and constructing a workpiece template image of the target workpiece based on the standard target workpiece image, the standard side polishing area and the standard outer curved polishing area.
7. The visual inspection-based workpiece surface inspection method according to claim 6, wherein the performing the next polishing of the target workpiece by using the workpiece polishing device after the parameter adjustment until the target workpiece meets a preset polishing standard comprises:
performing next polishing on the target workpiece by adopting workpiece polishing equipment with adjusted parameters, and collecting real-time polishing images of the target workpiece;
Extracting characteristic detection points in the real-time polished image;
performing feature point matching on the feature detection points and the workpiece template image to obtain feature point matching results;
and generating a polishing detection result corresponding to the original polishing image according to the characteristic point matching result.
8. A workpiece surface inspection device based on visual inspection, the workpiece surface inspection device based on visual inspection comprising:
the labeling module is used for acquiring a plurality of sample polishing images, labeling side polishing areas in each sample polishing image respectively to obtain a side polishing training set, and labeling outer curved surface polishing areas in each sample polishing image respectively to obtain an outer curved surface polishing training set;
the training module is used for carrying out model training on a preset first training model according to the side surface grinding training set to obtain a side surface grinding detection model, and carrying out training on a preset second training model according to the outer curved surface grinding training set to obtain an outer curved surface grinding detection model;
the first detection module is used for acquiring an original polishing image of a target workpiece based on an image acquisition terminal in workpiece polishing equipment, inputting the original polishing image into the side polishing detection model for detection, and obtaining a side polishing quality detection result;
The second detection module is used for inputting the original grinding image into the outer curved surface grinding detection model for detection to obtain an outer curved surface grinding quality detection result;
the adjusting module is used for adjusting equipment parameters of the workpiece polishing equipment according to the outer curved surface polishing quality detection result and the side surface polishing quality detection result;
and the processing module is used for polishing the target workpiece in the next round by adopting the workpiece polishing equipment with the parameters adjusted until the target workpiece meets the preset polishing standard.
9. A workpiece surface inspection apparatus based on visual inspection, the workpiece surface inspection apparatus based on visual inspection comprising: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the vision-based workpiece surface inspection apparatus to perform the vision-based workpiece surface inspection method of any of claims 1-7.
10. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the visual inspection-based workpiece surface inspection method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310192847.3A CN116071348B (en) | 2023-03-02 | 2023-03-02 | Workpiece surface detection method and related device based on visual detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310192847.3A CN116071348B (en) | 2023-03-02 | 2023-03-02 | Workpiece surface detection method and related device based on visual detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116071348A true CN116071348A (en) | 2023-05-05 |
| CN116071348B CN116071348B (en) | 2023-06-13 |
Family
ID=86176911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310192847.3A Active CN116071348B (en) | 2023-03-02 | 2023-03-02 | Workpiece surface detection method and related device based on visual detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116071348B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116883417A (en) * | 2023-09-08 | 2023-10-13 | 武汉东方骏驰精密制造有限公司 | Workpiece quality inspection method and device based on machine vision |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200033842A1 (en) * | 2018-07-25 | 2020-01-30 | Jtekt Corporation | Grinding quality estimation model generating device, grinding quality estimating device, poor quality factor estimating device, grinding machine operation command data adjustment model generating device, and grinding machine operation command data updating device |
| CN112348787A (en) * | 2020-11-03 | 2021-02-09 | 中科创达软件股份有限公司 | Training method of object defect detection model, object defect detection method and device |
| CN112712033A (en) * | 2020-12-30 | 2021-04-27 | 哈尔滨工业大学 | Automatic division method for catchment areas of municipal drainage pipe network |
| CN112862763A (en) * | 2021-01-25 | 2021-05-28 | 中国石油天然气集团有限公司 | System and method for detecting heat treatment state of high-steel-grade thick-wall pipe fitting based on deep learning |
| CN114083358A (en) * | 2022-01-19 | 2022-02-25 | 河北工业大学 | Industrial robot polishing process optimization method |
| CN114705685A (en) * | 2022-01-30 | 2022-07-05 | 中信云网有限公司 | AI visual detection method and system based on deep learning and readable storage medium |
| WO2022156061A1 (en) * | 2021-01-22 | 2022-07-28 | 平安科技（深圳）有限公司 | Image model training method and apparatus, electronic device, and storage medium |
| CN114943733A (en) * | 2022-07-20 | 2022-08-26 | 张家港华程机车精密制管有限公司 | Steel pipe polishing quality assessment method and system |
| CN115331224A (en) * | 2022-10-17 | 2022-11-11 | 日照福瑞德科技有限公司 | Glass lens polishing quality analysis optimization method and system |
-
2023
- 2023-03-02 CN CN202310192847.3A patent/CN116071348B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200033842A1 (en) * | 2018-07-25 | 2020-01-30 | Jtekt Corporation | Grinding quality estimation model generating device, grinding quality estimating device, poor quality factor estimating device, grinding machine operation command data adjustment model generating device, and grinding machine operation command data updating device |
| CN112348787A (en) * | 2020-11-03 | 2021-02-09 | 中科创达软件股份有限公司 | Training method of object defect detection model, object defect detection method and device |
| CN112712033A (en) * | 2020-12-30 | 2021-04-27 | 哈尔滨工业大学 | Automatic division method for catchment areas of municipal drainage pipe network |
| WO2022156061A1 (en) * | 2021-01-22 | 2022-07-28 | 平安科技（深圳）有限公司 | Image model training method and apparatus, electronic device, and storage medium |
| CN112862763A (en) * | 2021-01-25 | 2021-05-28 | 中国石油天然气集团有限公司 | System and method for detecting heat treatment state of high-steel-grade thick-wall pipe fitting based on deep learning |
| CN114083358A (en) * | 2022-01-19 | 2022-02-25 | 河北工业大学 | Industrial robot polishing process optimization method |
| CN114705685A (en) * | 2022-01-30 | 2022-07-05 | 中信云网有限公司 | AI visual detection method and system based on deep learning and readable storage medium |
| CN114943733A (en) * | 2022-07-20 | 2022-08-26 | 张家港华程机车精密制管有限公司 | Steel pipe polishing quality assessment method and system |
| CN115331224A (en) * | 2022-10-17 | 2022-11-11 | 日照福瑞德科技有限公司 | Glass lens polishing quality analysis optimization method and system |
Non-Patent Citations (1)
| Title |
|---|
| 周良明 等: "飞机结构件内腔机器人自动打磨工艺", 《科学技术与工程》, vol. 19, no. 36, pages 128 - 133 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116883417A (en) * | 2023-09-08 | 2023-10-13 | 武汉东方骏驰精密制造有限公司 | Workpiece quality inspection method and device based on machine vision |
| CN116883417B (en) * | 2023-09-08 | 2023-12-05 | 武汉东方骏驰精密制造有限公司 | Workpiece quality inspection method and device based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116071348B (en) | 2023-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110569878B (en) | Photograph background similarity clustering method based on convolutional neural network and computer | |
| Yogesh et al. | Computer vision based analysis and detection of defects in fruits causes due to nutrients deficiency | |
| CN114862845B (en) | Defect detection method, device and equipment for mobile phone touch screen and storage medium | |
| CN105184225B (en) | A kind of multinational banknote image recognition methods and device | |
| US10679094B2 (en) | Automatic ruler detection | |
| CN116071348B (en) | Workpiece surface detection method and related device based on visual detection | |
| CN110569856A (en) | sample labeling method and device, and damage category identification method and device | |
| CN102982305A (en) | Information processing apparatus and method of processing information, storage medium and program | |
| WO2015146113A1 (en) | Identification dictionary learning system, identification dictionary learning method, and recording medium | |
| CN117392042A (en) | Defect detection method, defect detection apparatus, and storage medium | |
| CN110991434B (en) | Self-service terminal certificate identification method and device | |
| CN117809124B (en) | Medical image association calling method and system based on multi-feature fusion | |
| CN114863129A (en) | Instrument numerical analysis method, device, equipment and storage medium | |
| CN116797553A (en) | Image processing method, device, equipment and storage medium | |
| CN109711287B (en) | Face acquisition method and related product | |
| CN116824337A (en) | Method and system for generating roughness prediction model based on feature transfer learning | |
| CN111325734A (en) | Bone age prediction method and device based on visual model | |
| CN112668365A (en) | Material warehousing identification method, device, equipment and storage medium | |
| CN203970354U (en) | A kind of Tongue analytical system based on mobile terminal | |
| CN109190489A (en) | A kind of abnormal face detecting method based on reparation autocoder residual error | |
| CN113506266A (en) | Method, device and equipment for detecting tongue greasy coating and storage medium | |
| CN110942081B (en) | Image processing method, device, electronic equipment and readable storage medium | |
| CN113627442A (en) | Medical information input method, device, equipment and storage medium | |
| CN111951287A (en) | Two-dimensional code detection and recognition method | |
| CN110990774A (en) | Community garbage classification identification method, device, equipment and 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 |