CN116167970A - Sand mold detection system and detection method - Google Patents
Sand mold detection system and detection method Download PDFInfo
- Publication number
- CN116167970A CN116167970A CN202211627197.2A CN202211627197A CN116167970A CN 116167970 A CN116167970 A CN 116167970A CN 202211627197 A CN202211627197 A CN 202211627197A CN 116167970 A CN116167970 A CN 116167970A
- Authority
- CN
- China
- Prior art keywords
- image
- sand mold
- current
- sand
- standard
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000004576 sand Substances 0.000 title claims abstract description 215
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 230000007547 defect Effects 0.000 claims abstract description 74
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000004891 communication Methods 0.000 claims description 21
- 230000011218 segmentation Effects 0.000 claims description 18
- 238000009826 distribution Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 12
- 238000005266 casting Methods 0.000 abstract description 8
- 230000000007 visual effect Effects 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 239000000853 adhesive Substances 0.000 description 1
- 230000001070 adhesive effect Effects 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000007528 sand casting Methods 0.000 description 1
- 238000007790 scraping Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- 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
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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]
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of sand molds, in particular to a sand mold detection system and a sand mold detection method, which solve the problems that the prior art adopts a traditional manual visual detection method to easily generate a plurality of false detection, omission detection and low efficiency phenomena, and the precision of each part of the sand mold is difficult to detect, so that the rejection rate of blank products obtained by casting the sand mold is high. The sand mold detection system comprises the steps of obtaining a current sand mold image to be detected, determining a sand mold model of the current sand mold image through a template matching method, and obtaining a standard sand mold image of the sand mold model; and respectively detecting the strip-shaped air holes and the round air holes of the current sand mold image and the standard sand mold image, and calculating the center point of the air holes. The invention ensures the product quality, improves the production efficiency and greatly reduces the rejection rate of cast blank products. And the defect data is stored in real time for the factory to improve the production process in time.
Description
Technical Field
The invention relates to the technical field of sand molds, in particular to a sand mold detection system and a sand mold detection method.
Background
The sand mould is a casting cavity made of raw sand, adhesive and other auxiliary materials in the casting production process; sand casting is a method for producing castings in sand molds, which is the most widely used casting method in practical production, and is suitable for producing various shapes, sizes, batches and various common alloy castings; the defect in the sand mould used for casting production is accurately detected, and the rejection rate of products can be greatly reduced.
Common sand mould defects include scraping, template sand-sticking and sand-blocking dropping, and in the process of manufacturing the sand mould, because the sand mould is complex in structure and large in area, accurate and rapid judgment is difficult to be carried out on all defects, especially small-size defects, by means of human eyes, a plurality of false detection, omission detection and inefficiency phenomena are easy to occur by using a traditional manual visual detection method, and the precision of each part of the sand mould is difficult to detect, so that the rejection rate of blank products obtained by casting the sand mould is high.
Disclosure of Invention
The invention aims to provide a sand mold detection system and a sand mold detection method, which are used for detecting sand mold defects in real time through image acquisition and image processing technology so as to improve the qualification rate of sand mold production.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the sand mold detection system comprises the steps of obtaining a current sand mold image to be detected, determining a sand mold type of the current sand mold image through a template matching method, and obtaining a standard sand mold image of the sand mold type; respectively detecting strip-shaped air holes and round air holes of a current sand mold image and a standard sand mold image, and calculating an air hole center point; aligning the two sand mold images based on the center point of the air hole; the two aligned sand mould images are respectively divided into a plurality of block areas with set sizes, the block areas of the current sand mould image are in one-to-one correspondence with the block areas of the standard sand mould image, and then an image block sequence of the current sand mould image and the standard sand mould image is obtained; calculating texture characteristics of each image block; comparing the similarity between the texture features of the image blocks at the corresponding positions in the current sand mold image and the standard sand mold image, and judging whether the current image block has defects or not; based on all the image blocks with defects, combining the defect segmentation model to obtain the type, the size and the position of each defect in the sand mold to be detected:
the light source is arranged when the lighting module provides detection, the lighting module is driven to move, adjust and rotate through the moving module and the control module, and meanwhile, the lighting module can be driven to adjust the brightness.
Preferably, the method for determining the sand mold type of the current sand mold image by a template matching method specifically comprises the following steps:
and performing similarity matching on the sand mold image to be detected and standard sand mold images of different models in a database, and taking the model of the standard sand mold image with the highest similarity with the current sand mold image as the sand mold model of the current sand mold image.
Preferably, the strip-shaped air holes and the round air holes for respectively detecting the current sand mold image and the standard sand mold image specifically comprise:
for the current sand mould image or the standard sand mould image, respectively dividing the sand mould image by using a series of continuous thresholds to obtain a series of binary images;
extracting all connected areas consisting of zero pixel points in each binary image, and calculating the center and the area of the connected areas;
screening out a strip-shaped communication region by limiting the aspect ratio and the area of the smallest circumscribed rectangle of the communication region, and screening out a circular communication region by limiting the roundness and the area of the communication region;
clustering the strip-shaped communication areas and the round communication areas with center coordinate spacing smaller than a first set threshold and area difference smaller than a second set threshold, and taking out the communication area with the largest area in each type, namely the strip-shaped air holes and the round air holes of the current sand mold image or the standard sand mold image.
Preferably, the method is characterized in that the two sand mould images are aligned based on the center point of the air hole, and specifically comprises the following steps:
calculating offset distances of the center points of the corresponding air holes of the current sand mold image and the standard sand mold image, and aligning the two sand mold images in sequence from the vertical direction and the horizontal direction according to the offset distances.
Preferably, the calculating the texture feature of each image block specifically includes:
carrying out Gaussian filtering on the image block and dividing the image block into a plurality of square areas with set sizes;
calculating the LBP value of each pixel in each square area to obtain an LBP distribution histogram of each square area, and carrying out normalization processing on the histogram;
the LBP distribution histogram of the whole square area of the image block is connected into a vector, and the vector is the LBP texture characteristic vector of the image block.
Preferably, the method is characterized by comparing the similarity between texture features of the image blocks at corresponding positions in the current sand mold image and the standard sand mold image, and specifically comprises the following steps:
and calculating the Euclidean distance between the texture features of the two image blocks, and if the Euclidean distance is larger than a set fourth threshold value, considering that the current image block has defects.
Preferably, the method is characterized in that based on all the image blocks with defects, combining a defect segmentation model to obtain the type, the size and the position of each defect in the sand mold to be detected, and specifically comprises the following steps:
combining adjacent image blocks with defects at the same time to obtain an image block sequence with defects in the current sand mold image;
inputting an image block with defects into a defect segmentation model, outputting the type of each pixel in the image block, and counting pixels belonging to the same defect type to obtain the defect type, size and position contained in the current image block;
wherein the defect segmentation model uses a multi-layer deep convolution network.
Sand mold detecting system and detecting system, characterized by comprising:
the image acquisition module is used for acquiring a current sand mold image to be detected, determining the sand mold type of the current sand mold image through a template matching method, and acquiring a standard sand mold image of the sand mold type;
the image alignment module is used for respectively detecting the strip-shaped air holes and the round air holes of the current sand mold image and the standard sand mold image and calculating the center point of the air holes; aligning the two sand mold images based on the center point of the air hole;
the defect identification module is used for dividing the two aligned sand mould images into a plurality of block areas with set sizes respectively, wherein the block areas of the current sand mould image correspond to the block areas of the standard sand mould image one by one, so that an image block sequence of the current sand mould image and the standard sand mould image is obtained; calculating texture characteristics of each image block; comparing the similarity between the texture features of the image blocks at the corresponding positions in the current sand mold image and the standard sand mold image, and judging whether the current image block has defects or not;
the defect segmentation module is used for obtaining the type, the size and the position of each defect in the sand mold to be detected based on all the image blocks with the defects and combining the defect segmentation model.
The invention has at least the following beneficial effects:
according to the invention, the current sand mould image is aligned with the standard sand mould image, the image blocks are segmented, whether each image block has defects or not is respectively judged, and then the defective image blocks are subjected to a neural network model, so that accurate and refined detection of all sand mould defect types is realized, the labor is saved, the cost is reduced, the detection accuracy is improved, the product quality is ensured, the production efficiency is improved, and the rejection rate of cast blank products is greatly reduced. And the defect data is stored in real time for the factory to improve the production process in time.
The invention also has the following beneficial effects:
additional features and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the structure of the present invention;
FIG. 2 is a flow chart of the air hole detection algorithm of the present invention;
FIG. 3 is a flow chart of the sand mold texture feature extraction algorithm of the invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Example 1
1-3, a sand mold detection system and a detection method thereof comprise the steps of obtaining a current sand mold image to be detected, determining a sand mold type of the current sand mold image through a template matching method, and obtaining a standard sand mold image of the sand mold type; respectively detecting strip-shaped air holes and round air holes of a current sand mold image and a standard sand mold image, and calculating an air hole center point; aligning the two sand mold images based on the center point of the air hole; the two aligned sand mould images are respectively divided into a plurality of block areas with set sizes, the block areas of the current sand mould image are in one-to-one correspondence with the block areas of the standard sand mould image, and then an image block sequence of the current sand mould image and the standard sand mould image is obtained; calculating texture characteristics of each image block; comparing the similarity between the texture features of the image blocks at the corresponding positions in the current sand mold image and the standard sand mold image, and judging whether the current image block has defects or not; based on all the image blocks with defects, combining the defect segmentation model to obtain the type, the size and the position of each defect in the sand mold to be detected:
the light source is arranged when the lighting module provides detection, the lighting module is driven to move, adjust and rotate through the moving module and the control module, and meanwhile, the lighting module can be driven to adjust the brightness.
As can be seen from the above embodiments: according to the invention, the current sand mould image is aligned with the standard sand mould image, the image blocks are segmented, whether each image block has defects or not is respectively judged, and then the defective image blocks are subjected to a neural network model, so that accurate and refined detection of all sand mould defect types is realized, the labor is saved, the cost is reduced, the detection accuracy is improved, the product quality is ensured, the production efficiency is improved, and the rejection rate of cast blank products is greatly reduced. And the defect data is stored in real time for the factory to improve the production process in time.
Example two
Referring to fig. 1-3, determining a sand mold model of a current sand mold image by a template matching method specifically includes: matching the similarity between the sand mould image to be detected and standard sand mould images of different models in a database, taking the model of the standard sand mould image with the highest similarity with the current sand mould image as the sand mould model of the current sand mould image, and respectively detecting strip-shaped air holes and circular air holes of the current sand mould image and the standard sand mould image, wherein the method specifically comprises the following steps of:
for the current sand mould image or the standard sand mould image, respectively dividing the sand mould image by using a series of continuous thresholds to obtain a series of binary images;
extracting all connected areas consisting of zero pixel points in each binary image, and calculating the center and the area of the connected areas;
screening out a strip-shaped communication region by limiting the aspect ratio and the area of the smallest circumscribed rectangle of the communication region, and screening out a circular communication region by limiting the roundness and the area of the communication region;
clustering the strip-shaped communication areas and the round communication areas with center coordinate spacing smaller than a set first threshold and area difference smaller than a set second threshold respectively, and taking out the communication area with the largest area in each category, namely the strip-shaped air holes and the round air holes of the current sand mold image or the standard sand mold image, wherein the alignment of the two sand mold images is carried out based on the center point of the air holes, and the method specifically comprises the following steps:
calculating the offset distance between the center points of the corresponding air holes of the current sand mold image and the standard sand mold image, and sequentially aligning the two sand mold images from the vertical direction and the horizontal direction according to the offset distance, wherein the calculating the texture feature of each image block specifically comprises the following steps:
carrying out Gaussian filtering on the image block and dividing the image block into a plurality of square areas with set sizes;
calculating the LBP value of each pixel in each square area to obtain an LBP distribution histogram of each square area, and carrying out normalization processing on the histogram;
connecting LBP distribution histograms of all square areas of the image block into a vector, wherein the vector is an LBP texture feature vector of the image block, and the method is characterized by comparing the similarity between texture features of the image block at the corresponding position in the current sand mold image and the standard sand mold image, and specifically comprises the following steps:
the method is characterized in that based on all image blocks with defects, a defect segmentation model is combined to obtain the type, the size and the position of each defect in a sand mold to be detected, and the method specifically comprises the following steps:
combining adjacent image blocks with defects at the same time to obtain an image block sequence with defects in the current sand mold image;
inputting an image block with defects into a defect segmentation model, outputting the type of each pixel in the image block, and counting pixels belonging to the same defect type to obtain the defect type, size and position contained in the current image block;
wherein the defect segmentation model uses a multi-layer deep convolution network.
The system comprises a sand mold detection system and a detection system, wherein an image acquisition module is used for acquiring a current sand mold image to be detected, determining a sand mold type of the current sand mold image through a template matching method, and acquiring a standard sand mold image of the sand mold type;
the image alignment module is used for respectively detecting the strip-shaped air holes and the round air holes of the current sand mold image and the standard sand mold image and calculating the center point of the air holes; aligning the two sand mold images based on the center point of the air hole;
the defect identification module is used for dividing the two aligned sand mould images into a plurality of block areas with set sizes respectively, wherein the block areas of the current sand mould image correspond to the block areas of the standard sand mould image one by one, so that an image block sequence of the current sand mould image and the standard sand mould image is obtained; calculating texture characteristics of each image block; comparing the similarity between the texture features of the image blocks at the corresponding positions in the current sand mold image and the standard sand mold image, and judging whether the current image block has defects or not;
the defect segmentation module is used for obtaining the type, the size and the position of each defect in the sand mold to be detected based on all the image blocks with the defects and combining the defect segmentation model.
As can be seen from the above embodiments: additional features and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention, which is defined by the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. The sand mold detection method is characterized by comprising the following steps of:
acquiring a current sand mold image to be detected, determining a sand mold type of the current sand mold image by a template matching method, and acquiring a standard sand mold image of the sand mold type; respectively detecting strip-shaped air holes and round air holes of a current sand mold image and a standard sand mold image, and calculating an air hole center point; aligning the two sand mold images based on the center point of the air hole; the two aligned sand mould images are respectively divided into a plurality of block areas with set sizes, the block areas of the current sand mould image are in one-to-one correspondence with the block areas of the standard sand mould image, and then an image block sequence of the current sand mould image and the standard sand mould image is obtained; calculating texture characteristics of each image block; comparing the similarity between the texture features of the image blocks at the corresponding positions in the current sand mold image and the standard sand mold image, and judging whether the current image block has defects or not; based on all the image blocks with defects, combining the defect segmentation model to obtain the type, size and position of each defect in the sand mold to be detected;
the light source is arranged when the lighting module provides detection, the lighting module is driven to move, adjust and rotate through the moving module and the control module, and meanwhile, the lighting module can be driven to adjust the brightness.
2. The sand mold detection method according to claim 1, wherein the sand mold type of the current sand mold image is determined by a template matching method, and specifically comprises:
and performing similarity matching on the sand mold image to be detected and standard sand mold images of different models in a database, and taking the model of the standard sand mold image with the highest similarity with the current sand mold image as the sand mold model of the current sand mold image.
3. The sand mold detection method according to claim 1, wherein the strip-shaped air holes and the round air holes of the current sand mold image and the standard sand mold image are detected respectively, specifically comprising:
for the current sand mould image or the standard sand mould image, respectively dividing the sand mould image by using a series of continuous thresholds to obtain a series of binary images;
extracting all connected areas consisting of zero pixel points in each binary image, and calculating the center and the area of the connected areas;
screening out a strip-shaped communication region by limiting the aspect ratio and the area of the smallest circumscribed rectangle of the communication region, and screening out a circular communication region by limiting the roundness and the area of the communication region;
clustering the strip-shaped communication areas and the round communication areas with center coordinate spacing smaller than a first set threshold and area difference smaller than a second set threshold, and taking out the communication area with the largest area in each type, namely the strip-shaped air holes and the round air holes of the current sand mold image or the standard sand mold image.
4. The sand mold detection method according to claim 1, wherein the two sand mold images are aligned based on the center point of the air hole, specifically comprising:
calculating offset distances of the center points of the corresponding air holes of the current sand mold image and the standard sand mold image, and aligning the two sand mold images in sequence from the vertical direction and the horizontal direction according to the offset distances.
5. A sand mould inspection method according to claim 1, characterized in that the calculation of the texture characteristics of each image block comprises:
carrying out Gaussian filtering on the image block and dividing the image block into a plurality of square areas with set sizes;
calculating the LBP value of each pixel in each square area to obtain an LBP distribution histogram of each square area, and carrying out normalization processing on the histogram;
the LBP distribution histogram of the whole square area of the image block is connected into a vector, and the vector is the LBP texture characteristic vector of the image block.
6. The sand mold detection method according to claim 1, wherein the comparing of the similarity between the texture features of the image blocks at the corresponding positions in the current sand mold image and the standard sand mold image specifically comprises:
and calculating the Euclidean distance between the texture features of the two image blocks, and if the Euclidean distance is larger than a set fourth threshold value, considering that the current image block has defects.
7. The sand mold detection method according to claim 1, wherein the type, the size and the position of each defect in the sand mold to be detected are obtained by combining a defect segmentation model based on all the image blocks with defects, specifically comprising:
combining adjacent image blocks with defects at the same time to obtain an image block sequence with defects in the current sand mold image;
inputting an image block with defects into a defect segmentation model, outputting the type of each pixel in the image block, and counting pixels belonging to the same defect type to obtain the defect type, size and position contained in the current image block;
wherein the defect segmentation model uses a multi-layer deep convolution network.
8. A sand mold detection system, comprising:
the image acquisition module is used for acquiring a current sand mold image to be detected, determining the sand mold type of the current sand mold image through a template matching method, and acquiring a standard sand mold image of the sand mold type;
the image alignment module is used for respectively detecting the strip-shaped air holes and the round air holes of the current sand mold image and the standard sand mold image and calculating the center point of the air holes; aligning the two sand mold images based on the center point of the air hole;
the defect identification module is used for dividing the two aligned sand mould images into a plurality of block areas with set sizes respectively, wherein the block areas of the current sand mould image correspond to the block areas of the standard sand mould image one by one, so that an image block sequence of the current sand mould image and the standard sand mould image is obtained; calculating texture characteristics of each image block; comparing the similarity between the texture features of the image blocks at the corresponding positions in the current sand mold image and the standard sand mold image, and judging whether the current image block has defects or not;
the defect segmentation module is used for obtaining the type, the size and the position of each defect in the sand mold to be detected based on all the image blocks with the defects and combining the defect segmentation model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211627197.2A CN116167970A (en) | 2022-12-16 | 2022-12-16 | Sand mold detection system and detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211627197.2A CN116167970A (en) | 2022-12-16 | 2022-12-16 | Sand mold detection system and detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116167970A true CN116167970A (en) | 2023-05-26 |
Family
ID=86415471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211627197.2A Pending CN116167970A (en) | 2022-12-16 | 2022-12-16 | Sand mold detection system and detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116167970A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116402809A (en) * | 2023-05-31 | 2023-07-07 | 华中科技大学 | Defect identification method and device in three-dimensional sand mould printing and sanding process |
-
2022
- 2022-12-16 CN CN202211627197.2A patent/CN116167970A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116402809A (en) * | 2023-05-31 | 2023-07-07 | 华中科技大学 | Defect identification method and device in three-dimensional sand mould printing and sanding process |
| CN116402809B (en) * | 2023-05-31 | 2023-08-11 | 华中科技大学 | Defect identification method and device in three-dimensional sand mould printing and sanding process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109961049B (en) | Cigarette brand identification method under complex scene | |
| CN108982508B (en) | Plastic package IC chip defect detection method based on feature template matching and deep learning | |
| CN111223088B (en) | Casting surface defect identification method based on deep convolutional neural network | |
| CN114972356B (en) | Plastic product surface defect detection and identification method and system | |
| CN114387233A (en) | Sand mold defect detection method and system based on machine vision | |
| CN108985337A (en) | A kind of product surface scratch detection method based on picture depth study | |
| CN106919910B (en) | Traffic sign identification method based on HOG-CTH combined features | |
| CN109816648A (en) | Complicated injection-molded item overlap defect identification method based on multi-template low-rank decomposition | |
| CN111539330B (en) | Transformer substation digital display instrument identification method based on double-SVM multi-classifier | |
| CN113256624A (en) | Continuous casting round billet defect detection method and device, electronic equipment and readable storage medium | |
| CN114926410A (en) | Method for detecting appearance defects of brake disc | |
| CN114022483B (en) | Injection molding flash area identification method based on edge characteristics | |
| CN116167970A (en) | Sand mold detection system and detection method | |
| CN111709934B (en) | Injection molding impeller warping defect detection method based on point cloud characteristic comparison | |
| CN114820625A (en) | Automobile top block defect detection method | |
| CN114119603A (en) | Image processing-based snack box short shot defect detection method | |
| CN108073940A (en) | A kind of method of 3D object instance object detections in unstructured moving grids | |
| CN116309577A (en) | Intelligent detection method and system for high-strength conveyor belt materials | |
| CN112967271A (en) | Casting surface defect identification method based on improved DeepLabv3+ network model | |
| CN113516123A (en) | Detection and identification method for tire embossed characters | |
| CN112784922A (en) | Extraction and classification method of intelligent cloud medical images | |
| CN111231253A (en) | Injection molding safety production system based on machine vision | |
| CN111507404A (en) | Hub model identification method based on deep vision | |
| CN114445483B (en) | Injection molding part quality analysis method based on image pyramid | |
| CN114937015A (en) | Intelligent visual identification method and system in lithium battery pole piece manufacturing |
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 |