CN111062391B - Magnetic sheet initial positioning method - Google Patents
Magnetic sheet initial positioning method Download PDFInfo
- Publication number
- CN111062391B CN111062391B CN201911352934.0A CN201911352934A CN111062391B CN 111062391 B CN111062391 B CN 111062391B CN 201911352934 A CN201911352934 A CN 201911352934A CN 111062391 B CN111062391 B CN 111062391B
- Authority
- CN
- China
- Prior art keywords
- magnetic sheet
- pixel
- image
- label
- pixel point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a magnetic sheet initial positioning method, which comprises the following steps: step S1, inputting a magnetic sheet image into a segmentation neural network for image feature extraction to obtain a segmentation map corresponding to the magnetic sheet image; step S2, according to the real region of the magnetic sheet region on the magnetic sheet image, a first pixel label is given to each pixel point in the magnetic sheet region on the magnetic sheet image, and a second pixel label is given to each pixel point in the non-magnetic sheet region on the magnetic sheet image; step S3, calculating cross entropy loss of the segmentation neural network output segmentation map in the step S1 according to the label endowing result in the step S2; step S4, according to the cross entropy loss calculated in the step S3, training parameters of a segmentation model for identifying the magnetic sheet image are adjusted; and S5, updating and training the segmentation model according to the adjusted training parameters to obtain an updated segmentation model.
Description
Technical Field
The application relates to the technical field of image recognition, in particular to a magnetic sheet initial positioning method for positioning and detecting a magnetic sheet area in a magnetic sheet image.
Background
In the field of magnetic sheet defect detection application, it is necessary to identify the region of the magnetic sheet from the magnetic sheet image (the magnetic sheet image includes other images of non-magnetic sheet regions, such as background images), then cut the magnetic sheet region from the magnetic sheet image, and then perform further defect analysis.
The existing magnetic sheet area detection method mainly comprises the following two methods:
1. the position of the magnetic sheet in the magnetic sheet image is judged based on the conventional computer image recognition technology. This method has a disadvantage of slow recognition speed. And when the identification scene is replaced, the identification rule needs to be changed, the identification process is tedious and inconvenient, and the false detection rate is higher.
2. The recognition algorithm based on the deep learning performs pixel-level segmentation on the magnetic sheet region. This method has disadvantages in that when a plurality of magnetic sheet regions exist in a magnetic sheet image or when the intervals between the plurality of magnetic sheet regions are small, it is difficult to effectively distinguish each magnetic sheet region, and when the magnetic sheet region is incomplete, abnormality of the magnetic sheet region cannot be detected.
Disclosure of Invention
The application aims to provide a magnetic sheet initial positioning method for solving the technical problems.
To achieve the purpose, the application adopts the following technical scheme:
the method for initially positioning the magnetic sheet is used for positioning and detecting the magnetic sheet area in the magnetic sheet image and comprises the following steps:
step S1, inputting a magnetic sheet image into a segmentation neural network for image feature extraction, and obtaining a segmentation map corresponding to the magnetic sheet image, wherein the segmentation map displays suspected areas of the magnetic sheet areas in the magnetic sheet image;
step S2, according to the real region of the magnetic sheet region on the magnetic sheet image, a first pixel label is given to each pixel point in the magnetic sheet region on the magnetic sheet image, and a second pixel label is given to each pixel point in the non-magnetic sheet region on the magnetic sheet image;
step S3, calculating the cross entropy loss of the segmentation neural network output segmentation map in the step S1 according to the label endowing result of the step S2;
step S4, according to the cross entropy loss calculated in the step S3, training parameters of a segmentation model for identifying the magnetic sheet image are adjusted;
and S5, updating and training the segmentation model according to the adjusted training parameters to obtain the updated segmentation model, wherein the segmentation model is used for identifying the magnetic sheet region on the magnetic sheet image.
In a preferred embodiment of the present application, in the step S2, the first pixel label is a first pixel value corresponding to each pixel point in the magnetic sheet area on the magnetic sheet image, and the first pixel value is assigned to be 1;
and the second pixel label is a second pixel value corresponding to each pixel point in the non-magnetic sheet area on the magnetic sheet image, and the second pixel value is assigned to be 0.
In a preferred embodiment of the present application, in the step S2, labeling is further performed on each pixel point on an area edge line of the magnetic sheet area on the magnetic sheet image, a line width of the area edge line is 5 pixels, and a pixel value corresponding to each pixel point on the area edge line is assigned to 1.
As a preferred solution of the present application, in the step S2, the method further includes labeling each pixel point on the magnetic sheet corner point of the magnetic sheet region on the magnetic sheet image, and labeling each pixel point on the magnetic sheet corner point specifically includes the following steps:
step L1, establishing a circle at each magnetic sheet angular point position, and endowing a third pixel label to the center of the circle, wherein the pixel value corresponding to the third pixel label is M, and the radius of the circle is a fixed reduction multiple P of the magnetic sheet length L;
and step L2, calculating a label pixel value corresponding to each pixel point in the circle range according to the pixel value M corresponding to the circle center determined in the step L1 and the position distance between each pixel point in the circle range of the circle and the circle center.
In a preferred embodiment of the present application, in the step L1, the pixel value M corresponding to the center of the circle is 10.
As a preferred embodiment of the present application, the fixed reduction factor P is 1%.
As a preferable mode of the present application, in the step L2, the label pixel value corresponding to each pixel point in the circumferential range is calculated by the following formula:
Vxy＝10-r2；
in the above formula, vxy is used to represent the label pixel value corresponding to the pixel point located in the (x, y) coordinate in the circumferential range;
and r is used for representing the distance between each pixel point on coordinates and the circle center of the corresponding circle, and r is less than or equal to L and equal to 0.01.
As a preferable mode of the present application, the magnetic sheet area is square in shape, and the magnetic sheet corner point is an apex of the magnetic sheet area.
The method fully considers the characteristic of obvious magnetic sheet characteristics such as the regional edge of the magnetic sheet region, the magnetic sheet corner point and the like, assigns corresponding labels for the regional edge of the magnetic sheet region, each pixel point in the region and the magnetic sheet corner point region, calculates the cross entropy loss for detecting the magnetic sheet image according to the assigned label value, and adjusts the training parameters of the segmentation model for identifying the magnetic sheet image according to the cross entropy loss calculation result, so that the segmentation model obtained by training has higher identification precision, and can detect possible abnormal conditions such as incompleteness and the like of the magnetic sheet region.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below. It is evident that the drawings described below are only some embodiments of the present application and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a diagram showing steps of a method for preliminary positioning of a magnetic sheet according to an embodiment of the present application;
fig. 2 is a method step diagram of labeling magnetic sheet corner points of magnetic sheet areas.
Detailed Description
The technical scheme of the application is further described below by the specific embodiments with reference to the accompanying drawings.
Wherein the drawings are for illustrative purposes only and are shown in schematic, non-physical, and not intended to be limiting of the present patent; for the purpose of better illustrating embodiments of the application, certain elements of the drawings may be omitted, enlarged or reduced and do not represent the size of the actual product; it will be appreciated by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numbers in the drawings of embodiments of the application correspond to the same or similar components; in the description of the present application, it should be understood that, if the terms "upper", "lower", "left", "right", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, only for convenience in describing the present application and simplifying the description, rather than indicating or implying that the apparatus or elements being referred to must have a specific orientation, be constructed and operated in a specific orientation, so that the terms describing the positional relationships in the drawings are merely for exemplary illustration and should not be construed as limiting the present patent, and that the specific meaning of the terms described above may be understood by those of ordinary skill in the art according to specific circumstances.
In the description of the present application, unless explicitly stated and limited otherwise, the term "coupled" or the like should be interpreted broadly, as it may be fixedly coupled, detachably coupled, or integrally formed, as indicating the relationship of components; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between the two parts or interaction relationship between the two parts. The specific meaning of the above terms in the present application will be understood in specific cases by those of ordinary skill in the art.
The embodiment of the application provides a magnetic sheet initial positioning method for positioning and detecting a magnetic sheet area in a magnetic sheet image, referring to fig. 2, the method comprises the following steps:
step S1, inputting a magnetic sheet image into a segmentation neural network for image feature extraction to obtain a segmentation map corresponding to the magnetic sheet image, wherein the segmentation map displays suspected areas of magnetic sheet areas in the magnetic sheet image;
step S2, according to the real region of the magnetic sheet region on the magnetic sheet image, a first pixel label is given to each pixel point in the magnetic sheet region on the magnetic sheet image, and a second pixel label is given to each pixel point in the non-magnetic sheet region on the magnetic sheet image;
step S3, calculating cross entropy loss of the segmentation neural network output segmentation map in the step S1 according to the label endowing result in the step S2;
step S4, according to the cross entropy loss calculated in the step S3, training parameters of a segmentation model for identifying the magnetic sheet image are adjusted;
and S5, updating and training the segmentation model according to the adjusted training parameters to obtain an updated segmentation model, wherein the segmentation model is used for identifying the magnetic sheet region in the magnetic sheet image.
In the above technical solution, step S1, the segmented neural network for extracting the image features of the magnetic sheet image is an existing neural network, and the specific process of extracting the features of the magnetic sheet image by the segmented neural network is not described herein because the process of extracting the features of the magnetic sheet image by the segmented neural network is not within the scope of the application claimed.
In the above technical solution, in step S2, the first pixel label is a first pixel value corresponding to each pixel point in the magnetic sheet area on the magnetic sheet image, and the first pixel value is assigned to be 1;
the second pixel label is a second pixel value corresponding to each pixel point in a non-magnetic sheet area on the magnetic sheet image, namely, other image areas except the magnetic sheet area, and the second pixel value is assigned to be 0.
As a preferable case, after assigning values to each pixel point inside and outside the real magnetic sheet region, the cross entropy loss calculation is performed on the segmentation map output by the segmentation neural network in step S1, then the training parameters of the segmentation model for identifying the magnetic sheet image are adjusted according to the cross entropy loss calculation result, and then the segmentation model is updated to improve the accuracy of identifying the magnetic sheet region by the segmentation model.
In another preferred case, in step S2, labeling is performed on each pixel point on the edge line of the magnetic sheet region on the magnetic sheet image, the line width of the edge line is preferably 5 pixels, and the pixel value corresponding to each pixel point on the edge line of the region may be assigned to 1.
After each pixel point of the region edge line is assigned, cross entropy loss calculation is performed on the segmentation map output by the segmentation neural network in the step S1, training parameters of a segmentation model for identifying the magnetic sheet image are adjusted according to the cross entropy loss calculation result, and then the segmentation model is updated to improve accuracy of identifying the magnetic sheet region by the segmentation model.
And the pixel points on the edge line of the region are assigned, and then the region surrounded by the edge line of the region is used as a real magnetic sheet region.
As another preferable aspect, in step S2, labeling each pixel point on the magnetic sheet corner point of the magnetic sheet region on the magnetic sheet image, referring to fig. 2, specifically, the method for labeling each pixel point on the magnetic sheet corner point includes the following steps:
step L1, establishing a circle at each magnetic sheet angular point position, endowing a third pixel label to the center of the circle, wherein the pixel value corresponding to the third pixel label is M, and the radius of the circle is a fixed reduction multiple P of the magnetic sheet length L; it should be noted that, the center position may be formed by a plurality of pixel points, or may be just one pixel point;
and step L2, calculating a label pixel value corresponding to each pixel point in the circle range according to the pixel value M corresponding to the circle center determined in the step L1 and the position distance between each pixel point in the circle range of the circle and the circle center.
In the above technical solution, preferably, in step L1, the pixel value M corresponding to the center of the circle is 10.
The fixed reduction factor P is preferably 1%. I.e. the radius of the circle is preferably 1% of the length L of the magnet sheet.
In step L2, the label pixel value corresponding to each pixel point in the circumferential range is calculated by the following formula:
Vxy＝10-r 2 ；
in the above formula, vxy is used to represent a label pixel value corresponding to a pixel point located in the (x, y) coordinate in the circumferential range;
r is used for representing the distance between each pixel point on the coordinates and the circle center of the corresponding circle, and r is less than or equal to L and equal to 0.01.
When the circle center is a pixel point, r represents the distance between each pixel point on coordinates in the circle range and the pixel point serving as the circle center; when the circle center is composed of a plurality of pixel points, r represents an average value of distances between each pixel point on coordinates in the circle range and each pixel point as the circle center.
Preferably, the shape of the candidate frame for extracting the magnetic sheet region is square, that is, the shape of the magnetic sheet region is square, so the magnetic sheet corner points are four vertexes of the magnetic sheet region.
In the scheme, the four vertexes of the magnetic sheet area are determined, and then the area surrounded by connecting lines of the four vertexes is used as the magnetic sheet area, so that the identification accuracy of the magnetic sheet area can be effectively ensured on the basis of considering the identification speed of the segmentation model.
In the scheme, after each pixel point of the magnetic sheet corner point is assigned, cross entropy loss calculation is performed on the segmentation map output by the segmentation neural network in the step S1, training parameters of a segmentation model for identifying the magnetic sheet image are adjusted according to the cross entropy loss calculation result, and then the segmentation model is updated, so that the accuracy of identifying the magnetic sheet region by the segmentation model is improved.
In summary, the application fully considers the characteristic of significant magnetic sheet characteristics such as the regional edge of the magnetic sheet region, the magnetic sheet corner point and the like, and the abnormal conditions such as the possible incompleteness of the magnetic sheet region can be detected by endowing the regional edge of the magnetic sheet region, each pixel point in the region and the magnetic sheet corner point region with corresponding labels, calculating the cross entropy loss for detecting the magnetic sheet image according to the endowed label value, and adjusting the training parameters of the segmentation model for identifying the magnetic sheet image according to the calculation result of the cross entropy loss.
It should be understood that the above description is only illustrative of the preferred embodiments of the present application and the technical principles employed. It will be apparent to those skilled in the art that various modifications, equivalents, variations, and the like can be made to the present application. However, such modifications are intended to fall within the scope of the present application without departing from the spirit of the present application. In addition, some terms used in the description and claims of the present application are not limiting, but are merely for convenience of description.
Claims (7)
1. The initial positioning method of the magnetic sheet is used for positioning and detecting the magnetic sheet area in the magnetic sheet image and is characterized by comprising the following steps:
step S1, inputting a magnetic sheet image into a segmentation neural network for image feature extraction, and obtaining a segmentation map corresponding to the magnetic sheet image, wherein the segmentation map displays suspected areas of the magnetic sheet areas in the magnetic sheet image;
step S2, according to the real region of the magnetic sheet region on the magnetic sheet image, a first pixel label is given to each pixel point in the magnetic sheet region on the magnetic sheet image, and a second pixel label is given to each pixel point in the non-magnetic sheet region on the magnetic sheet image;
step S3, calculating the cross entropy loss of the segmentation neural network output segmentation map in the step S1 according to the label endowing result of the step S2;
step S4, according to the cross entropy loss calculated in the step S3, training parameters of a segmentation model for identifying the magnetic sheet image are adjusted;
step S5, updating and training the segmentation model according to the adjusted training parameters to obtain an updated segmentation model, wherein the segmentation model is used for identifying the magnetic sheet area on the magnetic sheet image;
in the step S2, labeling is further performed on each pixel point on an area edge line of the magnetic sheet area on the magnetic sheet image, the line width of the area edge line is 5 pixels, and a value of each pixel point on the area edge line is assigned to 1.
2. The method for initially positioning a magnetic disk according to claim 1, wherein in the step S2, the first pixel label is a first pixel value corresponding to each pixel point in the magnetic disk area on the magnetic disk image, and the first pixel value is assigned to be 1;
and the second pixel label is a second pixel value corresponding to each pixel point in the non-magnetic sheet area on the magnetic sheet image, and the second pixel value is assigned to be 0.
3. The method for initially positioning a magnetic sheet according to claim 1, wherein in the step S2, each pixel point on a magnetic sheet corner point of the magnetic sheet region on the magnetic sheet image is labeled, and the method for labeling each pixel point on the magnetic sheet corner point specifically comprises the following steps:
step L1, establishing a circle at each magnetic sheet angular point position, and endowing a third pixel label to the center of the circle, wherein the pixel value corresponding to the third pixel label is M, and the radius of the circle is a fixed reduction multiple P of the magnetic sheet length L;
and step L2, calculating a label pixel value corresponding to each pixel point in the circle range according to the pixel value M corresponding to the circle center determined in the step L1 and the position distance between each pixel point in the circle range of the circle and the circle center.
4. The method for initially positioning a magnetic disk as claimed in claim 3, wherein in the step L1, the pixel value M corresponding to the center of a circle is 10.
5. The method for initially positioning a magnetic sheet according to claim 3, wherein the fixed reduction factor P is 1%.
6. The method for initially positioning a magnetic disk according to claim 4, wherein in the step L2, the label pixel value corresponding to each pixel point in the circumferential range is calculated by the following formula:
Vxy=10-r 2 ；
in the above formula, vxy is used to represent the label pixel value corresponding to the pixel point located in the (x, y) coordinate in the circumferential range;
and r is used for representing the distance between each pixel point on coordinates and the circle center of the corresponding circle, and r is less than or equal to L and equal to 0.01.
7. The preliminary positioning method of a magnetic sheet according to claim 3, wherein the magnetic sheet region is square in shape, and the magnetic sheet corner is an apex of the magnetic sheet region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911352934.0A CN111062391B (en) | 2019-12-25 | 2019-12-25 | Magnetic sheet initial positioning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911352934.0A CN111062391B (en) | 2019-12-25 | 2019-12-25 | Magnetic sheet initial positioning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111062391A CN111062391A (en) | 2020-04-24 |
| CN111062391B true CN111062391B (en) | 2023-09-19 |
Family
ID=70303728
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911352934.0A Active CN111062391B (en) | 2019-12-25 | 2019-12-25 | Magnetic sheet initial positioning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111062391B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002027713A (en) * | 2000-07-11 | 2002-01-25 | Sumitomo Special Metals Co Ltd | Detecting method for magnetized position |
| JP2016001281A (en) * | 2014-06-12 | 2016-01-07 | 株式会社東芝 | Image forming apparatus |
| CN107316287A (en) * | 2017-05-26 | 2017-11-03 | 浙江工业大学 | A kind of defect identification method in rectangle ferrite magnetic disk sheet face |
| CN108074231A (en) * | 2017-12-18 | 2018-05-25 | 浙江工业大学 | Magnetic sheet surface defect detection method based on convolutional neural network |
| CN109492143A (en) * | 2018-09-21 | 2019-03-19 | 平安科技（深圳）有限公司 | Image processing method, device, computer equipment and storage medium |
| CN110010335A (en) * | 2019-04-25 | 2019-07-12 | 天通控股股份有限公司 | Flexible magnetic sheet production method, flexible magnetic sheet and wireless charger |
-
2019
- 2019-12-25 CN CN201911352934.0A patent/CN111062391B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002027713A (en) * | 2000-07-11 | 2002-01-25 | Sumitomo Special Metals Co Ltd | Detecting method for magnetized position |
| JP2016001281A (en) * | 2014-06-12 | 2016-01-07 | 株式会社東芝 | Image forming apparatus |
| CN107316287A (en) * | 2017-05-26 | 2017-11-03 | 浙江工业大学 | A kind of defect identification method in rectangle ferrite magnetic disk sheet face |
| CN108074231A (en) * | 2017-12-18 | 2018-05-25 | 浙江工业大学 | Magnetic sheet surface defect detection method based on convolutional neural network |
| CN109492143A (en) * | 2018-09-21 | 2019-03-19 | 平安科技（深圳）有限公司 | Image processing method, device, computer equipment and storage medium |
| CN110010335A (en) * | 2019-04-25 | 2019-07-12 | 天通控股股份有限公司 | Flexible magnetic sheet production method, flexible magnetic sheet and wireless charger |
Non-Patent Citations (2)
| Title |
|---|
| 姚明海 ; 陈志浩 ; .基于深度主动学习的磁片表面缺陷检测.计算机测量与控制.2018,(09),全文. * |
| 姚明海.基于优化卷积神经网络的表面缺陷检测.《高技术通讯》.2019,第第29卷卷(第第29卷期),参见正文第564-568页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111062391A (en) | 2020-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10762376B2 (en) | Method and apparatus for detecting text | |
| WO2019228063A1 (en) | Product inspection terminal, method and system, computer apparatus and readable medium | |
| CN109389121B (en) | Nameplate identification method and system based on deep learning | |
| JP4970195B2 (en) | Person tracking system, person tracking apparatus, and person tracking program | |
| US9607199B2 (en) | Decoding machine-readable optical codes with aesthetic component | |
| EP1970839B1 (en) | Apparatus, method, and program for face feature point detection | |
| CN107392141B (en) | Airport extraction method based on significance detection and LSD (least squares distortion) line detection | |
| CN111046872B (en) | Optical character recognition method | |
| EP3624001A1 (en) | Methods and systems for parking line marker detection and pairing and parking spot detection and classification | |
| CN113592828B (en) | Nondestructive testing method and system based on industrial endoscope | |
| CN106709518A (en) | Android platform-based blind way recognition system | |
| CN114972356B (en) | Plastic product surface defect detection and identification method and system | |
| CN111209920B (en) | Airplane detection method under complex dynamic background | |
| CN115082466B (en) | PCB surface welding spot defect detection method and system | |
| CN109087294A (en) | A kind of product defects detection method, system and computer readable storage medium | |
| CN110263662B (en) | Human body contour key point and key part identification method based on grading | |
| CN114331986A (en) | Dam crack identification and measurement method based on unmanned aerial vehicle vision | |
| CN113947714B (en) | Multi-mode collaborative optimization method and system for video monitoring and remote sensing | |
| CN110827263B (en) | Magnetic shoe surface defect detection system and detection method based on visual identification technology | |
| CN110348307B (en) | Path edge identification method and system for crane metal structure climbing robot | |
| CN111105411B (en) | Magnetic shoe surface defect detection method | |
| CN111062391B (en) | Magnetic sheet initial positioning method | |
| US20160283805A1 (en) | Method and device for classifying an object in an image | |
| Chen et al. | Image segmentation based on mathematical morphological operator | |
| CN105574841A (en) | Color-based image segmenting method and device |
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 |