CN112132783A - Part identification method based on digital image processing technology - Google Patents
Part identification method based on digital image processing technology Download PDFInfo
- Publication number
- CN112132783A CN112132783A CN202010852451.3A CN202010852451A CN112132783A CN 112132783 A CN112132783 A CN 112132783A CN 202010852451 A CN202010852451 A CN 202010852451A CN 112132783 A CN112132783 A CN 112132783A
- Authority
- CN
- China
- Prior art keywords
- outline
- main
- contour
- area
- contours
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a part identification method based on a digital image processing technology, which comprises the steps of obtaining all outlines of a part, taking the outermost layer outline of the part as a main outline, forming a part index library by the main outline and a part drawing number, and forming a part feature library by the rest outlines and the part drawing number; the method comprises the steps of obtaining a part real image, matching the outermost layer outline of the part real image with a main outline in a part index library, selecting a plurality of part drawing numbers with the highest matching degree, extracting all features in a part feature library corresponding to the part drawing numbers to match with the inner outlines in the part real image one by one, and giving out the part drawing number closest to the real part according to the matching result, so that the automatic part identification is realized, the accuracy of part identification is improved, and the identification efficiency is improved.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a part identification method based on a digital image processing technology.
Background
The aviation structural part has the characteristics of small batch and multiple varieties, and as the aviation structural part has high part similarity and complex processing technology, after the procedures of surface treatment, paint spraying and the like are finished, the part does not have any mark to distinguish part drawing numbers, can be marked only by digital-analog files and worker experience, and is easy to generate marking errors, so that the subsequent assembly is carried out on wrong parts, and the use life cycle of the part is reduced and other accidents are caused.
In view of the above, the invention provides an aviation structural part identification method based on digital image processing, which uses a digital image processing technology to perform index matching and feature matching with part features and indexes extracted from a process digital-analog file after parts are subjected to processes such as heat treatment, paint spraying and the like, so as to give a most similar part figure number and improve the part identification efficiency and the identification accuracy.
Disclosure of Invention
The invention aims to provide a part identification method based on a digital image processing technology, and aims to realize automatic part identification, improve the accuracy of part identification and improve the identification efficiency.
The invention is mainly realized by the following technical scheme: a part identification method based on a digital image processing technology is characterized in that all outlines of a part are obtained, the outermost layer outline of the part is used as a main outline, the main outline and a part drawing number form a part index library, and the rest outlines and the part drawing number form a part feature library; acquiring a part real object image, matching the outermost layer outline of the part real object image with a main outline in a part index library, selecting a plurality of part drawing numbers with the highest matching degree, then extracting all features in a part feature library corresponding to the part drawing numbers to match with the internal outlines in the part real object image one by one, and giving out the part drawing number closest to the real object part according to the matching result.
In order to better implement the method, further, all the contours of the digital-analog file are extracted, the outermost contour is extracted to be used as a main contour, and the rest contours are used as feature contours; storing the main outline and the part drawing number as a { drawing number, outline } as a part drawing number index; and storing the characteristic outline in a storage mode of { main outline center coordinate, outline coordinate, main outline area, area enclosed by the outline, outline }, and forming a part internal data characteristic mark.
In order to better realize the invention, further, all the outlines of the main view are extracted by reading the process digital-analog file; calculating the areas of all the contours, sequencing the contours according to the areas, storing information of a figure P and a contour V as { P, V } of a main contour with the largest area as a part figure number, and using the information as a part contour index to further form a contour index library; extracting the characteristic contour, and storing the figure number P of the corresponding main contourmainCenter point coordinate CmainCenter point coordinate C of feature profilenMain contour area SmainArea of contour SnContour information VnForming a feature vector store { Pmain,Cmain,Cn,Smain,Sn,Vn}。
In order to better realize the method, further, an image of the part is extracted, Gaussian blur, gray level processing and binary processing are sequentially carried out on the image, and all contours are extracted; and then calculating the area according to the contour, sequencing according to the size of the area, and taking the contour with the largest area as the outermost contour of the part.
In order to better realize the method, a Hough invariant moment algorithm is further used for matching with the actual main contours of the part, and a plurality of main contours with the highest similarity and corresponding figure numbers are selected according to the matching degree; and then extracting the sub-outline of the process drawing number and the sub-outline of the process drawing for matching, and giving the part drawing number with the highest matching degree as the recommended process drawing number.
In order to better implement the invention, further, the similarity between the profiles is calculated, and after the similarity reaches a preset threshold value, the distance L from the main profile center coordinate of the characteristic point to the profile center point is calculated1Calculating the distance L from the center point of the characteristic contour to the center point of the main contour2Calculating L1And L2The square of the ratio of (a) to the ratio alpha of the area of the real object outline of the part to the area of the characteristic outline,
if alpha is within the range of the set threshold, recording the similarity, storing the similarity in an array, and averaging.
In order to better implement the invention, the method mainly comprises the following steps:
s11: reading a digital-analog file, extracting a main view of the digital-analog file into a picture form, sequentially carrying out gray processing and binary processing to extract all contours of the digital-analog file, taking the outermost contour as a main contour and taking the rest contours as feature contours; storing the main outline and the part drawing number as a { drawing number, outline } form as a part drawing number index; storing the characteristic outline in a mode of { main outline center coordinate, outline coordinate, main outline area, area enclosed by the outline, outline } to form a part internal data characteristic mark;
s12: shooting a part real object image, sequentially carrying out Gaussian blur, gray level processing and binary processing on the digital image, and extracting all contours; calculating the area according to the contour, sequencing according to the size of the area, and taking the maximum area as the outermost contour of the part real object image;
s13: acquiring a main contour picture number and contour information of a process image from a process index, matching with a part real main contour by using a Hough invariant moment algorithm, and selecting a plurality of contours with highest similarity and corresponding picture numbers according to the matching degree; and then extracting the sub-outline of the process drawing number and the sub-outline of the process drawing for matching, and giving the part drawing number with the highest matching degree as the recommended process drawing number.
The invention has the beneficial effects that:
the method comprises the steps of taking the outermost layer contour of a part as a main contour, forming a part index library with part drawing numbers, and forming a part feature library with the rest contours and the part drawing numbers; the method comprises the steps of firstly, obtaining a plurality of part drawing numbers with high matching degree according to the outermost layer outline index of a part real object, then accurately matching the internal outlines in the part real object image in sequence, and giving the part drawing number closest to the real object part according to the matching result, so that the automatic part identification is realized, and the part identification accuracy and the identification efficiency are improved.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
Example 1:
a part identification method based on a digital image processing technology is characterized in that all outlines of a part are obtained, the outermost layer outline of the part is used as a main outline, the main outline and a part drawing number form a part index library, and the rest outlines and the part drawing number form a part feature library; acquiring a part real object image, matching the outermost layer outline of the part real object image with a main outline in a part index library, selecting a plurality of part drawing numbers with the highest matching degree, then extracting all features in a part feature library corresponding to the part drawing numbers to match with the internal outlines in the part real object image one by one, and giving out the part drawing number closest to the real object part according to the matching result.
Example 2:
in the embodiment, optimization is performed on the basis of embodiment 1, all contours of the digital-analog file are extracted, the outermost contour is extracted as a main contour, and the rest contours are used as feature contours; storing the main outline and the part drawing number as a { drawing number, outline } as a part drawing number index; and storing the characteristic outline in a storage mode of { main outline center coordinate, outline coordinate, main outline area, area enclosed by the outline, outline }, and forming a part internal data characteristic mark.
By reading the process digital-analog fileTaking all the outlines of the main view; calculating the areas of all the contours, sequencing the contours according to the areas, storing information of a figure P and a contour V as { P, V } of a main contour with the largest area as a part figure number, and using the information as a part contour index to further form a contour index library; extracting the characteristic contour, and storing the figure number P of the corresponding main contourmainCenter point coordinate CmainCenter point coordinate C of feature profilenMain contour area SmainArea of contour SnContour information VnForming a feature vector store { Pmain,Cmain,Cn,Smain,Sn,Vn}。
Other parts of this embodiment are the same as embodiment 1, and thus are not described again.
Example 3:
in the embodiment, optimization is performed on the basis of embodiment 1 or 2, an image of a part is extracted, gaussian blurring, gray processing and binary processing are sequentially performed on the image, and all contours are extracted; and then calculating the area according to the contour, sequencing according to the size of the area, and taking the contour with the largest area as the outermost contour of the part. The method is suitable for extracting the outermost layer outline in the process digital-analog file and the part real object image.
Extracting a main view of a process digital-analog file into a picture form by reading the process digital-analog file, and sequentially performing gray processing and binary processing to extract all outlines of the digital-analog file; and calculating the areas of all the contours, sequencing the contours according to the areas, and taking the outermost contour with the largest area as the main contour of the part drawing number.
And (4) photographing the part real object image, and performing Gaussian blur and gray level processing binary processing on the digital image. All contours are extracted. And calculating the area according to the contour, and sorting according to the size of the area. The maximum area of the image is used as the outermost outline of the part real image.
The rest of this embodiment is the same as embodiment 1 or 2, and therefore, the description thereof is omitted.
Example 4:
the method is characterized in that optimization is carried out on the basis of any one of embodiments 1-3, a Hough invariant moment algorithm is used for matching with the main outlines of the part real objects, and a plurality of main outlines with the highest similarity and corresponding graph numbers are selected according to the matching degree; and then extracting the sub-outline of the process drawing number and the sub-outline of the process drawing for matching, and giving the part drawing number with the highest matching degree as the recommended process drawing number.
And acquiring a plurality of part drawing numbers with the highest matching degree, acquiring all part characteristics, and matching with the outline in the material object information outline. The matching method comprises the following steps: calculating the similarity between the profiles, and calculating the distance L from the main profile center coordinates of the feature points to the profile center point after the similarity reaches an expected threshold value1Calculating the distance L from the center point of the characteristic contour to the center point of the main contour2Calculating L1And L2The square of the ratio of (a) to (b) and the ratio of the area of the real object outline of the part to the area of the characteristic outline α:
if alpha is within the range of the set threshold, recording the similarity, storing the similarity in an array, and averaging. And calculating the alpha ratio of the rest drawing numbers, storing the similarity of the alpha ratio, and finally selecting the optimal part drawing number as a recommended drawing number.
Other parts of this embodiment are the same as any of embodiments 1 to 3, and thus are not described again.
Example 5:
the present embodiment is optimized on the basis of any one of embodiments 1 to 4, and as shown in fig. 1, the present embodiment mainly includes the following steps:
s11: reading a digital-analog file, extracting a main view of the digital-analog file into a picture form, sequentially carrying out gray processing and binary processing to extract all contours of the digital-analog file, taking the outermost contour as a main contour and taking the rest contours as feature contours; storing the main outline and the part drawing number as a { drawing number, outline } form as a part drawing number index; storing the characteristic outline in a mode of { main outline center coordinate, outline coordinate, main outline area, area enclosed by the outline, outline } to form a part internal data characteristic mark;
s12: shooting a part real object image, sequentially carrying out Gaussian blur, gray level processing and binary processing on the digital image, and extracting all contours; calculating the area according to the contour, sequencing according to the size of the area, and taking the maximum area as the outermost contour of the part real object image;
s13: acquiring a main contour picture number and contour information of a process image from a process index, matching with a part real main contour by using a Hough invariant moment algorithm, and selecting a plurality of contours with highest similarity and corresponding picture numbers according to the matching degree; and then extracting the sub-outline of the process drawing number and the sub-outline of the process drawing for matching, and giving the part drawing number with the highest matching degree as the recommended process drawing number.
Other parts of this embodiment are the same as any of embodiments 1 to 4, and thus are not described again.
Example 6:
a part identification method based on digital image processing technology, as shown in FIG. 1, mainly includes the following steps:
s11: extracting all outlines of a top view in the digital-analog file by reading the process digital-analog file; the area of all contours is calculated. And reading the digital-analog file, and extracting the main view of the digital-analog file into a picture form. And carrying out gray level processing and binary processing on the extracted picture. And extracting all the contours of the digital-analog file, extracting the outermost contour of the digital-analog file to be used as a main contour, and taking the rest contours as feature contours. The master outline and the part drawing number are stored in the form of { drawing number, outline } as a part drawing number index. And storing the characteristic outline in a mode of { main outline center coordinate, outline coordinate, main outline area, area enclosed by the outline, outline } to form a part internal data characteristic mark.
S12: and (4) photographing the part real object image, and performing Gaussian blur and gray level processing binary processing on the digital image. All contours are extracted. And calculating the area according to the contour, and sorting according to the size of the area. The maximum area of the image is used as the outermost outline of the part real image.
S13: and acquiring the original contour picture number and the contour information of the process image from the process index, matching the original contour of the part by using a Hu moment invariant algorithm, and selecting a plurality of contours with the highest similarity and corresponding picture numbers according to the matching degree. And extracting the sub-contour of the process diagram and matching the sub-contour with the process sub-contour. And giving the part drawing number with the highest matching degree as the recommended process drawing number.
Example 7:
in this embodiment, optimization is performed on the basis of embodiment 6, and in step S11:
and extracting all the outlines of the main view by reading the process digital-analog file. Sorting the parts according to the areas, storing the information of the figure number P and the profile V of the main profile with the maximum area as the figure number of the part in a { P, V } form, and using the information as a part profile index. And performing the above operation on all the process digital-analog files to form a profile index library.
Extracting the characteristic contour, and storing the figure number P of the corresponding main contourmainCenter point coordinate CmainCenter point coordinates C of the feature profilenMain contour area SmainThe area of the contour SnThe contour profile information Vn. Form a feature vector store Pmain,Cmain,Cn,Smain,Sn,Vn}。
The rest of this embodiment is the same as embodiment 6, and thus, the description thereof is omitted.
Example 8:
in this embodiment, optimization is performed based on embodiment 6 or 7, and in step S12:
all contour information M { V } of the part real object image is acquired from S121...VnObtaining a main outline V of the part real object by comparing outline areasmainWill no longer be the profile V inside the main profile of the partkAnd deleting the contour information of the real object.
The rest of this embodiment is the same as embodiment 6 or 7, and therefore, the description thereof is omitted.
Example 9:
this embodiment is optimized on the basis of any one of embodiments 6 to 8, and in step S13:
using the physical main profile V of the partmainAnd carrying out Hough invariant moment calculation on the main contour of the part digital-analog file stored in the contour index library. And acquiring 10 part drawing numbers with the highest matching degree.
S131: and acquiring all the part characteristics, and matching with the outline in the real object information outline. The matching method comprises the following steps: calculating the similarity between the profiles, and calculating the distance L from the main profile center coordinate of the feature point to the profile center point after the similarity reaches an expected threshold value1Calculating the distance L from the center point of the characteristic contour to the center point of the main contour2Calculating L1And L2The square of the ratio of (a) to the ratio alpha of the area of the physical outline of the part to the area of the characteristic outline.
If the ratio alpha of the two is within a certain specified range, the similarity is recorded and stored in the array A. The average value is calculated. And S131 operation is carried out on all the similarity of the 10 drawing numbers with the highest matching degree, the similarity is stored, and finally the optimal part drawing number is selected as the recommended drawing number.
Other parts of this embodiment are the same as those of any of embodiments 6 to 8, and thus are not described again.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications and equivalent variations of the above embodiments according to the technical spirit of the present invention are included in the scope of the present invention.
Claims (7)
1. A part identification method based on a digital image processing technology is characterized in that all outlines of a part are obtained, the outline of the outermost layer of the part is used as a main outline, the main outline and a part drawing number form a part index library, and the rest outlines and the part drawing number form a part feature library; acquiring a part real object image, matching the outermost layer outline of the part real object image with a main outline in a part index library, selecting a plurality of part drawing numbers with the highest matching degree, then extracting all features in a part feature library corresponding to the part drawing numbers to match with the internal outlines in the part real object image one by one, and giving out the part drawing number closest to the real object part according to the matching result.
2. The part identification method based on the digital image processing technology as claimed in claim 1, characterized in that all contours of the digital-to-analog file are extracted, the outermost contour is extracted as a main contour, and the rest contours are extracted as feature contours; storing the main outline and the part drawing number as a { drawing number, outline } as a part drawing number index; and storing the characteristic outline in a storage mode of { main outline center coordinate, outline coordinate, main outline area, area enclosed by the outline, outline }, and forming a part internal data characteristic mark.
3. The method for identifying parts based on digital image processing technology as claimed in claim 2, wherein the information of the number P and the profile V is stored as { P, V } and used as the profile index of the part to form a profile index library; extracting the characteristic contour, and storing the figure number P of the corresponding main contourmainCenter point coordinate CmainCenter point coordinate C of feature profilenMain contour area SmainArea of contour SnContour information VnForming a feature vector store { Pmain,Cmain,Cn,Smain,Sn,Vn}。
4. The method for identifying parts based on the digital image processing technology as claimed in claim 1, wherein the image of the part is extracted, and the image is sequentially subjected to Gaussian blur, gray processing and binary processing to extract all contours; and then calculating the area according to the contour, sequencing according to the size of the area, and taking the contour with the largest area as the outermost contour of the part.
5. The part identification method based on the digital image processing technology as claimed in claim 1, characterized in that a Hough invariant moment algorithm is used for matching with the actual main contours of the parts, and a plurality of main contours with the highest similarity and corresponding picture numbers are selected according to the matching degree; and then extracting the sub-outline of the process drawing number and the sub-outline of the process drawing for matching, and giving the part drawing number with the highest matching degree as the recommended process drawing number.
6. The method of claim 5, wherein the similarity between the contours is calculated, and after the similarity reaches a predetermined threshold, the distance L from the center coordinates of the main contour to the center point of the contour is calculated1Calculating the distance L from the center point of the characteristic contour to the center point of the main contour2Calculating L1And L2The square of the ratio of (a) to the ratio alpha of the area of the real object outline of the part to the area of the characteristic outline,
if alpha is within the range of the set threshold, recording the similarity, storing the similarity in an array, and averaging.
7. The method for identifying parts based on digital image processing technology according to any one of claims 1-6, characterized in that it essentially comprises the following steps:
s11: reading a digital-analog file, extracting a main view of the digital-analog file into a picture form, sequentially carrying out gray processing and binary processing to extract all contours of the digital-analog file, taking the outermost contour as a main contour and taking the rest contours as feature contours; storing the main outline and the part drawing number as a { drawing number, outline } form as a part drawing number index; storing the characteristic outline in a mode of { main outline center coordinate, outline coordinate, main outline area, area enclosed by the outline, outline } to form a part internal data characteristic mark;
s12: shooting a part real object image, sequentially carrying out Gaussian blur, gray level processing and binary processing on the digital image, and extracting all contours; calculating the area according to the contour, sequencing according to the size of the area, and taking the maximum area as the outermost contour of the part real object image;
s13: acquiring a main contour picture number and contour information of a process image from a process index, matching with a part real main contour by using a Hough invariant moment algorithm, and selecting a plurality of contours with highest similarity and corresponding picture numbers according to the matching degree; and then extracting the sub-outline of the process drawing number and the sub-outline of the process drawing for matching, and giving the part drawing number with the highest matching degree as the recommended process drawing number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010852451.3A CN112132783B (en) | 2020-08-21 | 2020-08-21 | Part identification method based on digital image processing technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010852451.3A CN112132783B (en) | 2020-08-21 | 2020-08-21 | Part identification method based on digital image processing technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112132783A true CN112132783A (en) | 2020-12-25 |
| CN112132783B CN112132783B (en) | 2022-09-20 |
Family
ID=73851001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010852451.3A Active CN112132783B (en) | 2020-08-21 | 2020-08-21 | Part identification method based on digital image processing technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112132783B (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102654902A (en) * | 2012-01-16 | 2012-09-05 | 江南大学 | Contour vector feature-based embedded real-time image matching method |
| WO2013084731A1 (en) * | 2011-12-08 | 2013-06-13 | 日本電気株式会社 | Image identifying system |
| US20140169683A1 (en) * | 2012-12-18 | 2014-06-19 | Samsung Electronics Co., Ltd. | Image retrieval method, real-time drawing prompting method, and devices thereof |
| CN105550381A (en) * | 2016-03-17 | 2016-05-04 | 北京工业大学 | Efficient image retrieval method based on improved SIFT (scale invariant feature transform) feature |
| CN105574161A (en) * | 2015-12-15 | 2016-05-11 | 徐庆 | Trademark graph element identification method, device and system |
| CN105787891A (en) * | 2016-01-31 | 2016-07-20 | 厦门美图之家科技有限公司 | Image processing method, system and shooting terminal for optimizing edge aliasing |
| CN106295649A (en) * | 2015-05-15 | 2017-01-04 | 中云智慧（北京）科技有限公司 | Target identification method based on contour features |
| CN106339479A (en) * | 2016-08-30 | 2017-01-18 | 深圳市金立通信设备有限公司 | Picture naming method and terminal |
| CN106599515A (en) * | 2016-12-30 | 2017-04-26 | 武汉理工大学 | Automobile covering part sheet metal forming technology optimizing method based on STL grid feature recognition |
| CN108171102A (en) * | 2016-12-07 | 2018-06-15 | 广州映博智能科技有限公司 | A kind of part method for quickly identifying of view-based access control model |
| US20180268551A1 (en) * | 2015-01-08 | 2018-09-20 | Ju Sung LEE | A file conversion method and apparatus |
| CN109614977A (en) * | 2018-11-14 | 2019-04-12 | 华南理工大学 | A kind of hub type recognition methods |
| CN109711404A (en) * | 2018-12-20 | 2019-05-03 | 中科院成都信息技术股份有限公司 | Recognition methods, device and the computer readable storage medium of seal ballot paper full-filling |
| CN110222703A (en) * | 2019-06-12 | 2019-09-10 | 江苏通佑视觉科技有限公司 | Image outline identification method, apparatus, equipment and medium |
| CN110443128A (en) * | 2019-06-28 | 2019-11-12 | 广州中国科学院先进技术研究所 | One kind being based on SURF characteristic point accurately matched finger vein identification method |
| CN110766750A (en) * | 2019-09-09 | 2020-02-07 | 浙江大学 | Mechanical arm visual servo target identification method based on local contour |
| CN110866894A (en) * | 2019-10-08 | 2020-03-06 | 南京航空航天大学 | Cross-granularity sheet metal part identification system and method based on machine vision technology |
| CN111369690A (en) * | 2018-12-26 | 2020-07-03 | 深圳市优必选科技有限公司 | Building block model generation method and device, terminal and computer readable storage medium |
-
2020
- 2020-08-21 CN CN202010852451.3A patent/CN112132783B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013084731A1 (en) * | 2011-12-08 | 2013-06-13 | 日本電気株式会社 | Image identifying system |
| CN102654902A (en) * | 2012-01-16 | 2012-09-05 | 江南大学 | Contour vector feature-based embedded real-time image matching method |
| US20140169683A1 (en) * | 2012-12-18 | 2014-06-19 | Samsung Electronics Co., Ltd. | Image retrieval method, real-time drawing prompting method, and devices thereof |
| US20180268551A1 (en) * | 2015-01-08 | 2018-09-20 | Ju Sung LEE | A file conversion method and apparatus |
| CN106295649A (en) * | 2015-05-15 | 2017-01-04 | 中云智慧（北京）科技有限公司 | Target identification method based on contour features |
| CN105574161A (en) * | 2015-12-15 | 2016-05-11 | 徐庆 | Trademark graph element identification method, device and system |
| CN105787891A (en) * | 2016-01-31 | 2016-07-20 | 厦门美图之家科技有限公司 | Image processing method, system and shooting terminal for optimizing edge aliasing |
| CN105550381A (en) * | 2016-03-17 | 2016-05-04 | 北京工业大学 | Efficient image retrieval method based on improved SIFT (scale invariant feature transform) feature |
| CN106339479A (en) * | 2016-08-30 | 2017-01-18 | 深圳市金立通信设备有限公司 | Picture naming method and terminal |
| CN108171102A (en) * | 2016-12-07 | 2018-06-15 | 广州映博智能科技有限公司 | A kind of part method for quickly identifying of view-based access control model |
| CN106599515A (en) * | 2016-12-30 | 2017-04-26 | 武汉理工大学 | Automobile covering part sheet metal forming technology optimizing method based on STL grid feature recognition |
| CN109614977A (en) * | 2018-11-14 | 2019-04-12 | 华南理工大学 | A kind of hub type recognition methods |
| CN109711404A (en) * | 2018-12-20 | 2019-05-03 | 中科院成都信息技术股份有限公司 | Recognition methods, device and the computer readable storage medium of seal ballot paper full-filling |
| CN111369690A (en) * | 2018-12-26 | 2020-07-03 | 深圳市优必选科技有限公司 | Building block model generation method and device, terminal and computer readable storage medium |
| CN110222703A (en) * | 2019-06-12 | 2019-09-10 | 江苏通佑视觉科技有限公司 | Image outline identification method, apparatus, equipment and medium |
| CN110443128A (en) * | 2019-06-28 | 2019-11-12 | 广州中国科学院先进技术研究所 | One kind being based on SURF characteristic point accurately matched finger vein identification method |
| CN110766750A (en) * | 2019-09-09 | 2020-02-07 | 浙江大学 | Mechanical arm visual servo target identification method based on local contour |
| CN110866894A (en) * | 2019-10-08 | 2020-03-06 | 南京航空航天大学 | Cross-granularity sheet metal part identification system and method based on machine vision technology |
Non-Patent Citations (4)
| Title |
|---|
| HAIBIN LING等: "Shape Classification Using the Inner-Distance", 《IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》 * |
| 司小婷: "基于视觉的零件特征识别与分类方法研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 杨攀: "基于机器视觉的螺纹零件头部检测方法及实验研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 许加陈等: "基于IGES的钣金零件特征识别的方法研究", 《机电工程》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112132783B (en) | 2022-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105574063B (en) | The image search method of view-based access control model conspicuousness | |
| CN108491430B (en) | Unsupervised Hash retrieval method based on clustering characteristic directions | |
| CN108038435B (en) | Feature extraction and target tracking method based on convolutional neural network | |
| CN110543822A (en) | finger vein identification method based on convolutional neural network and supervised discrete hash algorithm | |
| CN107784321B (en) | Method and system for quickly identifying digital picture books and computer readable storage medium | |
| CN108629762B (en) | Image preprocessing method and system for reducing interference characteristics of bone age evaluation model | |
| CN110634131B (en) | Crack image identification and modeling method | |
| CN108875629B (en) | Palm vein identification method based on multi-sample feature fusion | |
| CN110942057A (en) | Container number identification method and device and computer equipment | |
| CN111783722B (en) | Lane line extraction method of laser point cloud and electronic equipment | |
| CN112818989A (en) | Image matching method based on gradient amplitude random sampling | |
| CN111695498A (en) | Wood identity detection method | |
| CN107729863B (en) | Human finger vein recognition method | |
| CN112132783B (en) | Part identification method based on digital image processing technology | |
| CN116958126B (en) | Method and system for detecting injection molding of mold based on computer vision | |
| CN112070116B (en) | Automatic artistic drawing classification system and method based on support vector machine | |
| CN111951234B (en) | Model detection method | |
| CN111339974B (en) | Method for identifying modern ceramics and ancient ceramics | |
| CN109299295B (en) | Blue printing layout database searching method | |
| CN108898045B (en) | Multi-label image preprocessing method based on deep learning gesture recognition | |
| CN112862767B (en) | Surface defect detection method for solving difficult-to-distinguish unbalanced sample based on metric learning | |
| CN105844299A (en) | Image classification method based on bag of words | |
| CN112818735B (en) | Article identification-based vessel spare part identification method | |
| CN104361354B (en) | A kind of large nuber of images sorting technique based on sparse coding K arest neighbors histograms | |
| CN113920391A (en) | Target counting method based on generated scale self-adaptive true value graph |
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 |