CN104574448A - Method for identifying connected pixel blocks - Google Patents
Method for identifying connected pixel blocks Download PDFInfo
- Publication number
- CN104574448A CN104574448A CN201410710102.2A CN201410710102A CN104574448A CN 104574448 A CN104574448 A CN 104574448A CN 201410710102 A CN201410710102 A CN 201410710102A CN 104574448 A CN104574448 A CN 104574448A
- Authority
- CN
- China
- Prior art keywords
- lastrow
- thisrow
- node
- swimming
- distance
- 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
Classifications
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the field of image processing, and provides a method for identifying connected pixel blocks. The method comprises the following steps: scanning images to be identified row by row to obtain a run-length section of each image row of the images to be identified; including the run-length section in a run-length node of a current image row, dividing the run-length node into a target run-length node and a background run-length node, and obtaining run-length information of the run-length node; identifying whether the target run-length node of the image row is connected with that of an adjacent image row or not according to the obtained run-length information of the run-length node and a preset connection identifying relationship; updating a pointer of the target run-length node of the This Row till the image processing of the last image row is finished. The method has the advantages that as the scanning of the images to be identified is conducted row by row, the run-length section of each image row of the images to be identified is obtained and included in the run-length node of the image row, the run-length information of the run-length node is obtained, whether the target run-length node of the image row is connected with that of the adjacent image row or not is identified according to the preset connection identifying relationship, and the problem of labeling redundancy is solved.
Description
Technical field
The invention belongs to image processing field, particularly relate to a kind of recognition methods of connected pixel block.
Background technology
Blob refer to there is similar image features (as color, texture etc.) and also be spatially be communicated with pixel composition block.It is the very important ingredient of computer vision and image understanding one that Blob analyzes, in the position to objects in images, shape and size almost without any can positioning object very easily when priori, calculate the various geometric properties of object, thus can select object according to these features and classify.
The core that Blob analyzes is connected region detection algorithm, and current algorithm roughly can be divided into two classes according to disposal route: the method based on picture element scan and the method based on Run-Length Coding.Labeling method based on pixel is more representational is recurrence method and twice sweep method.Recurrence method scan image, finds and does not have markd X point, and to the label L that its distribution one is new, recurrence distribute labels L is to the adjoint point of X point, until a little there is mark in institute.This method needs scan image repeatedly, and space complexity and time complexity are all very high.Twice sweep method is improved method above: first time scanning, carries out temporary marker to all connected regions, records all mark redundancies with table of equal value simultaneously; Second time scanning table of equal value, utilizes specific searching algorithm, carries out equal tag merging.First method based on Run-Length Coding carries out Run-Length Coding to bianry image, then connected component labeling is carried out to the image after coding, same utilization equivalence table, carry out recording mark redundancy, the method can compressed image effectively, search volume is diminished, thus reduces the space complexity of algorithm search.Utilize table record of equal value to mark redundancy, avoid multiple scanning connected region, but, when connected region number very greatly or connected region shape is very complicated in the picture, mark redundancy phenomena is serious, and list structure of equal value is complicated, and the algorithm that search table of equal value carries out equal tag merging is consuming time very long.The image gathered in industrial settings is due to the reason such as noise, illumination, a lot of noise is there is in the image gathered after binary conversion treatment, algorithm based on equivalence table is very consuming time, and algorithm is very unstable when noise is very serious, is difficult to be applied in industrial vision detection.
Summary of the invention
Given this, the invention provides a kind of recognition methods of connected pixel block, to solve the technical matters of prior art mark redundancy.
The embodiment of the present invention is achieved in that a kind of recognition methods of connected pixel block, said method comprising the steps of:
To line by line scan image to be identified, obtain the distance of swimming section of every a line image of described image to be identified;
Described distance of swimming section is counted the distance of swimming node of one's own profession image, described distance of swimming node is divided into target distance of swimming node and background distance of swimming node, and obtaining the Itinerary Information of described distance of swimming node, described Itinerary Information comprises: label information known, index information index, origin coordinates start, termination coordinate end and gray-scale value value;
Whether be communicated with the target distance of swimming node being communicated with identification relation recognition adjacent rows preset for the Itinerary Information according to described distance of swimming node, wherein, ThisRow represents one's own profession image, and LastRow represents lastrow image;
Upgrade the pointer of ThisRow target distance of swimming node, to the last a line image procossing completes.
The embodiment of the present invention, to line by line scan image to be identified, obtain the distance of swimming section of every a line image of image to be identified, distance of swimming section is counted the distance of swimming node of every a line, and obtain the Itinerary Information of this distance of swimming node, the connection identification relation according to presetting judges whether adjacent rows image is communicated with, make to do in the proper way and use the method for distance of swimming chained list and dynamic array, only need scan image once, and without the need to setting up table of equal value and carrying out equal tag merging, solve the mark redundancy phenomena in existing algorithm.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the process flow diagram of the connected pixel block identifying method that the embodiment of the present invention provides;
Be adjacent rows target distance of swimming node connected relation schematic diagram that one embodiment of the invention provides as shown in Figure 2 a;
Be adjacent rows target distance of swimming node connected relation schematic diagram that another embodiment of the present invention provides as shown in Figure 2 b;
Be adjacent rows target distance of swimming node connected relation schematic diagram that yet another embodiment of the invention provides as shown in Figure 2 c;
Be adjacent rows target distance of swimming node connected relation schematic diagram that yet another embodiment of the invention provides as shown in Figure 2 d;
Be adjacent rows target distance of swimming node connected relation schematic diagram that yet another embodiment of the invention provides as shown in Figure 2 e;
Be adjacent rows target distance of swimming node connected relation schematic diagram that yet another embodiment of the invention provides as shown in figure 2f;
Be adjacent rows target distance of swimming node connected relation schematic diagram that yet another embodiment of the invention provides as shown in Figure 2 g;
Be adjacent rows target distance of swimming node connected relation schematic diagram that yet another embodiment of the invention provides as shown in fig. 2h.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
In order to technical solutions according to the invention are described, be described below by specific embodiment.
Embodiment one
Be illustrated in figure 1 the process flow diagram of the connected pixel block identifying method that the embodiment of the present invention provides, said method comprising the steps of:
Step S101, image to be identified of lining by line scan, obtains the distance of swimming section of every a line image of described image to be identified.
In embodiments of the present invention, recognition system is lined by line scan image to be identified, to obtain the distance of swimming section of every a line image of image to be identified.
Step S102, described distance of swimming section is counted the distance of swimming node of one's own profession image, described distance of swimming node is divided into target distance of swimming node and background distance of swimming node, and obtaining the Itinerary Information of described distance of swimming node, described Itinerary Information comprises: label information known, index information index, origin coordinates start, termination coordinate end and gray-scale value value.
In embodiments of the present invention, recognition system is after the distance of swimming section obtaining every a line image, this distance of swimming section counted the distance of swimming node of one's own profession image and be divided into target distance of swimming node and background distance of swimming node, obtain the Itinerary Information of distance of swimming node simultaneously, wherein, Itinerary Information includes but not limited to: label information known, index information index, origin coordinates start, termination coordinate end and gray-scale value value, and wherein, the meaning that Itinerary Information is expressed is as follows:
Label information: for representing whether this distance of swimming node is labeled.
Index information: for representing the index of distance of swimming node at one's own profession image, record distance of swimming node is in the positional information of one's own profession image.
Origin coordinates: for representing the origin coordinates of distance of swimming node at one's own profession image.
Stop coordinate: for representing the termination coordinate of distance of swimming node at one's own profession image.
Gray-scale value: for representing the gray-scale value of distance of swimming node.
Whether step S103, be communicated with the target distance of swimming node being communicated with identification relation recognition adjacent rows preset for the Itinerary Information according to described distance of swimming node, wherein, ThisRow represents one's own profession image, and LastRow represents lastrow image.
In embodiments of the present invention, recognition system is after the Itinerary Information obtaining distance of swimming node, whether the target distance of swimming node according to this Itinerary Information identification adjacent rows is communicated with, wherein, described default connection identification pass is: LastRow.srart-1≤ThisRow.end, ThisRow.start-1≤LastRow.end and LastRow.value=ThisRow.value.Whether the described target distance of swimming node for the Itinerary Information identification adjacent rows according to described distance of swimming node is communicated with, and is specially:
(1) if Thisrow.start-1 > is LastRow.end, then the target distance of swimming node of adjacent rows is not communicated with.
In embodiments of the present invention, as Thisrow.start-1 > LastRow.end, the target distance of swimming node of adjacent rows does not meet the connection identification relation preset, the label information of target distance of swimming node is: LastRow → index++, namely points to the capable next distance of swimming of LastRow and continues to judge.Be the adjacent rows target distance of swimming node connected relation schematic diagram that one embodiment of the invention provides as shown in Figure 2 a, wherein white is target distance of swimming node, and black is background distance of swimming node.
(2) if LastRow.end+1 >=ThisRow.start >=LastRow.start and ThisRow.end > LastRow.end, then the target distance of swimming node of adjacent rows is communicated with.
In embodiments of the present invention, as LastRow.end+1 >=ThisRow.start >=LastRow.start and ThisRow.end > LastRow.end time, the target distance of swimming node of adjacent rows meets default connection identification relation, LastRow target distance of swimming node is less than the origin coordinates of ThisRow target distance of swimming node, termination coordinate is also little, then perform following operation: the target distance of swimming node target distance of swimming node of ThisRow being included into LastRow, LastRow → index++.Be the adjacent rows target distance of swimming node connected relation schematic diagram that another embodiment of the present invention provides as shown in Figure 2 b, wherein white is target distance of swimming node, and black is background distance of swimming node.
(3) if ThisRow.start >=LastRow.star and ThisRow.end < LastRow.end, then the target distance of swimming node of adjacent rows is communicated with.
In embodiments of the present invention, as ThisRow.start >=LastRow.star and ThisRow.end < LastRow.end time, the target distance of swimming node of adjacent rows meets default connection identification relation, LastRow target distance of swimming node is less than the origin coordinates of ThisRow target distance of swimming node but termination coordinate is large, then perform following operation: the target distance of swimming node target distance of swimming node of ThisRow being included into LastRow, ThisRow → index++.Be the adjacent rows target distance of swimming node connected relation schematic diagram that yet another embodiment of the invention provides as shown in Figure 2 c, wherein white is target distance of swimming node, and black is background distance of swimming node.
(4) if ThisRow.start >=LastRow.star and ThisRow.end=LastRow.end, then the target distance of swimming node of adjacent rows is communicated with.
In embodiments of the present invention, as ThisRow.start >=LastRow.star and ThisRow.end=LastRow.end time, the target distance of swimming node of adjacent rows meets default connection identification relation, LastRow target distance of swimming node is less than ThisRow target distance of swimming node origin coordinates, termination coordinate is identical, then perform following operation: the target distance of swimming node target distance of swimming node of ThisRow being included into LastRow, ThisRow → index++, LastRow → index++.Be the adjacent rows target distance of swimming node connected relation schematic diagram that yet another embodiment of the invention provides as shown in Figure 2 d, wherein white is target distance of swimming node, and black is background distance of swimming node.
(5) if ThisRow.start < LastRow.star and ThisRow.end=LastRow.end, then the target distance of swimming node of adjacent rows is communicated with.
In embodiments of the present invention, as ThisRow.start < LastRow.star and ThisRow.end=LastRow.end time, the target distance of swimming node of adjacent rows meets default connection identification relation, LastRow target distance of swimming node is larger than ThisRow target distance of swimming node origin coordinates, so ThisRow target distance of swimming node may be communicated with the previous row target distance of swimming node of LastRow target distance of swimming node simultaneously, namely ThisRow target distance of swimming node may be labeled, therefore need to carry out following process: the target distance of swimming node of the target distance of swimming node of ThisRow and LastRow is merged, and carry out following operation:
If (T.known==0) // judge that T is not labeled
{ ThisRow target distance of swimming node is included into LastRow target distance of swimming node; }
Else //T is marked
{ the target distance of swimming node of the target distance of swimming node of ThisRow and LastRow is merged; }
LastRow→index++；
ThisRow→index++；
Be the adjacent rows target distance of swimming node connected relation schematic diagram that yet another embodiment of the invention provides as shown in Figure 2 e, wherein white is target distance of swimming node, and black is background distance of swimming node.
(6) if ThisRow.start < LastRow.star and ThisRow.end > LastRow.end, then the target distance of swimming node of adjacent rows is communicated with.
In embodiments of the present invention, as ThisRow.start < LastRow.star and ThisRow.end > LastRow.end time, the target distance of swimming node of adjacent rows meets default connection identification relation, LastRow target distance of swimming node is larger than ThisRow target distance of swimming node origin coordinates, need to judge whether ThisRow target distance of swimming node is labeled, then perform following operation:
If (ThisRow.known==0) // judge that ThisRow is not labeled
{ ThisRow target distance of swimming node is included into LastRow target distance of swimming node; }
Else // judge that ThisRow is labeled
{ the target distance of swimming node of the target distance of swimming node of ThisRow and LastRow is merged; }
LastRow→index++。
Be the adjacent rows target distance of swimming node connected relation schematic diagram that yet another embodiment of the invention provides as shown in figure 2f, wherein white is target distance of swimming node, and black is background distance of swimming node.
(7) if LastRow.end > ThisRow.end > LasrRow.start-1 and ThisRow.start < LastRow.start, then the target distance of swimming node of adjacent rows is communicated with.
In embodiments of the present invention, as LastRow.end > ThisRow.end > LasrRow.start-1 and ThisRow.start < LastRow.start time, the target distance of swimming node of adjacent rows meets default connection identification relation, LastRow target distance of swimming node is larger than the origin coordinates of ThisRow target distance of swimming node, termination target is also large, need to judge whether ThisRow target distance of swimming node is labeled, then perform following operation:
If (ThisRow.known==0) // judge that ThisRow is not labeled
{ ThisRow target distance of swimming node is included into LastRow target distance of swimming node; }
Else // judge that ThisRow is labeled
{ the target distance of swimming node of the target distance of swimming node of ThisRow and LastRow is merged; }
LastRow→index++。
Be the adjacent rows target distance of swimming node connected relation schematic diagram that yet another embodiment of the invention provides as shown in Figure 2 g, wherein white is target distance of swimming node, and black is background distance of swimming node.
(8) if ThisRow.end < is LastRow.start-1, then the target distance of swimming node of adjacent adjacent rows is not communicated with.
In embodiments of the present invention, as ThisRow.end < LastRow.start-1, the target distance of swimming node of adjacent rows does not meet the connection identification relation preset, then perform following operation: ThisRow → index++, points to the next distance of swimming of ThisRow and judges.Be the adjacent rows target distance of swimming node connected relation schematic diagram that yet another embodiment of the invention provides as shown in fig. 2h, wherein white is target distance of swimming node, and black is background distance of swimming node.
Step S104, upgrade the pointer of ThisRow target distance of swimming node, to the last a line image procossing completes.
The embodiment of the present invention, to line by line scan image to be identified, obtain the distance of swimming section of every a line image of image to be identified, distance of swimming section is counted the distance of swimming node of every a line, and obtain the Itinerary Information of this distance of swimming node, the connection identification relation according to presetting judges whether adjacent rows image is communicated with, make to do in the proper way and use the method for distance of swimming chained list and dynamic array, only need scan image once, and without the need to setting up table of equal value and carrying out equal tag merging, solve the mark redundancy phenomena in existing algorithm.
As an embodiment of the present invention, before the described step for whether being communicated with according to the Itinerary Information of described distance of swimming node and the target distance of swimming node being communicated with identification relation recognition adjacent rows preset, described method is further comprising the steps of:
Preset described connection identification relation.
Those of ordinary skill in the art it is also understood that, the all or part of step realized in above-described embodiment method is that the hardware that can carry out instruction relevant by program has come, described program can be stored in a computer read/write memory medium, described storage medium, comprises ROM/RAM, disk, CD etc.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.
Claims (4)
1. a recognition methods for connected pixel block, is characterized in that, said method comprising the steps of:
To line by line scan image to be identified, obtain the distance of swimming section of every a line image of described image to be identified;
Described distance of swimming section is counted the distance of swimming node of one's own profession image, described distance of swimming node is divided into target distance of swimming node and background distance of swimming node, and obtaining the Itinerary Information of described distance of swimming node, described Itinerary Information comprises: label information known, index information index, origin coordinates start, termination coordinate end and gray-scale value value;
Whether be communicated with the target distance of swimming node being communicated with identification relation recognition adjacent rows preset for the Itinerary Information according to described distance of swimming node, wherein, ThisRow represents one's own profession image, and LastRow represents lastrow image;
Upgrade the pointer of ThisRow target distance of swimming node, to the last a line image procossing completes.
2. the method for claim 1, it is characterized in that, before the described step for whether being communicated with according to the Itinerary Information of described distance of swimming node and the target distance of swimming node being communicated with identification relation recognition adjacent rows preset, described method is further comprising the steps of:
Preset described connection identification relation.
3. the method for claim 1, is characterized in that, described default connection identification pass is: LastRow.srart-1≤ThisRow.end, ThisRow.start-1≤LastRow.end and LastRow.value=ThisRow.value.
4. method as claimed in claim 3, it is characterized in that, whether the described target distance of swimming node for the Itinerary Information identification adjacent rows according to described distance of swimming node is communicated with, and is specially:
If Thisrow.start-1 > is LastRow.end, then the target distance of swimming node of adjacent rows is not communicated with; Or,
If LastRow.end+1 >=ThisRow.start >=LastRow.start and ThisRow.end > LastRow.end, then the target distance of swimming node of adjacent rows is communicated with; Or,
If ThisRow.start >=LastRow.star and ThisRow.end < LastRow.end, then the target distance of swimming node of adjacent rows is communicated with; Or,
If ThisRow.start >=LastRow.star and ThisRow.end=LastRow.end, then the target distance of swimming node of adjacent rows is communicated with; Or,
If ThisRow.start >=LastRow.star and ThisRow.end=LastRow.end, then the target distance of swimming node of adjacent rows is communicated with; Or,
If ThisRow.start < LastRow.star and ThisRow.end > LastRow.end, then the target distance of swimming node of adjacent rows is communicated with; Or,
If ThisRow.start < LastRow.star and ThisRow.end > LastRow.end, then the target distance of swimming node of adjacent rows is communicated with; Or,
If ThisRow.end < is LastRow.start-1, then the target distance of swimming node of adjacent adjacent rows is not communicated with.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410710102.2A CN104574448A (en) | 2014-11-28 | 2014-11-28 | Method for identifying connected pixel blocks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410710102.2A CN104574448A (en) | 2014-11-28 | 2014-11-28 | Method for identifying connected pixel blocks |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104574448A true CN104574448A (en) | 2015-04-29 |
Family
ID=53090415
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410710102.2A Pending CN104574448A (en) | 2014-11-28 | 2014-11-28 | Method for identifying connected pixel blocks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104574448A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107067400A (en) * | 2016-11-30 | 2017-08-18 | 南京航空航天大学 | A kind of bianry image method for marking connected region based on the distance of swimming |
| CN109584262A (en) * | 2018-12-15 | 2019-04-05 | 中国科学院深圳先进技术研究院 | Cloud detection method of optic, device and electronic equipment based on remote sensing image |
| CN110738106A (en) * | 2019-09-05 | 2020-01-31 | 天津大学 | optical remote sensing image ship detection method based on FPGA |
| CN117152458A (en) * | 2023-11-01 | 2023-12-01 | 南京盛视工业技术有限公司 | Method and system for rapidly extracting connected domain based on travel coding |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040247179A1 (en) * | 2003-03-31 | 2004-12-09 | Seiko Epson Corporation | Image processing apparatus, image processing method, and image processing program |
| CN101042734A (en) * | 2007-04-17 | 2007-09-26 | 华东师范大学 | Method for rapid making image connection element |
| CN101930544A (en) * | 2010-09-07 | 2010-12-29 | 东南大学 | Run adjacency table-based staff quick connected domain analysis method |
-
2014
- 2014-11-28 CN CN201410710102.2A patent/CN104574448A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040247179A1 (en) * | 2003-03-31 | 2004-12-09 | Seiko Epson Corporation | Image processing apparatus, image processing method, and image processing program |
| CN101042734A (en) * | 2007-04-17 | 2007-09-26 | 华东师范大学 | Method for rapid making image connection element |
| CN101930544A (en) * | 2010-09-07 | 2010-12-29 | 东南大学 | Run adjacency table-based staff quick connected domain analysis method |
Non-Patent Citations (2)
| Title |
|---|
| 张二虎 等: "Blob分析中基于游程链的连通区域标记", 《应用科学学报》 * |
| 沈乔楠 等: "基于游程递归的连通区域标记算法", 《计算机应用》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107067400A (en) * | 2016-11-30 | 2017-08-18 | 南京航空航天大学 | A kind of bianry image method for marking connected region based on the distance of swimming |
| CN109584262A (en) * | 2018-12-15 | 2019-04-05 | 中国科学院深圳先进技术研究院 | Cloud detection method of optic, device and electronic equipment based on remote sensing image |
| CN110738106A (en) * | 2019-09-05 | 2020-01-31 | 天津大学 | optical remote sensing image ship detection method based on FPGA |
| CN117152458A (en) * | 2023-11-01 | 2023-12-01 | 南京盛视工业技术有限公司 | Method and system for rapidly extracting connected domain based on travel coding |
| CN117152458B (en) * | 2023-11-01 | 2024-01-30 | 南京盛视工业技术有限公司 | Method and system for rapidly extracting connected domain based on travel coding |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107633526B (en) | Image tracking point acquisition method and device and storage medium | |
| JP2020119550A (en) | Graphical reference marker identification suitable for augmented reality, virtual reality, and robotics | |
| US20190014301A1 (en) | Image processing apparatus, image processing method thereof and storage medium | |
| CN104574448A (en) | Method for identifying connected pixel blocks | |
| WO2016065701A1 (en) | Image text recognition method and device | |
| CN111626238B (en) | Text recognition method, electronic device and storage medium | |
| JP2007317184A (en) | Two-dimensional bar code, and encoding and decoding method thereof | |
| RU2729399C1 (en) | Method for detection and recognition of visual markers of long range and high density | |
| CN104778741A (en) | Method and device for converting two-dimensional figure into three-dimensional figure | |
| CN110827189B (en) | Watermark removing method and system for digital image or video | |
| US20180096480A1 (en) | Image processing apparatus and image processing method | |
| US20240020923A1 (en) | Positioning method based on semantic information, device and computer-readable storage medium | |
| US8798391B2 (en) | Method for pre-processing an image in facial recognition system | |
| CN111168676B (en) | Mechanical arm hand-eye cooperation painting method and device, painting robot and medium | |
| CN110348351B (en) | Image semantic segmentation method, terminal and readable storage medium | |
| US11699053B2 (en) | Narrow-strip 2-dimensional bar codes, methods, apparatuses, and devices for generating and identifying narrow-strip 2-dimensional bar codes | |
| KR20070014767A (en) | Id judgment method by using extension type visual marker including direrction information | |
| CN111292341B (en) | Image annotation method, image annotation device and computer storage medium | |
| CN112967359A (en) | Data labeling method and device, terminal equipment and storage medium | |
| JP4871918B2 (en) | Image conversion apparatus, image conversion method, image conversion program, and computer-readable recording medium recording the image conversion program | |
| CN110659587A (en) | Marker, marker identification method, marker identification device, terminal device and storage medium | |
| CN115953563A (en) | Three-dimensional model completion repairing method and system based on point cloud vectorization framework matching | |
| Han et al. | L-split marker for augmented reality in aircraft assembly | |
| CN112434632B (en) | Pattern recognition method, intelligent terminal and storage medium | |
| CN113095104A (en) | Defective two-dimensional code positioning method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150429 |
|
| RJ01 | Rejection of invention patent application after publication |