CN109711476A - A kind of image data mark color spot modified method automatically - Google Patents
A kind of image data mark color spot modified method automatically Download PDFInfo
- Publication number
- CN109711476A CN109711476A CN201811634992.8A CN201811634992A CN109711476A CN 109711476 A CN109711476 A CN 109711476A CN 201811634992 A CN201811634992 A CN 201811634992A CN 109711476 A CN109711476 A CN 109711476A
- Authority
- CN
- China
- Prior art keywords
- index value
- image
- color spot
- image data
- modified method
- 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
- 238000000034 method Methods 0.000 title claims abstract description 17
- 239000011159 matrix material Substances 0.000 claims abstract description 14
- 238000013507 mapping Methods 0.000 claims description 5
- 238000006748 scratching Methods 0.000 description 2
- 230000002393 scratching effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The present invention relates to technical field of image processing, more particularly to a kind of image data marks color spot modified method automatically, it is characterized in that knowing method for distinguishing by connected graph, obtain the corresponding image block of different index value in index value matrix, again by the number of pixels of identification image block, number of pixels is replaced with into the pixel index value closed on less than the corresponding index value of a certain number of image blocks.
Description
Technical field
The present invention relates to technical field of image processing more particularly to a kind of image data to mark color spot modified side automatically
Method.
Background technique
Image data annotation process is deducted by the stingy figure software such as Photoshop, since two objects for scratching figure are tight
When contiguity touching, the figure plucked out can have the pixel for being not belonging to any one object on a small quantity, i.e. color spot.These pixels naked eyes can not be known
Not, but on the training of machine learning model very big influence is caused.
Summary of the invention
The technical problem to be solved by the present invention is to overcome the deficiencies in the prior art, providing one kind can be by color spot
The image data of removal marks color spot modified method automatically.
The present invention is to be achieved by the following technical programs:
A kind of image data mark color spot modified method automatically, which comprises the following steps:
A. image is read, the corresponding index value matrix of image and color mapping matrix are obtained；
B. method for distinguishing is known by connected graph, obtains the corresponding image block of different index value in the index value matrix of step a；
C. the number of pixels of image block is identified, if number of pixels is less than setting value, by the corresponding index of the image block
Value replaces with the index value for closing on the pixel of the image block.
Preferably, setting value 100.
The beneficial effects of the present invention are:
The present invention reads picture at index value and color mapping matrix, and knowing method for distinguishing by connected graph will not belong on a small quantity
It is identified in the pixel of any object, and is disposed adjacent to the index value of pixel, this method is compensated for using stingy figure software etc.
Tool can not find the difficulty of color spot problem, while the energy of mark person being concentrated on scratching in figure task, improve annotating efficiency.
Detailed description of the invention
Fig. 1 is flow diagram of the invention.
Specific embodiment
In order to make those skilled in the art more fully understand technical solution of the present invention, with reference to the accompanying drawing and most
The present invention is described in further detail for good embodiment.
As shown, the present invention the following steps are included:
A. image is read, the corresponding index value matrix of image and color mapping matrix are obtained, index value matrix is pixel
The matrix that the index value of corresponding color is formed, the index value of any color are equal to color line number where in color mapping matrix
Numerical value subtract one；
B. method for distinguishing is known by connected graph, obtains the corresponding image block of different index value in the index value matrix of step a；
C. distinguish the number of pixels of multiple images block obtained in identification step b, if number of pixels is less than setting value,
The corresponding index value of the image block is replaced with to the index value for closing on the pixel of the image block.
Preferably, setting value 100, the pixel number of usual color spot can be completed by this method in image less than 100
The automatic amendment of color spot.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (2)
1. a kind of image data marks color spot modified method automatically, which comprises the following steps:
A. image is read, the corresponding index value matrix of image and color mapping matrix are obtained；
B. method for distinguishing is known by connected graph, obtains the corresponding image block of different index value in the index value matrix of step a；
C. identify that the number of pixels of image block replaces the corresponding index value of the image block if number of pixels is less than setting value
It is changed to the index value for closing on the pixel of the image block.
2. a kind of image data according to claim 1 marks color spot modified method automatically, which is characterized in that setting value
It is 100.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811634992.8A CN109711476A (en) | 2018-12-29 | 2018-12-29 | A kind of image data mark color spot modified method automatically |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811634992.8A CN109711476A (en) | 2018-12-29 | 2018-12-29 | A kind of image data mark color spot modified method automatically |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109711476A true CN109711476A (en) | 2019-05-03 |
Family
ID=66258233
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811634992.8A Pending CN109711476A (en) | 2018-12-29 | 2018-12-29 | A kind of image data mark color spot modified method automatically |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109711476A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114495824A (en) * | 2022-01-26 | 2022-05-13 | 苇创微电子(上海)有限公司 | Method and system for correcting edge color cast of OLED display image and character, storage medium and processor |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002135570A (en) * | 2000-10-25 | 2002-05-10 | Canon Inc | Image processing method and image forming device |
| US6538771B1 (en) * | 1997-01-21 | 2003-03-25 | Minolta Co., Ltd. | Image processor |
| JP2009099098A (en) * | 2007-10-19 | 2009-05-07 | Toshiba Corp | Computer graphics drawing device and drawing method |
| CN102300095A (en) * | 2011-09-15 | 2011-12-28 | 重庆邮电大学 | Fast compression coding method for hyperspectral signal and image compression method |
| CN102508923A (en) * | 2011-11-22 | 2012-06-20 | 北京大学 | Automatic video annotation method based on automatic classification and keyword marking |
| US8599214B1 (en) * | 2009-03-20 | 2013-12-03 | Teradici Corporation | Image compression method using dynamic color index |
| CN104751489A (en) * | 2015-04-09 | 2015-07-01 | 苏州阔地网络科技有限公司 | Grid-based relay tracking method and device in online class |
| WO2015120050A1 (en) * | 2014-02-10 | 2015-08-13 | Microsoft Technology Licensing, Llc | Adaptive screen and video coding scheme |
| CN105335989A (en) * | 2014-06-11 | 2016-02-17 | 富士通株式会社 | Image coding method and image coding apparatus |
| CN107169508A (en) * | 2017-04-17 | 2017-09-15 | 杭州电子科技大学 | A kind of cheongsam Image emotional semantic method for recognizing semantics based on fusion feature |
| CN108876804A (en) * | 2017-10-12 | 2018-11-23 | 北京旷视科技有限公司 | It scratches as model training and image are scratched as methods, devices and systems and storage medium |
-
2018
- 2018-12-29 CN CN201811634992.8A patent/CN109711476A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6538771B1 (en) * | 1997-01-21 | 2003-03-25 | Minolta Co., Ltd. | Image processor |
| JP2002135570A (en) * | 2000-10-25 | 2002-05-10 | Canon Inc | Image processing method and image forming device |
| JP2009099098A (en) * | 2007-10-19 | 2009-05-07 | Toshiba Corp | Computer graphics drawing device and drawing method |
| US8599214B1 (en) * | 2009-03-20 | 2013-12-03 | Teradici Corporation | Image compression method using dynamic color index |
| CN102300095A (en) * | 2011-09-15 | 2011-12-28 | 重庆邮电大学 | Fast compression coding method for hyperspectral signal and image compression method |
| CN102508923A (en) * | 2011-11-22 | 2012-06-20 | 北京大学 | Automatic video annotation method based on automatic classification and keyword marking |
| WO2015120050A1 (en) * | 2014-02-10 | 2015-08-13 | Microsoft Technology Licensing, Llc | Adaptive screen and video coding scheme |
| CN105335989A (en) * | 2014-06-11 | 2016-02-17 | 富士通株式会社 | Image coding method and image coding apparatus |
| CN104751489A (en) * | 2015-04-09 | 2015-07-01 | 苏州阔地网络科技有限公司 | Grid-based relay tracking method and device in online class |
| CN107169508A (en) * | 2017-04-17 | 2017-09-15 | 杭州电子科技大学 | A kind of cheongsam Image emotional semantic method for recognizing semantics based on fusion feature |
| CN108876804A (en) * | 2017-10-12 | 2018-11-23 | 北京旷视科技有限公司 | It scratches as model training and image are scratched as methods, devices and systems and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114495824A (en) * | 2022-01-26 | 2022-05-13 | 苇创微电子(上海)有限公司 | Method and system for correcting edge color cast of OLED display image and character, storage medium and processor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102542275B (en) | Automatic identification method for identification photo background and system thereof | |
| CN110930427B (en) | Image segmentation method, device and storage medium based on semantic contour information | |
| CN107590447A (en) | A kind of caption recognition methods and device | |
| CN105279506B (en) | The localization method of language of the Manchus word central axes | |
| CN114240939B (en) | Method, system, equipment and medium for detecting appearance defects of mainboard components | |
| CN108509988B (en) | Test paper score automatic statistical method and device, electronic equipment and storage medium | |
| CN113160222A (en) | Production data identification method for industrial information image | |
| CN110210577B (en) | Deep learning and identification method for dense bird group | |
| CN112446262A (en) | Text analysis method, text analysis device, text analysis terminal and computer-readable storage medium | |
| CN106570515A (en) | Method and system for treating medical images | |
| CN115273115A (en) | Document element labeling method and device, electronic equipment and storage medium | |
| CN109800750A (en) | A kind of character area mask method of the text based on morphological image for rule composing | |
| CN104700417A (en) | Computer image based automatic identification method of timber knot flaws | |
| CN109711476A (en) | A kind of image data mark color spot modified method automatically | |
| Tang et al. | Leaf extraction from complicated background | |
| CN110956147A (en) | Method and device for generating training data | |
| CN116310548A (en) | Method for detecting invasive plant seeds in imported seed products | |
| CN112686872B (en) | Wood counting method based on deep learning | |
| CN106248634A (en) | Fruit exocuticle glossiness measurement apparatus and method | |
| CN111316934B (en) | Bee birth and fertility analyzer and method | |
| CN109934152B (en) | Improved small-bent-arm image segmentation method for sign language image | |
| CN116664519A (en) | Welding defect detection method, equipment and storage medium based on weak supervision learning | |
| CN115578333A (en) | Domestic ceramic surface defect detection method based on region division and yolo5 | |
| CN115063405A (en) | Method, system, electronic device and storage medium for detecting defects on surface of steel | |
| CN112270683B (en) | IHC digital preview image identification and organization foreground segmentation method and system |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190503 |