CN110084746A - A kind of knowledge figure pattern splicing method of mosaic machine people - Google Patents
A kind of knowledge figure pattern splicing method of mosaic machine people Download PDFInfo
- Publication number
- CN110084746A CN110084746A CN201910192851.3A CN201910192851A CN110084746A CN 110084746 A CN110084746 A CN 110084746A CN 201910192851 A CN201910192851 A CN 201910192851A CN 110084746 A CN110084746 A CN 110084746A
- Authority
- CN
- China
- Prior art keywords
- mosaic
- color
- block
- pixels
- machine people
- 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 25
- 238000010191 image analysis Methods 0.000 claims abstract description 10
- 239000000463 material Substances 0.000 claims description 11
- 238000003384 imaging method Methods 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 6
- 230000037452 priming Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000004040 coloring Methods 0.000 description 2
- 229910002056 binary alloy Inorganic materials 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- 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
-
- 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
- G06T2207/20021—Dividing image into blocks, subimages or windows
Abstract
The invention discloses the knowledge figure pattern splicing methods of mosaic machine people a kind of, comprising the following steps: (1) image pickup, (2) image analysis, (3) color assignment and (4) picture mosaic.Knowledge figure pattern splicing method of the invention is by obtaining target image and being analyzed and processed to target image, target image is reasonably resolved into the executable block of pixels mode of robot by image analysis, and accurately number forming position-color code numerical value is carried out rationally to block of pixels, each block of pixels corresponds to an independent position-color code numerical value, and mosaic machine people is made to complete picture mosaic like clockwork.
Description
Technical field
The invention belongs to robot picture mosaic technical field, in particular to the knowledge figure picture mosaic side of a kind of mosaic machine people
Method.
Background technique
With the rapid development of science and technology, the development field of intelligent robot is more and more wider, such as with robot according to obtaining
The picture taken carries out picture mosaic.How by known image confidence be converted into the acceptable information of robot and according to image information it is complete
It is the technological difficulties of jigsaw puzzle robot development at picture mosaic reduction.
Summary of the invention
The present invention the above-mentioned prior art there are aiming at the problem that, the knowledge figure picture mosaic of mosaic machine people a kind of is provided
Method.
A kind of knowledge figure pattern splicing method of mosaic machine people, comprising the following steps:
(1) image pickup: mosaic machine people obtains known image from the external world and stores to database；
(2) image analysis: the fritter that the image thinning received resolves into array is formed block of pixels by database, and to every
Independent number i is arranged in a block of pixelsxy, x is the line number where block of pixels, and y is the columns where block of pixels；
(3) color assignment: assignment is carried out using color of the RGB color mode to each block of pixels, forming position-color is compiled
Number value pair；
(4) picture mosaic: mosaic machine people is according to position-color code numerical value to from the mosaic color lump of Material Staging Area
Corresponding color lump is picked up, one-to-one picture mosaic is carried out, to realize knowledge figure picture mosaic.
It is further improved as ground of the invention, the image pickup in the step (1) includes shooting imaging, scanning imagery
It is imaged with transmission.
It is further improved as ground of the invention, the camera shooting by being arranged on mosaic machine people is imaged in the shooting
Head is completed, and the memory of the camera is connect with the database of mosaic machine people；The scanning imagery is by being arranged in horse
It matches the scanner outside gram jigsaw puzzle robot to complete, the memory of the scanner and the database of mosaic machine people connect
It connects；The transmission imaging is completed by shared network, and external electronic device is by the same network to mosaic machine people's
Image is transmitted in data cloud, and the data cloud is connect with the database of mosaic machine people.
It is further improved as ground of the invention, image analysis includes following steps in step (2):
(2-1) Image Adjusting: the image that will acquire is adjusted by long side, makes 5 cun of size of long side, the size and length of short side
Side scales in proportion；
(2-2) pixel is decomposed: on the basis of the long side of image, being decomposed by every cun of 20 block of pixels, the short side of image
It is decomposed simultaneously by same datum, obtains the block of pixels of array；
(2-3) pixel block number: independent number i is arranged to each block of pixelsxy, x is the line number where block of pixels, and y is
Columns where block of pixels.
It is further improved as ground of the invention, color assignment includes the following steps: in the step (3)
(3-1) color picks up and statistics: picking up institute's colored in each block of pixels, and calculates the face of each color
Product size；
(3-2) fixation: the size of every kind of color in one block of pixels of comparison takes the maximum color of area to be set to the picture
The color of plain block；
(3-3) assignment: priming color value is assigned to block of pixels after fixation, by the mosaic of the priming color value and Material Staging Area
The color value of color lump compares, and calculates color difference, and the color value of the minimum corresponding mosaic color lump of gained color difference positions picture
The color value of plain block.
It is further improved as ground of the invention, the color value letter of the mosaic color lump of Material Staging Area in the step (3-3)
Breath is stored in the database of mosaic machine people.
It is further improved as ground of the invention, the picture mosaic of the step (4) is from i11It indulges and is arranged successively after beginning is first horizontal, institute
Picture puzzle is stated to be equipped with and block of pixels i11Corresponding datum mark.
The invention has the benefit that knowledge figure pattern splicing method of the invention by obtain target image and to target image into
Target image is reasonably resolved into the executable block of pixels mode of robot by image analysis by row analysis processing, and to picture
Plain block carries out rationally accurately number forming position-color code numerical value, the corresponding independent position-face of each block of pixels
Color number numerical value makes mosaic machine people complete picture mosaic like clockwork.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention,
Technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is the present invention one
Divide embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making
Every other embodiment obtained, shall fall within the protection scope of the present invention under the premise of creative work.
Embodiment
A kind of knowledge figure pattern splicing method of mosaic machine people, comprising the following steps:
(1) image pickup: mosaic machine people obtains known image from the external world and stores to database；
(2) image analysis: the fritter that the image thinning received resolves into array is formed block of pixels by database, and to every
Independent number i is arranged in a block of pixelsxy, x is the line number where block of pixels, and y is the columns where block of pixels；
(3) color assignment: assignment is carried out using color of the RGB color mode to each block of pixels, forming position-color is compiled
Number value pair；
(4) picture mosaic: mosaic machine people is according to position-color code numerical value to from the mosaic color lump of Material Staging Area
Corresponding color lump is picked up, one-to-one picture mosaic is carried out, to realize knowledge figure picture mosaic.
Traditional color of image is more and miscellaneous, and no any rule can be sayed, robot can not distinguishing colours extraction information.
What robot can be performed is single pixel, so needing to convert images into the pixel picture mosaic being made of several block of pixels, RGB
For traditional color mode, R represents red, and G represents green, and B represents blue, these three primary colours numberical ranges are 0~255,
Each color is all represented by (m, n, k), and m is the color value of R, and n is the color value of G, and k is the color value of B, ultimately forms ixy(m, n,
K) position-color code numerical value pair can mutually be converted with binary system, the identifiable information-oriented language of computer be formed, by not
Combination with numerical value can identify different colouring informations.Knowledge figure pattern splicing method of the invention is by obtaining target image and to mesh
Logo image is analyzed and processed, and target image is reasonably resolved into the executable block of pixels mould of robot by image analysis
Formula, and accurately number forming position-color code numerical value pair is carried out rationally to block of pixels, corresponding one of each block of pixels is solely
Vertical position-color code numerical value pair makes mosaic machine people complete picture mosaic like clockwork.
Further, the image pickup in the step (1) includes shooting imaging, scanning imagery and transmission imaging.It is abundant
The acquisition source of image, thus the application environment of abundant mosaic machine people.
Further, the shooting imaging is completed by the camera being arranged on mosaic machine people, the camera shooting
The memory of head is connect with the database of mosaic machine people；The scanning imagery is by being arranged in outside mosaic machine people
The scanner in portion is completed, and the memory of the scanner is connect with the database of mosaic machine people；Transmission imaging by
Shared network is completed, and external electronic device transmits image to the data cloud of mosaic machine people by the same network,
The data cloud is connect with the database of mosaic machine people.The acquiring way of all external images is all connected with mosaic
The database of jigsaw puzzle robot is handled, directly quickly by the internal processor of mosaic machine people.
Further, image analysis includes following steps in step (2):
(2-1) Image Adjusting: the image that will acquire is adjusted by long side, makes 5 cun of size of long side, the size and length of short side
Side scales in proportion；
(2-2) pixel is decomposed: on the basis of the long side of image, being decomposed by every cun of 20 block of pixels, the short side of image
It is decomposed simultaneously by same datum, obtains the block of pixels of array；
(2-3) pixel block number: independent number i is arranged to each block of pixelsxy, x is the line number where block of pixels, and y is
Columns where block of pixels.
Since the image acquiring way of mosaic machine people is abundant, the resolution ratio of image obtained and image it is big
It is small multifarious, it is unfavorable for robot advanced treating image.Image size is first tuned into same standard before analysis, so that subsequent
Pixel disintegration faster carries out, and improves the analysis speed of robot, reduces operation load.
Further, color assignment includes the following steps: in the step (3)
(3-1) color picks up and statistics: picking up institute's colored in each block of pixels, and calculates the face of each color
Product size；
(3-2) fixation: the size of every kind of color in one block of pixels of comparison takes the maximum color of area to be set to the picture
The color of plain block；
(3-3) assignment: priming color value is assigned to block of pixels after fixation, by the mosaic of the priming color value and Material Staging Area
The color value of color lump compares, and calculates color difference, and the color value of the minimum corresponding mosaic color lump of gained color difference positions picture
The color value of plain block.
What the image that robot is stored in database was made of pixel, since pixel is too small, robot is directly swept
A large amount of block of pixels can be obtained by retouching, and be unfavorable for actual picture mosaic work, so needing to carry out picture mosaic with block of pixels simulation pixel point.
Block of pixels actually contains many pixels, and each pixel has unique color value, so in people's block of pixels
Many colouring informations can be had, this is the difference of block of pixels and pixel, and robot passes through face all on scanning element block
Color information is simultaneously statisticallyd analyze, and is carried out color assignment to block of pixels using the method that maximum area replaces, is achieved pixel
The function of point, is just converted into the identifiable language message of robot for block of pixels in this way.
Further, the color value information of the mosaic color lump of Material Staging Area is stored in mosaic in the step (3-3)
In the database of jigsaw puzzle robot.Due to the diversity of color, the color value that mosaic machine people assigns block of pixels can
Can be there is no with the mosaic color lump of Material Staging Area, in picture mosaic, robot is unable to complete the identification of mosaic color lump, institute in this way
When needing to carry out final assignment to block of pixels, need when final assignment to compare meter with the color value information of mosaic color lump
It calculates, so the color value information for storing the mosaic color lump of Material Staging Area in the database of mosaic machine people can direct quilt
It calls, improves assignment efficiency.
Further, the picture mosaic of the step (4) is from i11Start it is first horizontal after indulge and be arranged successively, the picture puzzle be equipped with
Block of pixels i11Corresponding datum mark.The sequence of picture mosaic ought be the sequence consensus with image recognition, and agreement picture mosaic datum mark is on the one hand
It is that robot picture mosaic is facilitated to identify position, on the other hand to prevent picture mosaic be mosaic image biased contact picture mosaic desktop and can not
Smoothly complete picture mosaic.
It should be noted that, in this document, such as first and second or the like relational terms are used merely to one if it exists
A entity or operation with another entity or operate distinguish, without necessarily requiring or implying these entities or operation it
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant are intended to
Cover non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or setting
Standby intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in the process, method, article or apparatus that includes the element.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments
Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation
Technical solution documented by example is modified or equivalent replacement of some of the technical features；And these modification or
Replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (7)
1. the knowledge figure pattern splicing method of mosaic machine people a kind of, it is characterised in that, comprising the following steps:
(1) image pickup: mosaic machine people obtains known image from the external world and stores to database；
(2) image analysis: the fritter that the image thinning received resolves into array is formed block of pixels by database, and to each picture
Independent number i is arranged in plain blockxy, x is the line number where block of pixels, and y is the columns where block of pixels；
(3) assignment, forming position-color code number color assignment: are carried out using color of the RGB color mode to each block of pixels
Value pair；
(4) picture mosaic: mosaic machine people picks up according to position-color code numerical value to from the mosaic color lump of Material Staging Area
Corresponding color lump, carries out one-to-one picture mosaic, to realize knowledge figure picture mosaic.
2. the knowledge figure pattern splicing method of mosaic machine people according to claim 1 a kind of, it is characterised in that, it is described
Image pickup in step (1) includes shooting imaging, scanning imagery and transmission imaging.
3. the knowledge figure pattern splicing method of mosaic machine people according to claim 2 a kind of, it is characterised in that, it is described
Shooting imaging is completed by the camera being arranged on mosaic machine people, the memory and Mosaic pattern machine of the camera
The database of device people connects；The scanning imagery is completed by the scanner outside mosaic machine people is arranged in, described to sweep
The memory for retouching instrument is connect with the database of mosaic machine people；The transmission imaging is completed by shared network, external electrical
Equipment transmits image to the data cloud of mosaic machine people by the same network, and the data cloud and mosaic are spelled
The database of figure robot connects.
4. the knowledge figure pattern splicing method of mosaic machine people according to claim 1 a kind of, it is characterised in that, step
(2) image analysis includes following steps in:
(2-1) Image Adjusting: the image that will acquire is adjusted by long side, makes 5 cun of size of long side, and the size and long side of short side are same
Scaling；
(2-2) pixel is decomposed: on the basis of the long side of image, being decomposed by every cun of 20 block of pixels, the short side of image is simultaneously
It is decomposed by same datum, obtains the block of pixels of array；
(2-3) pixel block number: independent number i is arranged to each block of pixelsxy, x is the line number where block of pixels, and y is pixel
Columns where block.
5. the knowledge figure pattern splicing method of mosaic machine people according to claim 1 a kind of, it is characterised in that, it is described
Color assignment includes the following steps: in step (3)
(3-1) color picks up and statistics: picking up institute's colored in each block of pixels, and the area for calculating each color is big
It is small；
(3-2) fixation: the size of every kind of color in one block of pixels of comparison takes the maximum color of area to be set to the block of pixels
Color；
(3-3) assignment: priming color value is assigned to block of pixels after fixation, by the mosaic color lump of the priming color value and Material Staging Area
Color value compare, calculate color difference, the color value of the minimum corresponding mosaic color lump of gained color difference positions block of pixels
Color value.
6. the knowledge figure pattern splicing method of mosaic machine people according to claim 5 a kind of, it is characterised in that, it is described
The color value information of the mosaic color lump of Material Staging Area is stored in the database of mosaic machine people in step (3-3).
7. the knowledge figure pattern splicing method of mosaic machine people according to claim 1 a kind of, it is characterised in that, it is described
The picture mosaic of step (4) is from i11It indulges and is arranged successively after beginning is first horizontal, the picture puzzle is equipped with and block of pixels i11Corresponding benchmark
Point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910192851.3A CN110084746A (en) | 2019-03-14 | 2019-03-14 | A kind of knowledge figure pattern splicing method of mosaic machine people |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910192851.3A CN110084746A (en) | 2019-03-14 | 2019-03-14 | A kind of knowledge figure pattern splicing method of mosaic machine people |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110084746A true CN110084746A (en) | 2019-08-02 |
Family
ID=67413185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910192851.3A Pending CN110084746A (en) | 2019-03-14 | 2019-03-14 | A kind of knowledge figure pattern splicing method of mosaic machine people |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084746A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112017169A (en) * | 2020-08-25 | 2020-12-01 | 重庆大学 | Processing method of mosaic picture |
| CN112562571A (en) * | 2020-12-26 | 2021-03-26 | 文思海辉智科科技有限公司 | Image display method, image display device, computer equipment, storage medium and assembled dot matrix screen |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009026015A1 (en) * | 2007-08-20 | 2009-02-26 | Edward Acworth | Method and apparatus for making a mosaic |
| CN101739697A (en) * | 2008-11-25 | 2010-06-16 | 王源源 | Synthesis method of picture mosaic pattern and system therefor |
| CN106023081A (en) * | 2016-05-21 | 2016-10-12 | 广东邦宝益智玩具股份有限公司 | Mosaic processing method of 2D picture |
| CN107009367A (en) * | 2017-03-01 | 2017-08-04 | 江苏哈工海渡工业机器人有限公司 | One kind instruction humanoid robot puzzle system and picture mosaic all-in-one |
-
2019
- 2019-03-14 CN CN201910192851.3A patent/CN110084746A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009026015A1 (en) * | 2007-08-20 | 2009-02-26 | Edward Acworth | Method and apparatus for making a mosaic |
| CN101739697A (en) * | 2008-11-25 | 2010-06-16 | 王源源 | Synthesis method of picture mosaic pattern and system therefor |
| CN106023081A (en) * | 2016-05-21 | 2016-10-12 | 广东邦宝益智玩具股份有限公司 | Mosaic processing method of 2D picture |
| CN107009367A (en) * | 2017-03-01 | 2017-08-04 | 江苏哈工海渡工业机器人有限公司 | One kind instruction humanoid robot puzzle system and picture mosaic all-in-one |
Non-Patent Citations (1)
| Title |
|---|
| 吴旭虹等: "基于色彩传递的图像马赛克算法研究", 《计算机工程》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112017169A (en) * | 2020-08-25 | 2020-12-01 | 重庆大学 | Processing method of mosaic picture |
| CN112562571A (en) * | 2020-12-26 | 2021-03-26 | 文思海辉智科科技有限公司 | Image display method, image display device, computer equipment, storage medium and assembled dot matrix screen |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110502986A (en) | Identify character positions method, apparatus, computer equipment and storage medium in image | |
| CN114240939B (en) | Method, system, equipment and medium for detecting appearance defects of mainboard components | |
| CN108872265A (en) | Detection method, apparatus and system | |
| CN101946519A (en) | Image processing apparatus, imaging device, correction factor calculation method and image processing program | |
| CN110084746A (en) | A kind of knowledge figure pattern splicing method of mosaic machine people | |
| CN110991297A (en) | Target positioning method and system based on scene monitoring | |
| CN108616700A (en) | Image processing method and device, electronic equipment, computer readable storage medium | |
| CN208366871U (en) | Detection system | |
| CN101561316B (en) | On-line test visual data processing system based on region of interest (ROI) | |
| CN108388898A (en) | Character identifying method based on connector and template | |
| CN106791498B (en) | Image position method, lens array imaging method and device | |
| CN116343100A (en) | Target identification method and system based on self-supervision learning | |
| CN113592975B (en) | Aerial view rapid mapping system based on remote sensing | |
| CN115482462A (en) | Concrete crack identification system and method based on deep learning | |
| CN112215319B (en) | Two-dimensional code of color mark characteristic graph and identification method thereof | |
| CN111079617B (en) | Poultry identification method and device, readable storage medium and electronic equipment | |
| CN111784779A (en) | Checkerboard image recognition and positioning system and method based on convolutional neural network and nested contour recognition | |
| CN111476304A (en) | Image data processing method and device | |
| CN116245962B (en) | Data extraction system and method for wireless transmission to blockchain server | |
| CN115063605B (en) | Method for identifying color printing package by using electronic equipment | |
| KR102596670B1 (en) | System for providing augmented reality content using products printed with ar markers | |
| CN116866638B (en) | Intelligent video processing method and system based on images | |
| CN114897910B (en) | Internal reference and external reference combined optical fiber color mixing identification method, device, equipment and medium | |
| CN102456128B (en) | Stereoscopic vision dice point identification system and method in uncontrolled environments | |
| CN113989897A (en) | Human eye positioning method based on thermodynamic diagram of neural network model |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 230000 southwest of the intersection of Yunhu road and Jixian Road, Feixi Economic Development Zone, Hefei City, Anhui Province Applicant after: HEFEI PANSHI AUTOMATION TECHNOLOGY Co.,Ltd. Address before: 230000, Anhui City, Hefei Province opened peach blossom industrial park expansion zone, busy road, Gong cast Heng Industrial Plaza (phase two), A-13 West Applicant before: HEFEI PANSHI AUTOMATION TECHNOLOGY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190802 |