CN112733621A - Map high-precision information identification method - Google Patents
Map high-precision information identification method Download PDFInfo
- Publication number
- CN112733621A CN112733621A CN202011560048.XA CN202011560048A CN112733621A CN 112733621 A CN112733621 A CN 112733621A CN 202011560048 A CN202011560048 A CN 202011560048A CN 112733621 A CN112733621 A CN 112733621A
- Authority
- CN
- China
- Prior art keywords
- road
- map
- roads
- colors
- characters
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/42—Document-oriented image-based pattern recognition based on the type of document
- G06V30/422—Technical drawings; Geographical maps
-
- 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
- G06V10/56—Extraction of image or video features relating to colour
Abstract
The invention discloses a map high-precision information identification method, which comprises the following steps: s1, extracting roads, S2, unifying the colors of the roads, S3, eliminating characters in the roads, S4, smoothing the roads, S5, refining the roads, S6, vectorizing the roads, S7, and producing vectorized files and transmitting the vectorized files to terminal equipment. According to the map high-precision information identification method, the road is identified and extracted in a mode of combining the circularity and the color characteristics, characters in the road are removed in the extraction process, the road is smoothed, the accuracy and effectiveness of the road identification are guaranteed, and the display effect is improved.
Description
Technical Field
The invention relates to the technical field of map identification methods, in particular to a map high-precision information identification method.
Background
The map is a graph which is drawn according to a certain drawing rule by using a drawing method and is integrated on a certain carrier through drawing to express the spatial distribution, the relation and the development change state in time of various things on the earth (or other celestial bodies).
The map is a graph or image which selectively represents a plurality of phenomena of Earth (Earth) (or other stars) on a plane or a spherical surface in a two-dimensional (2D) or multi-dimensional (3D) form and means according to a certain rule, has strict mathematical basis, symbol system and character annotation, and can scientifically reflect the distribution characteristics and the mutual relations of the natural and social economic phenomena by using the general principle of the map. The definition of the map at the present stage is as follows: the image symbol model reflecting the objective reality is expressed in a certain Math (Math) rule (namely modeling), symbolization and abstraction, or is called as a graphic mathematic model. The map is based on a certain mathematical rule, and uses map language to reduce and reflect the natural and human phenomena on the earth (or other stars) on the plane by drawing synthesis, and reflects the spatial distribution, combination, connection, quantity and quality characteristics of various phenomena and the development change of various phenomena in time.
In color maps, identifying and extracting a certain geographic element by using a difference in color is a relatively natural extraction method, and is also the most commonly used method in map identification. However, it is not easy for the computer to layer the datamation map obtained from the scanner according to colors, because the paper map may cause the color difference of the original same color content due to printing or use, and may cause the obtained color to slightly change due to the fact that the placement of the map cannot be absolutely flat during the scanning process. Although the color differences and changes can be ignored when people read the map and the map is correctly identified without being influenced by the color differences and changes, the differences and changes become a problem which cannot be ignored and even need to be solved intensively when the work is completed by a computer. Therefore, if the elements in the map are recognized by colors alone, many errors may be caused, resulting in a low recognition rate.
Disclosure of Invention
The invention mainly aims to provide a map high-precision information identification method which can effectively solve the problems in the background technology.
In order to achieve the purpose, the invention adopts the technical scheme that:
a map high-precision information identification method comprises the following steps:
s1, extracting roads;
s2, unifying the colors of the roads;
s3, eliminating characters in the road;
s4, smoothing the road;
s5, road refinement;
s6, road vectorization;
and S7, producing the vectorized file and transmitting the vectorized file to the terminal equipment.
Preferably, the step S1 of road extraction includes the steps of:
s11, scanning the map by a scanner and transmitting the map to a computer;
s12, according to the scanned map, according to the calculation formula of the image degree, the circularity of each road is calculated by using tool software;
s13, marking areas with the same or similar colors as the road;
and S14, extracting the road, rescanning the image, setting unmarked pixels as white pixels, calculating the circularity of each area of the label value, setting all the pixels of the connecting components of the area as the white pixels if the result is not between 0 and 0.2, otherwise, not changing, and outputting the road image.
Preferably, in step S2, the colors of the roads are unified, the legend of the map is used to extract the colors of the legend roads, the entire map is scanned to calculate the distances between the colors of the roads in the map example and the colors in the map, if the distance is smaller than a smaller threshold, the color in the map is determined to identify the road, and the color is replaced with white.
Preferably, in step S3, the characters in the road are erased, and the characters are erased by erosion and dilation operations using grayscale morphology.
Preferably, in the process of eliminating the text, the scanning can be carried out for a plurality of times until the noise is completely removed from the map.
Preferably, in the step S4, the image obtained in step S3 should be scanned first, and if the number of black pixels connected between two white pixels is less than 3, the black pixels are replaced with white pixels, and during scanning, line scanning is performed first, and then line-by-line scanning is performed.
Preferably, the road refinement in step S5 is implemented by using Hilditch classical refinement algorithm.
Preferably, the road vector in step S6 is a contour tracing method.
Compared with the prior art, the invention has the following beneficial effects:
the high-precision map information identification method provided by the invention has the advantages that the method for identifying and extracting the road is realized by combining the circularity and the color characteristics, the characters in the road are removed in the extraction process, the road identification accuracy and effectiveness are ensured by the step of smoothing the road, and the display effect is improved.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.
A map high-precision information identification method comprises the following steps:
s1, extracting roads;
s2, unifying the colors of the roads;
s3, eliminating characters in the road;
s4, smoothing the road;
s5, road refinement;
s6, road vectorization;
and S7, producing the vectorized file and transmitting the vectorized file to the terminal equipment.
The step S1 road extraction includes the steps of:
s11, scanning the map by a scanner and transmitting the map to a computer;
s12, according to the scanned map, according to the calculation formula of the image degree, the circularity of each road is calculated by using tool software;
s13, marking areas with the same or similar colors as the road;
and S14, extracting the road, rescanning the image, setting unmarked pixels as white pixels, calculating the circularity of each area of the label value, setting all the pixels of the connecting components of the area as the white pixels if the result is not between 0 and 0.2, otherwise, not changing, and outputting the road image.
In step S2, unifying the colors of the roads, extracting the colors of the roads in the map by using the legend of the map, scanning the entire map to calculate the distances between the colors of the roads in the map and the colors in the map, if the distance is less than a small threshold, identifying the road marked by the color in the map, and replacing the color with white.
In step S3, characters in the road are erased, and the characters are erased by erosion and expansion operations using grayscale morphology.
In the process of eliminating text, the scan may be performed several times until the noise is completely removed from the map.
Step S4 is to smooth the road, the image obtained in step S3 should be scanned first, if the number of black pixels connected between two white pixels is less than 3, the black pixels are replaced with white pixels, and during scanning, line scanning is performed first, and then line-by-line scanning is performed.
In step S5, the road refinement is performed by using Hilditch classical refinement algorithm.
The road vector in step S6 is a contour tracing method.
The high-precision map information identification method provided by the invention has the advantages that the method for identifying and extracting the road is realized by combining the circularity and the color characteristics, the characters in the road are removed in the extraction process, the road identification accuracy and effectiveness are ensured by the step of smoothing the road, and the display effect is improved.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. A map high-precision information identification method is characterized by comprising the following steps:
s1, extracting roads;
s2, unifying the colors of the roads;
s3, eliminating characters in the road;
s4, smoothing the road;
s5, road refinement;
s6, road vectorization;
and S7, producing the vectorized file and transmitting the vectorized file to the terminal equipment.
2. The method of claim 1, wherein the method comprises: the step S1 road extraction includes the steps of:
s11, scanning the map by a scanner and transmitting the map to a computer;
s12, according to the scanned map, according to the calculation formula of the image degree, the circularity of each road is calculated by using tool software;
s13, marking areas with the same or similar colors as the road;
and S14, extracting the road, rescanning the image, setting unmarked pixels as white pixels, calculating the circularity of each area of the label value, setting all the pixels of the connecting components of the area as the white pixels if the result is not between 0 and 0.2, otherwise, not changing, and outputting the road image.
3. The method of claim 1, wherein the method comprises: in step S2, unifying the colors of the roads, extracting the colors of the roads in the legend of the map, scanning the entire map to calculate the distances between the colors of the roads in the map example and the colors in the map, if the distance is smaller than a smaller threshold, determining that the color in the map identifies the road, and replacing the color with white.
4. The method of claim 1, wherein the method comprises: in step S3, the characters in the road are erased, and the characters are erased by erosion and expansion operations using grayscale morphology.
5. A map high-precision information identification method according to claim 4, characterized in that: in the process of eliminating the characters, the characters can be scanned for a plurality of times until the noise is completely removed from the map.
6. The method of claim 1, wherein the method comprises: in step S4, the image obtained in step S3 should be scanned first, and if the number of black pixels connected between two white pixels is less than 3, the black pixels are replaced with white pixels, and line scanning is performed first during scanning, and then line-by-line scanning is performed.
7. The method of claim 1, wherein the method comprises: in the step S5, the road refinement is implemented by using Hilditch classical refinement algorithm.
8. The method of claim 1, wherein the method comprises: the road vectorization in step S6 is to adopt a contour tracking method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011560048.XA CN112733621A (en) | 2020-12-25 | 2020-12-25 | Map high-precision information identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011560048.XA CN112733621A (en) | 2020-12-25 | 2020-12-25 | Map high-precision information identification method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112733621A true CN112733621A (en) | 2021-04-30 |
Family
ID=75615926
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011560048.XA Pending CN112733621A (en) | 2020-12-25 | 2020-12-25 | Map high-precision information identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112733621A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013065164A (en) * | 2011-09-16 | 2013-04-11 | Ricoh Co Ltd | Image processing device, image processing method, and image processing program |
CN110517334A (en) * | 2018-05-21 | 2019-11-29 | 北京四维图新科技股份有限公司 | A kind of method and device that map vector data obtains |
CN110568451A (en) * | 2019-08-02 | 2019-12-13 | 北京三快在线科技有限公司 | Method and device for generating road traffic marking in high-precision map |
CN110728723A (en) * | 2019-09-23 | 2020-01-24 | 东南大学 | Tile map-oriented automatic road extraction method |
-
2020
- 2020-12-25 CN CN202011560048.XA patent/CN112733621A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013065164A (en) * | 2011-09-16 | 2013-04-11 | Ricoh Co Ltd | Image processing device, image processing method, and image processing program |
CN110517334A (en) * | 2018-05-21 | 2019-11-29 | 北京四维图新科技股份有限公司 | A kind of method and device that map vector data obtains |
CN110568451A (en) * | 2019-08-02 | 2019-12-13 | 北京三快在线科技有限公司 | Method and device for generating road traffic marking in high-precision map |
CN110728723A (en) * | 2019-09-23 | 2020-01-24 | 东南大学 | Tile map-oriented automatic road extraction method |
Non-Patent Citations (4)
Title |
---|
佟喜峰 等: "《图像处理与识别技术——应用与实践》", 哈尔滨工业大学出版社, pages: 146 - 123 * |
卫锋: "二值图像噪声控制的算法实现", 《广西科学院学报》, vol. 20, no. 4, pages 210 - 212 * |
王娜: "地图道路、河流信息的识别与提取方法研究", 《中国优秀博硕士学位论文全文数据库(电子期刊) 信息科技辑》, pages 20 - 28 * |
詹曦: "彩色城市交通地图的道路识别与提取", 《计算机仿真》, vol. 27, no. 2, pages 242 - 246 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111507251B (en) | Method and device for positioning answering area in test question image, electronic equipment and computer storage medium | |
CN111160352B (en) | Workpiece metal surface character recognition method and system based on image segmentation | |
CN104751187A (en) | Automatic meter-reading image recognition method | |
CN111242024A (en) | Method and system for recognizing legends and characters in drawings based on machine learning | |
CN108805126B (en) | Method for removing long interference lines of text image | |
CN112712273A (en) | Handwritten Chinese character beauty evaluation method based on skeleton similarity | |
JP4704601B2 (en) | Character recognition method, program, and recording medium | |
CN111126266B (en) | Text processing method, text processing system, equipment and medium | |
CN109543525B (en) | Table extraction method for general table image | |
CN101763510B (en) | Staggered line vectorization extraction and graph recognition method | |
CN111027545A (en) | Card picture mark detection method and device, computer equipment and storage medium | |
CN114419632A (en) | OCR training sample generation method, device and system | |
CN112070684B (en) | Method for repairing characters of a bone inscription based on morphological prior features | |
CN109087234A (en) | Watermark embedding method and device in a kind of text image | |
CN104809721A (en) | Segmentation method and device of cartoon | |
Park et al. | A method for automatically translating print books into electronic Braille books | |
CN112733621A (en) | Map high-precision information identification method | |
CN111444903A (en) | Method, device and equipment for positioning characters in cartoon bubbles and readable storage medium | |
JP2006227824A (en) | Drawing recognition method and device | |
Choi et al. | Relief extraction from a rough stele surface using SVM-based relief segment selection | |
Bloomberg et al. | Document image applications | |
CN114241486A (en) | Method for improving accuracy rate of identifying student information of test paper | |
CN112712860A (en) | Grain finite element model modeling method based on real metallographic structure | |
CN109685074B (en) | Bank card number row positioning method based on Scharr operator | |
Ye et al. | Document image matching and annotation lifting |
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 |