CN112733826B - Image processing method and device - Google Patents
Image processing method and device Download PDFInfo
- Publication number
- CN112733826B CN112733826B CN202011578351.2A CN202011578351A CN112733826B CN 112733826 B CN112733826 B CN 112733826B CN 202011578351 A CN202011578351 A CN 202011578351A CN 112733826 B CN112733826 B CN 112733826B
- Authority
- CN
- China
- Prior art keywords
- pixel points
- image
- origin
- chain code
- taking
- 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims description 23
- 230000003287 optical effect Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 238000003909 pattern recognition Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000010191 image analysis Methods 0.000 description 4
- 238000012512 characterization method Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 2
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 description 1
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Abstract
The invention discloses an image processing method, which comprises the following steps: drawing a continuous curve between pixel points of the closed boundary clockwise by taking an origin as a starting point, and terminating when a first preset condition is met; drawing a continuous curve between pixel points of the closed boundary along anticlockwise direction by taking the origin as a starting point, and terminating when the first preset condition is met; drawing a continuous curve between pixel points of a closed boundary clockwise by taking an origin as a starting point, and obtaining a first chain code by correspondingly pointing to a first indicator; drawing a continuous curve corresponding finger second dichroism between pixel points of the closed boundary along anticlockwise with an origin as a starting point to obtain a second chain code; combining the first chain code and the second chain code to obtain an image boundary complete chain code; the invention provides two paths which are mutually not in conflict and are simultaneously carried out for image processing, can more rapidly acquire the boundary chain code of the image, can shorten the encoding time of the chain code by 50%, and is particularly suitable for high-frequency image recognition scenes.
Description
Technical Field
The present invention relates to the field of image processing technology, and more particularly, to an image processing method.
Background
Image processing (image processing), a technique of analyzing an image with a computer to achieve a desired result. Also known as image processing. Image processing generally refers to digital image processing. The digital image is a large two-dimensional array obtained by photographing with equipment such as an industrial camera, a video camera, a scanner and the like, wherein the elements of the array are called pixels, and the values of the pixels are called gray values. Image processing techniques generally include image compression, enhancement and restoration, matching, description and recognition of 3 parts.
Some useful metrics, data or information are extracted from the image. The aim is to obtain a certain numerical result instead of generating another image. The content of the image analysis and the research field of pattern recognition and artificial intelligence are intersected, but the image analysis is different from the typical pattern recognition. Image analysis is not limited to classifying particular regions in an image by a fixed number of categories, and is primarily intended to provide a description of the image being analyzed. For this purpose, both pattern recognition techniques and knowledge bases concerning the content of the images, i.e. knowledge-based aspects of artificial intelligence, are used. Image analysis requires extracting features of an image by an image segmentation method, and then performing symbolic description on the image. This description can not only answer whether a particular object is present in the image, but also detail the image content.
Digital image processing, analysis and machine vision are an exciting and active branch of cognitive science and computer science, shape is a very important parameter in human perception, recognition and understanding, and chain coding is a shape description method extended by the concept;
Chain codes (also called freeman codes) are methods for describing curves or boundaries by using coordinates of starting points of the curves and direction codes of boundary points, and are often used for representing the boundaries of the curves and the regions in the fields of image processing, computer graphics, pattern recognition and the like;
According to the horizontal, vertical and two diagonal directions, 4 directors can be defined for two adjacent pixels: 0.1, 2, 3, respectively represent four directions of 0 degrees, 90 degrees, 180 degrees, and 270 degrees. Likewise, 8 directors can be defined: 0.1, 2, 3, 4, 5, 6, 7. The chain code is a set of sequences of the start of a line segment plus the number of the several symbols, commonly referred to as Freeman chain code. When Freeman chain code is used for representing a starting point of a curve, which is needed by the curve, for 8-chain codes, the lengths of corresponding line segments of odd numbers and even numbers are unequal, the unit length of the specified even number code is 1, and the unit length of the odd numbers is 1
Chain codes are a very common coding technique used in image processing and pattern recognition to represent line, plane curve and region boundaries. Chain code representation is used in many practical applications. Chain code technology is widely used because it can store more information with less data. The method of representing the line pattern with a chain code was originally proposed by Freeman(Freeman H.On the encoding of arbitrary geometric configurations.IRE Transactions on Electronic Computers,1961,10：260-268.) in 1961. Freeman chain code has remained one of the most widely used chain code encoding methods to date. The chain code moves in an 8-adjacent fashion along a digital curve or border pixel, each direction of movement is defined by a set of numbers i i=0, 1,2, encoding of.7, representing an angle of 45 deg. X i with respect to the positive X-axis direction. A chain code can be seen as consisting of a series of small straight segments with a fixed direction and length.
Sometimes one also uses a 4-contiguous version of the Freeman chain code, i.e. the chain code moves in 4 directions, representing an angle of 90 ° X i with the X axis in the numerical set { i|i=0, 1,2,3} code.
A modification to the Freeman chain code was proposed by ,Bribiesca(Bribiesca E.A geometric structure for two-dimensionalshapes and three-dimensional surfaces.Pattern Recognition,1992,25(5)：483-496.) in 1992 to represent the shape of the region. The method encodes small straight-line segments with their slopes, i.e., -3, -2 and-1 instead of 5,6 and 7 in Freeman chain code (4= -4). Thus, the accumulated sum of the code values (slopes) of a closed curve chain code is 8 or-8.
In 1999, bribiesca (Bribiesca E.A new chain code. Pattern Recognition,1999, 32 (2): 235-251.) has proposed a new chain code encoding method to represent region shapes, called "vertex chain codes" (Vertex Chain Code). The chain code is based on his concept of "shape number" (shape numbers) proposed by Guzman(Bribiesca E,Guzman A.How to describe pure form and how to measure differences in shapes using shapenumbers.Pattern Recognition,1980,12(1)：101-112.) in 1980. The code value of each of the vertex chain codes indicates that the vertex is the vertex of several boundary pixels. Thus, only three code values 1,2 and 3 are required to represent the boundary consisting of pixels on a square grid (as shown in fig. 1). The original vertex chain code is an equal length code whose three code values 1,2 and 3 are represented and stored by binary numbers 01, 10 and 11, respectively. The probability of occurrence of the code value is not considered in the encoding process. In addition, the eight-direction Freeman chain code, the four-direction Freeman chain code and the vertex chain code have relatively more storage bits, lower efficiency and influence the rapid and real-time transmission performance of the image.
For describing curves or boundaries of images in a Freeman chain code mode, the process of describing the curves boundaries and transcoding is required, and the required data volume to be processed is large, so that the time consumption is long, especially the process of describing the curves boundaries occupies most time consumption, the high-frequency image identification scene is realized, and a large computing power is required to obtain an image processing result in time.
Disclosure of Invention
The invention provides a rapid image processing method, which solves the technical problems in the related art.
According to an aspect of the present invention, there is provided an image processing method including the steps of:
S1, collecting image data, and placing the collected image data in a two-dimensional identification area;
S2, connecting pixel points at the edge of the image to form a closed boundary, taking a central connecting line of two adjacent pixel points as a fixed-length line segment, taking one pixel point of the closed boundary as an origin, and drawing a continuous curve between the pixel points of the closed boundary by taking the origin as a starting point, wherein the trend of the fixed-length line segment corresponds to the indicator to obtain a number, and the numbers obtained by the fixed-length line segment corresponds to the indicator are sequentially arranged to form a chain code;
S3, drawing a continuous curve between pixel points of the closed boundary clockwise by taking an origin as a starting point, and terminating when a first preset condition is met;
S4, drawing a continuous curve between pixel points of the closed boundary along the anticlockwise direction by taking the origin as a starting point, and terminating when the first preset condition is met;
The first predetermined condition is: drawing a continuous curve between the pixel points of the closed boundary clockwise by taking the origin as a starting point and drawing a continuous curve between the pixel points of the closed boundary anticlockwise by taking the origin as a starting point to form a closed curve;
s5, drawing a continuous curve between pixel points of the closed boundary clockwise by taking an origin as a starting point, and correspondingly pointing to a first indicator to obtain a first chain code;
S6, drawing a continuous curve corresponding to the second sign between the pixel points of the closed boundary along the anticlockwise direction by taking the origin as a starting point to obtain a second chain code;
s7, combining the first chain code and the second chain code to obtain the image boundary complete chain code.
Further, the identification area is provided with identification points corresponding to the pixel points as the background of the image, and the identification points have fixed coordinates in the identification area.
Further, the combining of the first chain code and the second chain code to obtain the image boundary complete chain code includes: the second chain code is inverted and then combined to the end of the first chain code.
Further, the first pointer and the second pointer are mutually center symmetric.
According to an aspect of the present invention, there is provided an image processing apparatus comprising:
an image acquisition unit for acquiring an image of an object;
the image data preprocessing unit is used for placing the image in a two-dimensional recognition area and establishing mapping between pixel points on the image and recognition points in the recognition area;
The chain code generation unit is used for selecting one pixel point of the closed boundary of the image as an origin point, and drawing a continuous curve between the pixel points of the closed boundary clockwise by taking the origin point as a starting point, and terminating when a first preset condition is met;
Drawing a continuous curve between pixel points of the closed boundary along anticlockwise direction by taking the origin as a starting point, and terminating when the first preset condition is met;
The first predetermined condition is: drawing a continuous curve between the pixel points of the closed boundary clockwise by taking the origin as a starting point and drawing a continuous curve between the pixel points of the closed boundary anticlockwise by taking the origin as a starting point to form a closed curve;
drawing a continuous curve between pixel points of a closed boundary clockwise by taking an origin as a starting point, and obtaining a first chain code by correspondingly pointing to a first indicator;
Drawing a continuous curve corresponding finger second dichroism between pixel points of the closed boundary along anticlockwise with an origin as a starting point to obtain a second chain code;
The first chain code and the second chain code are combined to obtain the image boundary complete chain code.
Further, the image acquisition unit acquires images based on the linear image sensor, can convert optical images into analog signals line by line, and acquires image data in units of lines.
Further, the chain code generating unit at least includes:
An origin selecting unit for selecting one pixel point of a closed boundary of the image as an origin;
the closed curve drawing unit is used for drawing a continuous curve between pixel points of the closed boundary clockwise by taking the origin as a starting point, and terminating when the first preset condition is met;
Drawing a continuous curve between pixel points of the closed boundary along anticlockwise direction by taking the origin as a starting point, and terminating when the first preset condition is met;
And a termination unit for judging whether the first predetermined condition is satisfied.
Further, the determining by the termination unit whether the first predetermined condition is satisfied includes: and (3) the closed curve is drawn between the pixel points of the clockwise and anticlockwise closed boundaries by taking the original point as a starting point, and the pixel points which are overlapped on the clockwise and anticlockwise drawn curves meet a first preset condition.
Further, the pixels overlapping on the curves marked clockwise and anticlockwise are pixels with the same coordinates of the two mapped identification points.
The invention has the beneficial effects that:
The two paths which do not conflict with each other and are carried out simultaneously are provided for image processing, so that the boundary chain codes of the images can be obtained more quickly, the chain codes which are the same as the one-way depiction can be obtained no matter from which point is used as the starting point, the encoding time of the chain codes can be shortened by about 50%, and the method is particularly suitable for high-frequency image recognition scenes, such as expressway vehicle recognition and the like.
Drawings
FIG. 1 is a flow chart of an image processing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an embodiment of the present invention depicting a continuous curve between pixels of a closed boundary in a clockwise direction and a counterclockwise direction with an origin as a starting point;
FIG. 3 is a schematic diagram of a first pointer according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a second pointer according to an embodiment of the present invention;
FIG. 5 is a schematic illustration depicting a continuous curve between pixel points at a closed boundary only in a clockwise direction in accordance with an embodiment of the present invention;
Fig. 6 is a block diagram of an image processing apparatus according to an embodiment of the present invention;
fig. 7 is a block diagram of a chain code generation unit according to an embodiment of the present invention.
In the figure: the image processing apparatus 100, the image acquisition unit 110, the image data preprocessing unit 120, the chain code generation unit 130, the origin selection unit 131, the closed curve characterization unit 132, and the termination unit 133.
Detailed Description
The subject matter described herein will now be discussed with reference to example embodiments. It should be appreciated that these embodiments are discussed only to enable a person skilled in the art to better understand and thereby practice the subject matter described herein, and are not limiting of the scope, applicability, or examples set forth in the claims. Changes may be made in the function and arrangement of elements discussed without departing from the scope of the disclosure as set forth in the specification. Various examples may omit, replace, or add various procedures or components as desired. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. In addition, features described with respect to some examples may be combined in other examples as well.
In this embodiment, there is provided an image processing method, as shown in fig. 1, which is a schematic diagram of an image processing method according to the present invention, as shown in fig. 1, including the steps of:
S1, collecting image data, and placing the collected image data in a two-dimensional identification area;
The method comprises the steps of placing an image in a two-dimensional identification area, wherein the identification area is provided with identification points corresponding to pixels as the background of the image, overlapping the identification points with the pixels of the image during processing, enabling the pixels of the image to be not easily identified due to the change of the image, mapping the pixels of the corresponding image based on the identification points of the identification area which are stored, and expressing the pixels of the image through the expression of the identification points;
S2, connecting pixel points at the edge of the image to form a closed boundary, taking a central connecting line of two adjacent pixel points as a fixed-length line segment, taking one pixel point of the closed boundary as an origin, and drawing a continuous curve between the pixel points of the closed boundary by taking the origin as a starting point, wherein the trend of the fixed-length line segment corresponds to the indicator to obtain a number, and the numbers obtained by the fixed-length line segment corresponds to the indicator are sequentially arranged to form a chain code;
S3, drawing a continuous curve between pixel points of the closed boundary clockwise by taking an origin as a starting point, and terminating when a first preset condition is met;
S4, drawing a continuous curve between pixel points of the closed boundary along the anticlockwise direction by taking the origin as a starting point, and terminating when the first preset condition is met;
The first predetermined condition is: drawing a continuous curve between the pixel points of the closed boundary clockwise by taking the origin as a starting point and drawing a continuous curve between the pixel points of the closed boundary anticlockwise by taking the origin as a starting point to form a closed curve;
s5, drawing a continuous curve between pixel points of the closed boundary clockwise by taking an origin as a starting point, and correspondingly pointing to a first indicator to obtain a first chain code;
S6, drawing a continuous curve corresponding to the second sign between the pixel points of the closed boundary along the anticlockwise direction by taking the origin as a starting point to obtain a second chain code;
S7, combining the first chain code and the second chain code to obtain an image boundary complete chain code;
The first indicator and the second indicator are mutually symmetrical in center;
in this embodiment, the identification point has fixed coordinates within the identification area.
As shown in fig. 2, a continuous curve corresponding indicator is drawn between pixel points of a closed boundary clockwise by taking an origin as a starting point to obtain a first chain code 434202;
drawing continuous curve corresponding directors between pixel points of the closed boundary along anticlockwise direction by taking the origin as a starting point to obtain a second chain code 6760;
the complete chain code combined with the first chain code after the second chain code is in the reverse order is 4342020676;
The first pointer is shown in fig. 3, and the second pointer is shown in fig. 4, wherein the first pointer and the second pointer are mutually symmetrical in center;
From the above procedure, the combining of the first chain code and the second chain code to obtain the image boundary complete chain code includes: the second chain code is inverted and then combined to the end of the first chain code.
As shown in fig. 5, the chain code obtained by drawing continuous curve corresponding directors between the pixel points of the closed boundary only clockwise is 4342020676, which is completely consistent with the complete chain code;
Further, the following table 1 shows the comparison of the chain code results obtained by two-way and one-way characterization with different starting points S1, S2, S3;
TABLE 1
| Bidirectional clockwise | Bidirectional anticlockwise | Unidirectional clockwise | |
| S1 | 1234 | 8765 | 12345678 |
| S2 | 8123 | 7654 | 81234567 |
| S3 | 4567 | 3218 | 45678123 |
From the above table, it can be seen that the same chain code as the unidirectional characterization can be obtained from any point, and the chain code encoding time can be shortened by nearly 50%, which is particularly suitable for high-frequency image recognition scenes, such as expressway vehicle recognition and the like.
The method provides two paths which are mutually not in conflict and are simultaneously carried out for image processing, so that the boundary chain code of the image can be obtained more quickly;
as shown in fig. 6 to 7, based on the above-described image processing method, the present invention provides an image processing apparatus 100 including:
An image acquisition unit 110 for acquiring an image of an object;
more preferably, the image acquisition unit 110 acquires images based on a linear image sensor, can convert optical images into analog signals line by line, and acquires image data in units of lines; two types of linear image sensors with different circuit configurations are recommended: CMOS image sensors and CCD image sensors.
An image data preprocessing unit 120, configured to place an image in a two-dimensional recognition area, and to map pixel points on the image with recognition points in the recognition area;
A chain code generating unit 130, configured to select one pixel point of the closed boundary of the image as an origin point, and draw a continuous curve between the pixel points of the closed boundary clockwise with the origin point as a starting point, and terminate when a first predetermined condition is satisfied;
Drawing a continuous curve between pixel points of the closed boundary along anticlockwise direction by taking the origin as a starting point, and terminating when the first preset condition is met;
The first predetermined condition is: drawing a continuous curve between the pixel points of the closed boundary clockwise by taking the origin as a starting point and drawing a continuous curve between the pixel points of the closed boundary anticlockwise by taking the origin as a starting point to form a closed curve;
drawing a continuous curve between pixel points of a closed boundary clockwise by taking an origin as a starting point, and obtaining a first chain code by correspondingly pointing to a first indicator;
Drawing a continuous curve corresponding finger second dichroism between pixel points of the closed boundary along anticlockwise with an origin as a starting point to obtain a second chain code;
The first chain code and the second chain code are combined to obtain the image boundary complete chain code.
Wherein the chain code generation unit 130 includes at least:
An origin selecting unit 131 for selecting one pixel point of a closed boundary of an image as an origin;
a closed curve drawing unit 132 for drawing a continuous curve between the pixels of the closed boundary clockwise with the origin as a starting point, and terminating when the first predetermined condition is satisfied;
Drawing a continuous curve between pixel points of the closed boundary along anticlockwise direction by taking the origin as a starting point, and terminating when the first preset condition is met;
a termination unit 133 for judging whether the first predetermined condition is satisfied,
The termination unit 133 determines whether the first predetermined condition is satisfied: the closed curve is characterized by taking an origin as a starting point along a continuous curve between pixel points of a clockwise and a counterclockwise closed boundary, and the pixel points which are coincident on the curve marked along the clockwise and the counterclockwise are met with a first preset condition;
the pixels overlapping along the curves marked clockwise and anticlockwise are pixels with the same coordinates of the two mapped identification points.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present embodiment may be essentially or what contributes to the prior art, and may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), including several instructions for causing a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method of the embodiments.
The embodiment of the present embodiment has been described above with reference to the accompanying drawings, but the embodiment is not limited to the above-described specific implementation, which is merely illustrative and not restrictive, and many forms may be made by those of ordinary skill in the art without departing from the spirit of the embodiment and the scope of the protection of the claims, which fall within the protection of the embodiment.
Claims (2)
1. An image processing method, characterized by comprising the steps of:
S1, collecting image data, and placing the collected image data in a two-dimensional identification area;
The method comprises the steps of placing an image in a two-dimensional identification area for identification, wherein identification points corresponding to pixel points are arranged in the identification area to serve as the background of the image, the identification points are overlapped with the pixel points of the image during processing, the pixel points of the image cannot be easily identified due to image change, the pixel points of the corresponding image can be mapped based on the identification points of the identification area which are stored, and the pixel points of the image are expressed through the expression of the identification points;
S2, connecting pixel points at the edge of the image to form a closed boundary, taking a central connecting line of two adjacent pixel points as a fixed-length line segment, taking one pixel point of the closed boundary as an origin, and drawing a continuous curve between the pixel points of the closed boundary by taking the origin as a starting point, wherein the trend of the fixed-length line segment corresponds to the indicator to obtain a number, and the numbers obtained by the fixed-length line segment corresponds to the indicator are sequentially arranged to form a chain code;
S3, drawing a continuous curve between pixel points of the closed boundary clockwise by taking an origin as a starting point, and terminating when a first preset condition is met;
S4, drawing a continuous curve between pixel points of the closed boundary along the anticlockwise direction by taking the origin as a starting point, and terminating when the first preset condition is met;
The first predetermined condition is: drawing a continuous curve between the pixel points of the closed boundary clockwise by taking the origin as a starting point and drawing a continuous curve between the pixel points of the closed boundary anticlockwise by taking the origin as a starting point to form a closed curve;
s5, a continuous curve corresponding to the first indicator is carved between the pixel points of the closed boundary clockwise by taking the origin as a starting point to obtain a first chain code;
S6, a continuous curve corresponding to a second indicator is carved between pixel points of the closed boundary along the anticlockwise direction by taking the origin as a starting point to obtain a second chain code;
S7, combining the first chain code and the second chain code to obtain an image boundary complete chain code;
The identification area is internally provided with identification points corresponding to the pixel points as the background of the image, and the identification points have fixed coordinates in the identification area;
the step of combining the first chain code and the second chain code to obtain the image boundary complete chain code comprises the following steps: reversing the second chain code and then combining to the end of the first chain code;
The first indicator and the second indicator are mutually centrosymmetric.
2. An image processing apparatus, comprising:
an image acquisition unit for acquiring an image of an object;
the image data preprocessing unit is used for placing the image in a two-dimensional recognition area and establishing mapping between pixel points on the image and recognition points in the recognition area;
The chain code generation unit is used for selecting one pixel point of the closed boundary of the image as an origin point, and drawing a continuous curve between the pixel points of the closed boundary clockwise by taking the origin point as a starting point, and terminating when a first preset condition is met;
Drawing a continuous curve between pixel points of the closed boundary along anticlockwise direction by taking the origin as a starting point, and terminating when the first preset condition is met;
The first predetermined condition is: drawing a continuous curve between the pixel points of the closed boundary clockwise by taking the origin as a starting point and drawing a continuous curve between the pixel points of the closed boundary anticlockwise by taking the origin as a starting point to form a closed curve;
the origin is used as a starting point to draw a continuous curve corresponding to a first indicator between pixel points of a closed boundary clockwise to obtain a first chain code;
the origin is used as a starting point to draw a continuous curve corresponding to a second indicator between pixel points of the closed boundary along the anticlockwise direction so as to obtain a second chain code;
combining the first chain code and the second chain code to obtain an image boundary complete chain code;
The image acquisition unit acquires images based on the linear image sensor, can convert optical images into analog signals line by line, and acquires image data taking lines as units;
the chain code generation unit includes at least:
An origin selecting unit for selecting one pixel point of a closed boundary of the image as an origin;
the closed curve drawing unit is used for drawing a continuous curve between pixel points of the closed boundary clockwise by taking the origin as a starting point, and terminating when the first preset condition is met;
Drawing a continuous curve between pixel points of the closed boundary along anticlockwise direction by taking the origin as a starting point, and terminating when the first preset condition is met;
a termination unit for judging whether a first predetermined condition is satisfied;
The termination unit determining whether the first predetermined condition is satisfied includes: the closed curve is characterized by taking an origin as a starting point along a continuous curve between pixel points of a clockwise and a counterclockwise closed boundary, and the pixel points which are coincident on the curve marked along the clockwise and the counterclockwise are met with a first preset condition;
The pixel points which are coincident on the curves marked clockwise and anticlockwise are the pixel points with the same coordinates of the two mapped identification points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011578351.2A CN112733826B (en) | 2020-12-28 | Image processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011578351.2A CN112733826B (en) | 2020-12-28 | Image processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112733826A CN112733826A (en) | 2021-04-30 |
| CN112733826B true CN112733826B (en) | 2024-05-31 |
Family
ID=
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4777651A (en) * | 1984-06-25 | 1988-10-11 | Tektronix, Inc. | Method of pixel to vector conversion in an automatic picture coding system |
| JPH05114027A (en) * | 1991-04-02 | 1993-05-07 | Yamaha Motor Co Ltd | Device and method for extracting image feature variable |
| US6728412B1 (en) * | 1999-10-29 | 2004-04-27 | S.V.V. Technology Innovations, Inc. | Method and apparatus for on-the-fly image coding |
| CN101201938A (en) * | 2006-12-13 | 2008-06-18 | 上海吉量软件科技有限公司 | Filling algorithm for rapidly matching pair of left and right boundary point |
| JP2008217206A (en) * | 2007-03-01 | 2008-09-18 | Fujifilm Corp | Image identification device, image identification method and imaging device |
| CN102158707A (en) * | 2011-05-19 | 2011-08-17 | 大连民族学院 | Image compression storage method based on comprehensive vertex chain code coding |
| CN107948571A (en) * | 2017-12-27 | 2018-04-20 | 努比亚技术有限公司 | The method, apparatus and computer-readable recording medium of video record |
| CN109711418A (en) * | 2019-01-29 | 2019-05-03 | 浙江大学 | A kind of contour corner detection method for object plane image |
| CN110097065A (en) * | 2019-05-07 | 2019-08-06 | 厦门商集网络科技有限责任公司 | A kind of line detection method and terminal based on FreeMan chain code |
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4777651A (en) * | 1984-06-25 | 1988-10-11 | Tektronix, Inc. | Method of pixel to vector conversion in an automatic picture coding system |
| JPH05114027A (en) * | 1991-04-02 | 1993-05-07 | Yamaha Motor Co Ltd | Device and method for extracting image feature variable |
| US6728412B1 (en) * | 1999-10-29 | 2004-04-27 | S.V.V. Technology Innovations, Inc. | Method and apparatus for on-the-fly image coding |
| CN101201938A (en) * | 2006-12-13 | 2008-06-18 | 上海吉量软件科技有限公司 | Filling algorithm for rapidly matching pair of left and right boundary point |
| JP2008217206A (en) * | 2007-03-01 | 2008-09-18 | Fujifilm Corp | Image identification device, image identification method and imaging device |
| CN102158707A (en) * | 2011-05-19 | 2011-08-17 | 大连民族学院 | Image compression storage method based on comprehensive vertex chain code coding |
| CN107948571A (en) * | 2017-12-27 | 2018-04-20 | 努比亚技术有限公司 | The method, apparatus and computer-readable recording medium of video record |
| CN109711418A (en) * | 2019-01-29 | 2019-05-03 | 浙江大学 | A kind of contour corner detection method for object plane image |
| CN110097065A (en) * | 2019-05-07 | 2019-08-06 | 厦门商集网络科技有限责任公司 | A kind of line detection method and terminal based on FreeMan chain code |
Non-Patent Citations (4)
| Title |
|---|
| Automatic extraction of contour lines and feature points from profile images;Okamoto, N 等;10th Canadian Conference on Electrical and Computer Engineering - Engineering Innovation: Voyage of Discovery;19971231;第1-2卷;第831-834页 * |
| Compression of information by coding based on dichotomous trajectories;Caruso, H.A.;Revista Telegrafica Electronica;19920430(第935期);第282-8, 311页 * |
| 基于组合特征的点状地图符号识别;黄文骞;测绘通报;19981225(第12期);第293-298页 * |
| 描述蝴蝶兰图像外轮廓信息的对称8链码编码算法;徐焕良;王一;熊迎军;任守纲;王浩云;;计算机科学(09);第299-304页 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109389552B (en) | Image super-resolution algorithm based on context-dependent multitask deep learning | |
| CN110222758B (en) | Image processing method, device, equipment and storage medium | |
| Zhou et al. | Omnidirectional image quality assessment by distortion discrimination assisted multi-stream network | |
| CN110853047A (en) | Intelligent image segmentation and classification method and device and computer readable storage medium | |
| CN109949224B (en) | Deep learning-based cascade super-resolution reconstruction method and device | |
| CN110136055B (en) | Super resolution method and device for image, storage medium and electronic device | |
| Wang et al. | Lightweight Single Image Super-Resolution Convolution Neural Network in Portable Device. | |
| CN107633482A (en) | A kind of super resolution ratio reconstruction method based on sequence image | |
| CN111899270B (en) | Card frame detection method, device, equipment and readable storage medium | |
| CN113642585B (en) | Image processing method, apparatus, device, storage medium, and computer program product | |
| CN108876716B (en) | Super-resolution reconstruction method and device | |
| Zhou et al. | Cross-scale residual network: A general framework for image super-resolution, denoising, and deblocking | |
| Guan et al. | Srdgan: learning the noise prior for super resolution with dual generative adversarial networks | |
| CN114627034A (en) | Image enhancement method, training method of image enhancement model and related equipment | |
| CN115131229A (en) | Image noise reduction and filtering data processing method and device and computer equipment | |
| CN112489062B (en) | Medical image segmentation method and system based on boundary and neighborhood guidance | |
| CN112733826B (en) | Image processing method and device | |
| Ruivo et al. | Double-deep learning-based point cloud geometry coding with adaptive super-resolution | |
| CN113096032A (en) | Non-uniform blur removing method based on image area division | |
| CN109996085B (en) | Model training method, image processing method and device and electronic equipment | |
| Li et al. | RGSR: A two-step lossy JPG image super-resolution based on noise reduction | |
| CN108550111B (en) | Residual error example regression super-resolution reconstruction method based on multi-level dictionary learning | |
| CN116580174A (en) | Real-time virtual scene construction method | |
| CN115471413A (en) | Image processing method and device, computer readable storage medium and electronic device | |
| Yu et al. | Shature: shape and texture deformation for human pose and attribute transfer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |