CN107480666B - Image capturing device, method and device for extracting scanning target of image capturing device, and storage medium - Google Patents
Image capturing device, method and device for extracting scanning target of image capturing device, and storage medium Download PDFInfo
- Publication number
- CN107480666B CN107480666B CN201710684808.XA CN201710684808A CN107480666B CN 107480666 B CN107480666 B CN 107480666B CN 201710684808 A CN201710684808 A CN 201710684808A CN 107480666 B CN107480666 B CN 107480666B
- Authority
- CN
- China
- Prior art keywords
- image
- preset
- target object
- target
- extracting
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an image capturing device and a scanning target extraction method, an extraction device and a storage medium thereof, wherein the scanning target extraction method comprises the following steps: acquiring a scanning area image; extracting closed contour lines of all objects in the image of the scanning area, wherein the objects comprise target objects; identifying a first corner of the closed contour line according to a first preset rule; judging whether the number of the first angular points is consistent with the number of preset angular points or not; if so, extracting an image of the target object from the image of the scanning area according to the first corner point; if not, determining second corner points with the same number as the preset corner points according to the closed contour lines and a preset algorithm, and extracting the image of the target object from the scanning area image according to the second corner points. By the method, when the target object is in any shape or has an interference object, the target object can be effectively extracted from the image of the scanning area, and the scene adaptability of the image capturing device in scanning is improved.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to an image capture device, a scan target extraction method, an extraction apparatus, and a storage medium.
Background
Scanners are now widely used in our lives, work and learning. With the development of technology, scanning using an image capturing apparatus is popular due to its convenience and rapidity.
However, when the image capturing device is used for scanning, there is a problem of poor scene adaptability, for example, when the image capturing device is used to scan a target object, other objects (such as fingers and interfering objects) enter a scanned image frame or directly cover a partial region of the target object, or the target object has an irregular and incomplete shape, or the target object does not completely enter the scanned image frame, the target object cannot be well identified.
Disclosure of Invention
The invention mainly aims to provide a scanned target extraction method, and aims to solve the problems that when an image capture device is used for scanning, the scene adaptability is not strong, and a target object cannot be well identified and extracted when the shape of the target object is uncertain or an interfering object exists.
In order to achieve the above object, the present invention provides a scan target extraction method, including the steps of:
acquiring a scanning area image;
extracting closed contour lines of all objects in the scanning area image, wherein the objects comprise target objects;
identifying a first corner of the closed contour line according to a first preset rule;
judging whether the number of the first angular points is consistent with the number of preset angular points or not;
if so, extracting the image of the target object from the scanning area image according to the first corner point;
if not, determining second corner points with the same number as the preset corner points according to the closed contour lines and a preset algorithm, and extracting the image of the target object from the scanning area image according to the second corner points.
Preferably, the step of identifying a first corner point of the contour according to a first preset rule specifically includes:
detecting all straight lines in the closed contour line;
identifying and eliminating interference lines in the straight lines to obtain effective straight lines;
determining an edge straight line of the target object according to the effective straight line;
acquiring all intersection points of the edge straight lines;
and extracting first corner points from the intersection points according to a second preset rule, and determining the coordinates and the number of the first corner points.
Preferably, if so, the step of extracting the image of the target object from the image of the scanning area according to the first corner point specifically includes:
when the number of the first corner points is consistent with the number of preset corner points, determining a first target extraction area according to the first corner point coordinates;
and extracting the image of the target object from the scanning area image according to the first target extraction area.
Preferably, if not, the step of determining second corner points with the same number as the preset corner points according to the closed contour line and a preset algorithm, and extracting the image of the target object from the scan region image according to the second corner points specifically includes:
when the number of the first angular points is inconsistent with the number of preset angular points, calculating a minimum circumscribed polygon of the closed contour line, wherein the number of vertexes of the minimum circumscribed polygon is consistent with the number of the preset angular points;
acquiring vertex coordinates of the minimum circumscribed polygon in the scanning area image, and taking the vertex coordinates as the position of the second corner point;
determining a second target extraction area according to the vertex coordinates;
and extracting the image of the target object from the scanning area image according to the second target extraction area.
Preferably, the number of the preset corner points is four.
Preferably, the minimum bounding polygon is a minimum bounding rectangle.
Preferably, the scan target extracting method further includes:
after the image of the target object is extracted, when a black edge exists in the image of the target object, identifying a region of the image of the target object occupied by the black edge;
and converting the image color of the area into a preset color.
Further, to achieve the above object, the present invention also provides a scan target extracting apparatus including: a memory, a processor, and a scan target extraction program stored on the memory and executable on the processor, the scan target extraction program when executed by the processor implementing the steps of the method as in any one of the above.
Further, to achieve the above object, the present invention also provides an image capturing apparatus including the scan target extracting device as described above.
Further, to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a scan target extraction program which, when executed by a processor, realizes the steps of the scan target extraction method as recited in any one of the above.
The embodiment of the invention provides a scanning target extraction method, which comprises the steps of extracting closed contour lines of all objects in a scanning area image after the scanning area image is obtained, wherein the objects comprise target objects, identifying first corner points of the closed contour lines according to a first preset rule, judging whether the number of the first corner points is consistent with the number of the preset corner points or not, eliminating the interference of the non-target objects to a certain extent as the first preset rule is established according to the preset shape of the target object image to be extracted, and directly extracting the image of the target object from the scanning area image according to the first corner points when the judgment result is consistent, wherein the shape of the target object is considered to be approximately consistent with the preset shape; when the judgment result is inconsistent, the target object consistent with the preset shape can not be identified, second corner points consistent with the preset corner points in number are determined according to the closed contour line and the preset algorithm, the preset algorithm ensures that the closed contour line can be completely included in the closed area formed by the second corner points, the closed area is consistent with the preset shape, the image of the target object can be extracted from the scanning area image according to the second corner points, and by the method, when the target object is in any shape or has an interfering object, the target object can be effectively extracted from the scanning area image, so that the scene adaptability of the image capturing device for scanning is improved.
Drawings
FIG. 1 is a first flowchart of a scan target extracting method according to an embodiment of the present invention;
FIG. 2 is a second flowchart of an embodiment of a scan target extraction method according to the invention;
FIG. 3 is a third flowchart of an embodiment of a scanned target extraction method according to the present invention;
FIG. 4 is a fourth flowchart illustrating a scanned object extracting method according to an embodiment of the invention;
FIG. 5 is a fifth flowchart illustrating a scanned object extracting method according to an embodiment of the invention;
fig. 6 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The main solution of the embodiment of the invention is as follows: the method comprises the steps of obtaining a scanning area image, extracting closed contour lines of all objects in the scanning area image, wherein the objects comprise target objects, identifying first corner points of the closed contour lines according to preset rules, judging whether the number of the first corner points is consistent with the number of the preset corner points, if so, extracting an image of the target objects from the scanning area image according to the first corner points, if not, determining second corner points consistent with the number of the preset corner points according to the closed contour lines and a preset algorithm, and extracting the image of the target objects from the scanning area image according to the second corner points.
The prior art has the problem that the scanning equipment based on the image capturing equipment has poor scene adaptability, so that the target object cannot be well identified and extracted when the shape of the target object is uncertain or an interfering object exists.
The invention provides a solution, which can effectively extract a target object in a scanning area image when the target object is in any shape or has an interference object, and improves the scene adaptability of the image capturing device during scanning.
Referring to fig. 1, an embodiment of the present invention provides a scan target extraction method, where the scan target extraction method includes:
s100, acquiring a scanning area image;
s200, extracting closed contour lines of all objects in the scanned area image, wherein the objects comprise target objects;
s300, identifying a first corner of the closed contour line according to a first preset rule;
s400, judging whether the number of the first angular points is consistent with the number of preset angular points or not;
s500, if yes, extracting an image of the target object from the image of the scanning area according to the first corner point;
s600, if not, determining second corner points with the same number as the preset corner points according to the closed contour lines and a preset algorithm, and extracting the image of the target object from the scanning area image according to the second corner points.
When a user needs to perform a scanning operation on a target object, the target object is first placed in a scanning area, and the range of the scanning area may be determined based on the maximum range of an image that can be captured by the image capturing device, or may be set according to actual use requirements. The scanning area should be selected or set as an area with a color different from that of the edge of the target object as a scanning background of the target object, so that the target object in the acquired target area image can form an obvious boundary in the scanning area, effective identification of the target object is realized, and for better identification, the scanning area can select a uniform color as the scanning background of the target object. Upon receiving the scan instruction, the image capturing apparatus acquires a scan area image.
After the scanning area image is acquired, analyzing the scanning area image and extracting closed contour lines of all objects in the scanning area image, where the object mentioned here should include a target object and other interfering objects except the target object, and the closed contour line should be a contour line when the detected enclosed area is the largest.
And after the closed contour line is obtained, identifying a first corner point of the closed contour line. The first corner point needs to be identified according to a first preset rule formed according to a preset shape of the target object, and the first preset rules formed by different preset shapes can be different. The preset shape is the shape of the target object image required to be extracted and set by the user, so that the user can conveniently perform further processing or use on the extracted target object image, such as printing, sending a mail, projecting and the like. The preset shape can be a polygon such as a rectangle, a triangle, a trapezoid and the like, and is determined according to the use requirement. The number of vertexes of the preset shape is the number of preset angular points. In order to be applied to most occasions of office work and study, the preset shape can be set to be the shape of a normal document, book or receipt, such as a rectangle, and the number of corresponding preset angular points is four. The first preset rule can be obtained according to methods such as empirical determination, virtual fitting or experimental determination. According to a first preset rule, effective lines meeting the preset shape feature range can be extracted from the closed contour lines, the vertexes of the regions surrounded and synthesized by the effective lines are screened and judged according to a certain rule, first corner points meeting the preset shape corner feature are identified, specifically, a certain parameter range can be set for the corner feature of the preset shape, such as relative position, included angle and the like, corresponding data of the vertexes of the regions are obtained, and if the vertex is located in the range, the first corner point can be judged. And judging whether the number of the first corner points is consistent with the number of the preset corner points or not, and recognizing the first corner points according to a preset rule formed by a preset shape, so that when the number of the first corner points is consistent with the number of the preset corner points, the shape of the target object can be considered to be consistent with the preset shape, and the image of the target object can be directly extracted according to a closed area formed by the first corner points. When the number of the first corner points is inconsistent with the number of the preset corner points, it can be considered that the target object with the same shape as the preset shape cannot be identified, then the second corner points with the same number as the preset corner points can be fitted according to the closed contour lines and a preset algorithm, so that the closed contour lines are all positioned in a closed area formed by the fitted second corner points, and the shape of the closed area is consistent with the preset shape. And after the second corner points are fitted, extracting the image of the target object according to the closed area formed by the second corner points.
Specifically, as shown in fig. 2, the step of identifying the first corner point of the closed contour line according to the preset rule specifically includes:
s310, detecting all straight lines in the closed contour line;
s320, identifying and eliminating interference lines in the straight line to obtain an effective straight line;
s330, determining the edge straight line of the target object according to the effective straight line;
s340, acquiring all intersection points of the edge straight lines;
s350, extracting first corner points from the intersection points according to a second preset rule, and determining coordinates and the number of the first corner points.
And after the closed contour line is obtained, performing straight line detection on the closed contour line, such as using a Hough transform algorithm. During detection, the closed contour line can be divided into regions according to the preset shape, and if the preset shape is a rectangle, the closed contour line can be divided into an upper part, a lower part, a left part and a right part for detection. The detection of each divided area corresponds to a group of straight lines, the straight lines in the same group meet a certain rule according to the characteristics of a preset shape, a certain parameter range can be set according to an experimental value or a test value and the like, the interference lines in the straight lines in the same group are identified, the straight lines meeting the parameter range are judged to be effective straight lines, the straight lines not meeting the parameter range are judged to be interference lines, and the effective straight lines are obtained after all the interference lines are eliminated. The edge straight line of the target object can be obtained by fitting the same group of effective straight lines, and it should be noted that the edge straight line of the target object is a calculated value, and if the shape of the target object is inconsistent with the preset shape or a certain error exists in the recognition, the edge straight line of the target object may not be consistent with the real edge of the target object.
By the method, a plurality of edge straight lines can be obtained, all intersection points formed by the edge straight lines are obtained, and due to the characteristic of infinite length of the straight lines, intersection points which are irrelevant to the shape of the target object may exist in the intersection points, so that the first angular point needs to be extracted from the intersection points according to a second preset rule. The second preset rule specifically includes a position relationship of the corner points, an included angle range of adjacent corner points, and the like, where the position relationship and the included angle range are allowable ranges set according to the corner point characteristics of the preset shape. The first corner points obtained through the steps can be obtained by establishing a coordinate system in the scanning area image, determining the coordinates of the obtained first corner points by using the coordinate system as a reference, and counting the number of the first corner points. The number of the first corner points can be a standard for judging whether the shape of the target object is consistent with a preset shape.
Specifically, as shown in fig. 3, if yes, the step of extracting the image of the target object from the image of the scanning area according to the first corner point specifically includes:
s510, when the number of the first corner points is consistent with the number of the preset corner points, determining a first target extraction area according to the coordinates of the first corner points;
s520, an image of the target object is extracted from the scan region image according to the first target extraction region.
When the number of the first corner points is consistent with the number of the preset corner points, the shape of the target object can be considered to be consistent with the preset shape, the closed region enclosed and synthesized by the first corner points is used as a first target extraction region, the shape of the first target extraction region is approximately consistent with the preset shape so as to meet the use requirement of a user, and the position of the first target extraction region in the scanning region image is correspondingly determined due to the fact that the coordinates of the first corner points are determined. And acquiring the image in the first target extraction area in the scanning area image to obtain the image of the target object.
Specifically, as shown in fig. 4, if not, the step of determining, according to the closed contour line and the preset algorithm, second corner points whose number is consistent with that of the preset corner points, and extracting the image of the target object from the scan region image according to the second corner points specifically includes:
s610, when the number of the first corner points is inconsistent with the number of the preset corner points, calculating a minimum external polygon of the closed contour line, wherein the number of vertexes of the minimum external polygon is consistent with the number of the preset corner points;
s620, acquiring vertex coordinates of a minimum circumscribed polygon in the image of the scanning area, and taking the vertex coordinates as the position of a second corner point;
s630, determining a second target extraction area according to the vertex coordinates;
s640, an image of the target object is extracted from the scan area image according to the second target extraction area.
When the number of the first corner points is inconsistent with the number of the preset corner points, it can be considered that the target object with the same shape as the preset shape cannot be identified, and at this time, a second target extraction area with the same shape as the preset shape can be constructed, and the second target extraction area includes the closed contour lines of all the objects so as to extract the target object image. The construction of the second target extraction region can be obtained by calculating a minimum circumscribed polygon of the closed contour line, the minimum circumscribed polygon is a polygon with the smallest area, and the polygon has the corner features meeting the second preset rule, has the vertex number consistent with the preset corner number and can completely contain the closed contour line, and preferably has the polygon shape consistent with the preset shape so as to meet the use requirements of users.
And after the minimum circumscribed polygon is obtained, obtaining the coordinates of the vertex of the minimum circumscribed polygon in the scanning area image coordinate system, and taking the vertex coordinates as the position of the second corner point. And the second corner points surround and form a closed area to form a second target extraction area. And acquiring an image according to the position of the second target extraction area in the scanning area image to obtain an image of the target object. When the preset shape is a rectangle and the number of the preset corner points is four, preferably, the corresponding minimum circumscribed polygon is the minimum circumscribed rectangle.
The determination of the minimum circumscribed polygon may preset a direction, when there are a plurality of minimum circumscribed polygons that cannot be determined, a vertex of one minimum circumscribed polygon that is the same as the preset direction is selected as a second corner point, and a determination that the minimum circumscribed polygon is the same as the preset direction may be set according to a user's requirement, and if a certain side, a symmetric axis, etc. of the minimum circumscribed polygon may be set to be parallel to one of coordinate axes of a coordinate system established by the scan region image, the minimum circumscribed polygon may be determined to be the same as the preset direction, or other manners may be used, and no specific limitation is made herein. For example, when the predetermined shape is a rectangle and the target object is a circle, there may be a plurality of minimum bounding rectangles, and when only one minimum bounding rectangle cannot be determined, the rectangle in which one side of the rectangle is parallel to the X axis of the coordinate system established by the scan region image may be set as the minimum bounding rectangle.
Further, as shown in fig. 5, the scan target extracting method of the present embodiment further includes:
s700, after the image of the target object is extracted, when a black edge exists in the image of the target object, identifying the area of the image of the target object occupied by the black edge;
and S800, converting the image color of the region into a preset color.
After the image of the target object is extracted, when a black edge exists in the image of the target object, the area range of the image of the target object occupied by the black edge is identified, and the image color of the area range is converted into the preset color. Whether the black edge exists can be automatically detected or artificially judged. When the user artificially judges, the user can input an instruction for eliminating the black edge after seeing the black edge, and the scanning equipment processes the black edge according to the steps after receiving the instruction for eliminating the black edge; and automatically detecting, namely automatically executing the steps to process the black edge after the black edge is detected. The preset color should be consistent with the color of the target object to achieve the effect of eliminating the black edge, and the setting of the preset color can be selected by a user according to the color of the target object.
Further, the scan target extracting method of the present embodiment further includes:
after the image of the target object is extracted, the image of the target object is subjected to a transform process.
The image of the target object may be a polygon, and since the output shape of the image is a rectangle in many general-purpose applications (e.g., computer display, printing, etc.), the image of the target object may be subjected to a transformation process (e.g., perspective transformation, etc.) to make the output shape of the image of the target object rectangular, so as to be suitable for various applications.
The embodiment of the invention provides a scanning target extraction method, which comprises the steps of extracting closed contour lines of all objects in a scanning area image after the scanning area image is obtained, wherein the objects comprise target objects, identifying first corner points of the closed contour lines according to a first preset rule, judging whether the number of the first corner points is consistent with the number of the preset corner points or not, eliminating the interference of the non-target objects to a certain extent as the first preset rule is established according to the preset shape of the target object image to be extracted, and directly extracting the image of the target object from the scanning area image according to the first corner points when the judgment result is consistent, wherein the shape of the target object is considered to be consistent with the preset shape; when the judgment result is inconsistent, the target object consistent with the preset shape can not be identified, second corner points consistent with the preset corner points in number are determined according to the closed contour line and the preset algorithm, the preset algorithm ensures that the closed contour line can be completely included in the closed area formed by the second corner points, the closed area is consistent with the preset shape, the image of the target object can be extracted from the scanning area image according to the second corner points, and by the method, when the target object is in any shape or has an interfering object, the target object can be effectively extracted from the scanning area image, so that the scene adaptability of the image capturing device for scanning is improved.
In addition, an embodiment of the present invention further provides a scan target extracting apparatus, where the scan target extracting apparatus includes: the scanning target extracting program is stored on the memory and can run on the processor, and when being executed by the processor, the scanning target extracting program realizes the steps of the scanning target extracting method of the embodiment.
Furthermore, an embodiment of the present invention also provides an image capturing apparatus including the scan target extracting device of the above-described embodiment.
Furthermore, an embodiment of the present invention further provides a computer-readable storage medium, where a scan target extraction program is stored on the computer-readable storage medium, and when executed by a processor, the scan target extraction program implements the steps of the scan target extraction method of the foregoing embodiment.
The scan target extraction method in the embodiment can be applied to image capturing devices such as scanners, high-speed cameras, smart phones and tablet computers.
As shown in fig. 6, the image capturing apparatus may include: a processor 1001 (e.g., a CPU), a memory 1002, a data interface 1003, a communication bus 1004, and a camera 1005. Wherein a communication bus 1004 is used to enable connective communication between these components. The data interface 1003 may also include a standard wired interface (e.g., a USB interface or an IO interface), a wireless interface (e.g., a WI-FI interface). The memory 1002 may be a high-speed RAM memory or a non-volatile memory (e.g., a disk memory). The memory 1002 may be integrated with the processor or may be a storage device separate from the processor. The camera 1005 is used to acquire a scan area image.
Those skilled in the art will appreciate that the configuration of the device shown in fig. 6 does not constitute a limitation of the device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 6, the memory 1002, which is a kind of computer storage medium, may include therein an operating system, a data interface implementation program, a scan target extraction program, and the like. The processor 1001 may be configured to call a scan target extraction program stored in the memory 1002 and execute steps of implementing the scan target extraction method of the above-described embodiment.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (9)
1. A scan target extraction method, characterized by comprising the steps of:
acquiring a scanning area image;
extracting closed contour lines of all objects in the scanning area image, wherein the objects comprise target objects;
identifying a first corner of the closed contour line according to a first preset rule;
judging whether the number of the first angular points is consistent with the number of preset angular points or not;
if so, extracting the image of the target object from the scanning area image according to the first corner point;
if not, determining second corner points with the same number as the preset corner points according to the closed contour lines and a preset algorithm, and extracting the image of the target object from the scanning area image according to the second corner points;
if not, determining second corner points with the same number as the preset corner points according to the closed contour lines and a preset algorithm, and extracting the image of the target object from the scanning area image according to the second corner points specifically comprises the following steps:
when the number of the first angular points is inconsistent with the number of preset angular points, calculating a minimum circumscribed polygon of the closed contour line, wherein the number of vertexes of the minimum circumscribed polygon is consistent with the number of the preset angular points;
acquiring vertex coordinates of the minimum circumscribed polygon in the scanning area image, taking the vertex coordinates as the position of the second corner point, and selecting the vertex of one minimum circumscribed polygon in the same preset direction as the second corner point when the minimum circumscribed polygon has a plurality of undeterminable positions;
determining a second target extraction area according to the vertex coordinates;
and extracting the image of the target object from the scanning area image according to the second target extraction area.
2. The method for extracting a scan target according to claim 1, wherein the step of identifying the first corner point of the contour according to the first preset rule specifically comprises:
detecting all straight lines in the closed contour line;
identifying and eliminating interference lines in the straight lines to obtain effective straight lines;
determining an edge straight line of the target object according to the effective straight line;
acquiring all intersection points of the edge straight lines;
and extracting first corner points from the intersection points according to a second preset rule, and determining the coordinates and the number of the first corner points.
3. The method for extracting a scan target according to claim 2, wherein if the image of the target object is extracted from the scan region image according to the first corner point, the step specifically includes:
when the number of the first corner points is consistent with the number of preset corner points, determining a first target extraction area according to the first corner point coordinates;
and extracting the image of the target object from the scanning area image according to the first target extraction area.
4. The scan target extraction method of claim 1, wherein the number of the preset corner points is four.
5. The scanned-object extraction method of claim 4, wherein the minimum bounding polygon is a minimum bounding rectangle.
6. The scan target extraction method of any one of claims 1 to 3, further comprising:
after the image of the target object is extracted, when a black edge exists in the image of the target object, identifying a region of the image of the target object occupied by the black edge;
and converting the image color of the area into a preset color.
7. A scan target extraction device, characterized by comprising: memory, a processor and a scan target extraction program stored on the memory and executable on the processor, the scan target extraction program when executed by the processor implementing the steps of the method of any one of claims 1 to 6.
8. An image capturing apparatus characterized by comprising the scan target extracting device according to claim 7.
9. A computer-readable storage medium, characterized in that a scan target extraction program is stored thereon, which when executed by a processor implements the steps of the scan target extraction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710684808.XA CN107480666B (en) | 2017-08-10 | 2017-08-10 | Image capturing device, method and device for extracting scanning target of image capturing device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710684808.XA CN107480666B (en) | 2017-08-10 | 2017-08-10 | Image capturing device, method and device for extracting scanning target of image capturing device, and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107480666A CN107480666A (en) | 2017-12-15 |
| CN107480666B true CN107480666B (en) | 2020-08-07 |
Family
ID=60600344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710684808.XA Active CN107480666B (en) | 2017-08-10 | 2017-08-10 | Image capturing device, method and device for extracting scanning target of image capturing device, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107480666B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019201141A1 (en) * | 2018-04-18 | 2019-10-24 | Beijing Didi Infinity Technology And Development Co., Ltd. | Methods and systems for image processing |
| CN108805124B (en) * | 2018-04-18 | 2019-10-18 | 北京嘀嘀无限科技发展有限公司 | Image processing method and device, computer readable storage medium |
| CN109946703B (en) * | 2019-04-10 | 2021-09-28 | 北京小马智行科技有限公司 | Sensor attitude adjusting method and device |
| CN110298282B (en) * | 2019-06-21 | 2021-07-23 | 华南师范大学 | Document image processing method, storage medium and computing device |
| CN111178224B (en) * | 2019-12-25 | 2024-04-05 | 浙江大华技术股份有限公司 | Object rule judging method, device, computer equipment and storage medium |
| CN111832558A (en) * | 2020-06-15 | 2020-10-27 | 北京三快在线科技有限公司 | Character image correction method, device, storage medium and electronic equipment |
| CN112288820B (en) * | 2020-12-29 | 2021-04-27 | 深圳市六合智能感知系统科技有限公司 | Contour calculation method, device and equipment for regular object and storage medium |
| CN118485709B (en) * | 2024-07-11 | 2024-09-27 | 惠州市凯默金属制品有限公司 | Three-dimensional size measuring method, device and apparatus for automobile die casting die |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831578A (en) * | 2011-06-15 | 2012-12-19 | 富士通株式会社 | Image processing method and image processing device |
| CN104834919A (en) * | 2015-05-20 | 2015-08-12 | 东南大学 | Contour line based three-dimensional human face iteration preprocessing and feature point extracting method |
| CN105741268A (en) * | 2016-01-22 | 2016-07-06 | 江苏科技大学 | Visual localization method based on color block and topological relationship thereof |
| CN107016394A (en) * | 2017-02-27 | 2017-08-04 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | A kind of decussating fibers characteristic point matching method |
-
2017
- 2017-08-10 CN CN201710684808.XA patent/CN107480666B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831578A (en) * | 2011-06-15 | 2012-12-19 | 富士通株式会社 | Image processing method and image processing device |
| CN104834919A (en) * | 2015-05-20 | 2015-08-12 | 东南大学 | Contour line based three-dimensional human face iteration preprocessing and feature point extracting method |
| CN105741268A (en) * | 2016-01-22 | 2016-07-06 | 江苏科技大学 | Visual localization method based on color block and topological relationship thereof |
| CN107016394A (en) * | 2017-02-27 | 2017-08-04 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | A kind of decussating fibers characteristic point matching method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107480666A (en) | 2017-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107480666B (en) | Image capturing device, method and device for extracting scanning target of image capturing device, and storage medium | |
| CN108875723B (en) | Object detection method, device and system and storage medium | |
| CN110599548A (en) | Camera calibration method and device, camera and computer readable storage medium | |
| CN111899270B (en) | Card frame detection method, device, equipment and readable storage medium | |
| CN111291753B (en) | Text recognition method and device based on image and storage medium | |
| MX2008011002A (en) | Model- based dewarping method and apparatus. | |
| CN110232369A (en) | A kind of face identification method and electronic equipment | |
| WO2022134771A1 (en) | Table processing method and apparatus, and electronic device and storage medium | |
| CN110765891B (en) | Engineering drawing identification method, electronic equipment and related product | |
| CN106875408B (en) | Screenshot method and device and terminal equipment | |
| CN112434546A (en) | Face living body detection method and device, equipment and storage medium | |
| CN111079730B (en) | Method for determining area of sample graph in interface graph and electronic equipment | |
| CN110414649B (en) | DM code positioning method, device, terminal and storage medium | |
| CN107272899B (en) | VR (virtual reality) interaction method and device based on dynamic gestures and electronic equipment | |
| CN111553251A (en) | Certificate four-corner incomplete detection method, device, equipment and storage medium | |
| CN110008943B (en) | Image processing method and device, computing equipment and storage medium | |
| CN109726613B (en) | Method and device for detection | |
| CN108304840B (en) | Image data processing method and device | |
| CN111783561A (en) | Picture examination result correction method, electronic equipment and related products | |
| CN110135512B (en) | Picture identification method, equipment, storage medium and device | |
| CN113177941B (en) | Steel coil edge crack identification method, system, medium and terminal | |
| CN108647570B (en) | Zebra crossing detection method and device and computer readable storage medium | |
| CN114608521A (en) | Monocular distance measuring method and device, electronic equipment and storage medium | |
| CN112633188A (en) | Wall body identification method, device, equipment and medium of house type graph | |
| US20220198814A1 (en) | Image dewarping with curved document boundaries |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230928 Address after: Room 728, 7th Floor, Building A, Datang Times Commercial Complex, No. 2203 Meilong Avenue, Tsinghua Community, Longhua Street, Longhua District, Shenzhen City, Guangdong Province, 518110 Patentee after: Shenzhen Guoguan Intelligent Technology Co.,Ltd. Address before: 701, Huatong Building, No. 19, Zone 2, Xiazaoxincun, Gaofeng Community, Dalang Office, Longhua New District, Shenzhen City, Guangdong Province, 518131 Patentee before: SHENZHEN BIHAIYANGFAN TECHNOLOGY CO.,LTD. |