KR101699063B1 - System, method and recording medium for map image recognition by using place names straight lines - Google Patents

Abstract

A method and system for map image recognition using nominal straight lines are disclosed. A method of recognizing a map includes: recognizing a character in an input image using a character recognition technique; Searching for a place name on the map and a location of the place name corresponding to the character; And obtaining a map area matching the input image using a straight line connecting a center point of the input image and a center point of the character and a location of the location name.

Description

TECHNICAL FIELD [0001] The present invention relates to a map image recognition method, a system, and a recording medium using a named straight line,

Embodiments of the present invention relate to techniques for recognizing a map image and finding a map area referred to by the recognized image.

In the map recognition method, it is possible for a person to directly see the map image and recognize the area referred to by the map image. However, there is an inconvenience in that a person manually must find and recognize the area referred to by the map image.

As another method, there is a map recognition method based on a map topography. In a state where a database of the topographic information of the map is built in advance, the terrain information is extracted from the inputted map image, A map area including the terrain information can be found.

For example, Korean Patent Laid-Open Publication No. 10-2013-0052970 (published May 23, 2013) entitled " Apparatus and Method for Providing Map Service Using Image Recognition Technology "includes extracting a feature point from a map image by receiving a map image, Discloses a technique for providing map information on a final image matching with a map image using minutiae points.

However, the conventional map recognition method has a problem that it is difficult to construct a database for the map image, and when the map image other than the map image in which the database is constructed is input, the map is not recognized.

A method and system for recognizing a map image without being influenced by the type or form of the map is provided.

A method and system for recognizing place names in a map image using optical character reader (OCR) technology is provided.

The present invention provides a method and system for providing a recognition result of a map image based on a POI (Point of Interest).

And provides a method and a system that can provide accurate map recognition results by discriminating the mistakes of place names.

A computer-implemented map recognition method comprising: recognizing a character in an input image using a character recognition technique; Searching for a place name on the map and a location of the place name corresponding to the character; And acquiring a map area matching the input image using a straight line connecting the center point of the input image and the center point of the character and the location of the location name.

A recognition unit for recognizing a character in an input image using a character recognition technique; A search unit for searching for a place name on the map and a location of the place name corresponding to the character; And a providing unit for acquiring a map area matching the input image by using a straight line connecting a center point of the input image and a center point of the character and a location of the place name, .

A computer readable medium comprising instructions for controlling a computer system to provide a map recognition function, the instructions comprising: recognizing a character in an input image using a character recognition technique; Searching for a place name on the map and a location of the place name corresponding to the character; And obtaining a map area matching the input image using a straight line connecting the center point of the input image and the center point of the character and the location of the place name, Capable storage medium.

According to an embodiment of the present invention, a POI (Point of Interest) is recognized in a map image by using an optical character reader (OCR) technology, and a map area referred to by the map image is searched based on the recognized name, It is possible to recognize all map images such as general paper maps and maps as well as precise electronic maps without being influenced by the shape.

According to an embodiment of the present invention, a map area referred to by a map image can be accurately located by utilizing a database including location information without using a database of the entire terrain information of the map image by recognizing the map image based on the place name have.

According to the embodiment of the present invention, it is possible to ensure the accuracy of the map recognition result by providing a strong recognition technique for noise by distinguishing the misidentified place names recognized from the map images and the recognized place names

1 illustrates an overview of a user terminal and a map recognition system in an embodiment of the present invention.
2 is a block diagram for explaining an internal configuration of a map recognition system according to an embodiment of the present invention.
3 is a flowchart showing a map recognition method according to an embodiment of the present invention.
4 is a flowchart illustrating a process of recognizing a place name in an embodiment of the present invention.
5 to 12 are illustrative drawings for explaining a specific process of place name recognition in an embodiment of the present invention.
13 is a flowchart illustrating a process of acquiring a map area referred to by an input image according to an exemplary embodiment of the present invention.
FIGS. 14 to 20 are illustrative drawings for explaining a specific process of acquiring a map area in an embodiment of the present invention. FIG.
21 is a block diagram for explaining an example of the internal configuration of a computer system in an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

The embodiments of the present invention are directed to a technique for finding an actual map area to which an input image is input by receiving a map image and can be applied to various map service fields such as a map search service, a location confirmation service, a route search /

1 illustrates an overview of a user terminal and a map recognition system in an embodiment of the present invention. FIG. 1 shows a map recognition system 100 and a user terminal 101. FIG. 1, it may mean that data can be transmitted and received between the map recognition system 100 and the user terminal 101 via the wired / wireless network.

The user terminal 101 is connected to a web / mobile site related to the map recognition system 100 or a service dedicated application (map recognition) by a PC, a smart phone, a tablet, a wearable computer, Application) can be installed and executed. At this time, the user terminal 101 can perform service-wide operations such as service screen configuration, data input, data transmission / reception, and data storage under the control of a web / mobile site or a dedicated application.

The map recognition system 100 serves as a service platform for providing a map service to a user terminal 101 as a client. In particular, the map recognition system 100 receives the map image from the user terminal 101, recognizes the location information through the OCR technology in the inputted map image, and displays the actual map area (latitude / Longitude and boundary area) of the mobile terminal. At this time, the map recognition system 100 may be implemented in an application form on the user terminal 101, but is not limited thereto and may be implemented in a service platform providing a service requiring map recognition in a client-server environment Is also possible.

FIG. 2 is a block diagram for explaining an internal configuration of a map recognition system according to an embodiment of the present invention. FIG. 3 is a flowchart illustrating a map recognition method according to an embodiment of the present invention.

2, the map recognition system 200 according to the present embodiment may include a processor 210, a bus 220, a network interface 230, a memory 240, and a database 250 . The memory 240 may include an operating system 241 and a map recognition routine 242. The processor 210 may include a recognition unit 211, a search unit 212, and a provider 213. In other embodiments, the map recognition system 200 may include more components than the components of FIG.

The memory 240 may be a computer-readable recording medium and may include a permanent mass storage device such as a random access memory (RAM), a read only memory (ROM), and a disk drive. Also, the memory 240 may store program codes for the operating system 241 and the map recognition routine 242. [ These software components may be loaded from a computer readable recording medium separate from the memory 240 using a drive mechanism (not shown). Such a computer-readable recording medium may include a computer-readable recording medium (not shown) such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, or a memory card. In other embodiments, the software components may be loaded into the memory 240 via the network interface 230 rather than from a computer readable recording medium.

The bus 220 may enable communication and data transfer between components of the map recognition system 200. The bus 220 may be configured using a high-speed serial bus, a parallel bus, a Storage Area Network (SAN), and / or other suitable communication technology.

The network interface 230 may be a computer hardware component for connecting the map recognition system 200 to a computer network. The network interface 230 may connect the map recognition system 200 to a computer network via a wireless or wired connection.

The database 250 includes a place name database (DB) storing and maintaining information necessary for map recognition, in particular, place name information. For example, the place name information is information on a POI (point of interest) The latitude and the longitude, which are position information of each place name, may be matched. Table 1 shows an example of a place name DB. Although FIG. 2 shows that the database 250 is included in the map recognition system 200, it is also possible to exist as an external database constructed on a separate system.

nomination Latitude Hardness Gangnam-gu Office 37.517319 127.047498 Gangnam Station 37.497984 127.027639 Mary Conventions Dottie Memorial Hospital 37.598214 126.928786 Myongji College 37.584667 126.925398 Water station 37.547765 126.922976 Sogang University 37.551727 126.941062 Sejong City Hall 36.592924 127.292382 Electronic hall 37.580984 126.888393

The processor 210 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations of the map recognition system 200. [ The instructions may be provided by the memory 240 or the network interface 230 and to the processor 210 via the bus 220. The processor 210 may be configured to execute the program code for the recognition unit 211, the search unit 212, and the provider 213. [ Such program code may be stored in a recording device such as memory 240. [

The recognition unit 211, the search unit 212, and the provider 213 may be configured to perform the steps S310 to S330 of FIG.

In step S310, the recognition unit 211 receives the map image from the user terminal as an input image, and recognizes the place name in the received map image. At this time, the user terminal can acquire an imaged map in various ways such as a camera photographing, a screen capture, and a map, and can input the imaged map to the map recognition system 200 as an input image. In other words, not only an electronic map but also a paper map such as a route map, a sightseeing map, a map imaged by a camera or a screen capture, and the like can be utilized as an input image for map recognition. Accordingly, the recognition unit 211 may extract the character region from the map image, and perform OCR on the extracted character region to recognize the character on the map image as a place name.

In step S320, the search unit 212 can search for and obtain the location on the actual map with respect to the place name recognized in step S310. In other words, the search unit 212 can search for a place name recognized in the map image through the OCR from the place name DB storing location information for each place name, and obtain the longitude and latitude, which are the locations of the place name.

The providing unit 213 may provide the actual map area corresponding to the map image as the map recognition result based on the location information of each place name acquired through the location DB search in step S320 in step S330. In other words, the provider 213 may provide the map information including the place name recognized as OCR as a recognition result of the map image. For example, the provider 213 compares the position on the map image with the location on the actual map obtained through the search of the place name DB with respect to the place name recognized in the map image, and calculates the center point (latitude / longitude) It is possible to calculate the boundary, and the map image recognition result can be displayed by calculating the level having the calculated center point and the boundary area and matching the size of the output screen.

The concrete process of recognizing place names in map images is as follows.

4 is a flowchart illustrating a process of recognizing a place name in an embodiment of the present invention. The name recognition process according to the embodiment may be performed by the recognition unit 211 of the map recognition system 200 described with reference to FIGS.

In step S401, the recognition unit 211 may receive a map image (hereinafter, referred to as an 'input image') imaged through a camera or an image capture from a user terminal. In order to recognize a place name, The region can be extracted. Hereinafter, it is assumed that a map as shown in FIG. 5 is input as an input image.

Since characters have many corners, if the corners are concentrated in a narrow region, the character region can be extracted on the assumption that the probability of the character is high. For example, the recognition unit 211 may detect a corner in the input image using a corner detector such as a Harris corner detector. 6 shows a result of detecting corners in an input image using a Harris corner detector. Then, the recognition unit 211 may generate a grid of binary corner grid maps, and then process the markings on the cells where the corners exist in the binary corner grid map. FIG. 7 shows the result of marking a grid cell where a corner exists in the binary corner grid map. Then, the recognition unit 211 can perform noise removal and area expansion on the marked character area in the binary corner grid map using the binary image morphology. FIG. 8 shows a result of performing noise removal and area expansion on the marking image of FIG. 9, the recognition unit 211 may detect contours in the binary corner grid map and process the detected contours into a rectangular area. At this time, the rectangle 901, (junk) can be processed. In other words, as shown in Fig. 9, a rectangle 902 satisfying the minimum size can be detected as a valid area, that is, a character area, after the outline is enclosed by a rectangle. At this time, the recognition unit 211 expands a rectangle detected as a character region by a certain cell (e.g., one cell) vertically and horizontally and determines an extended rectangular region 1002 as a final character region .

Referring again to FIG. 4, in step S402, the recognition unit 211 performs OCR on the character area recognized in step S401, and recognizes the character read in the corresponding area as a place name. In other words, the recognizing unit 211 can perform the OCR in the rectangular area 1002 determined as the final character area in FIG. 10 to obtain the place name. At this time, in order to increase the accuracy of the OCR, it is possible to improve the accuracy of the OCR result by post-processing with the correction of the query word. FIG. 11 shows a result of performing OCR on a character region detected from an input image. Therefore, the recognition unit 211 can acquire the name (POI name) of the main place listed in the input image.

As described above, in the present embodiment, by obtaining a name for map recognition using OCR technology, not only the specific map but also all kinds of maps such as general paper map and map can be recognized as well as electronic map.

Next, the specific process of acquiring the map area (center point and boundary area) referred to by the input image is as follows.

The providing unit 213 may calculate the center point and the boundary area of the area referred to by the input image to provide the map recognition result. In order to do this, the search unit 212 searches for a place name recognized as OCR in the place name DB, and obtains a place name on the actual map. FIG. 12 shows a place name on the actual map 1220 acquired through the location DB search with respect to the place name recognized in the input image. Thus, the provider 213 can perform the map image recognition based on the location name obtained through the recognition unit 211 and the location name searched through the search unit 212.

13 is a flowchart illustrating a process of acquiring a map area referred to by an input image according to an exemplary embodiment of the present invention. The process of acquiring the map area according to one embodiment may be performed by the provider 213 of the map recognition system 200 described with reference to FIG. 2 and FIG.

In step S1301, the providing unit 213 may obtain a nominal straight line for the recognized name in the input image. In this case, as shown in FIG. 14, the providing unit 213 can obtain the slope between the center point and each place name in the input image 1410. In this specification, the center point of the input image and the center point The straight line 1403 connecting the first straight line 1401 and the second straight line 1403 will be referred to as a first nominal straight line.

The providing unit 213 may obtain the intersection between the first nominal straight lines by projecting the first nominal straight line on the map area including the searched location searched through the location DB search in step S1302. In other words, as shown in FIG. 15, the providing unit 213 obtains the slope of the first nominal straight line 1503 obtained in step S1301 at each nominal position acquired through the search of the place name DB in the actual map 1520 It is possible to acquire the intersection point between the first designation straight lines 1503 after mapping the straight line having the same straight line.

The providing unit 213 may perform density-based clustering on the intersections acquired in step S1302 to obtain a set of significant intersections among the intersections between the first nominal straight lines in step S1303 . If the location of the location in the input image matches the location of the location on the actual map, the intersection point between the first location lines will match the coordinates of the center of the input image. However, the location name (FIG. 12) on the actual map acquired through the location DB search and the location name (FIG. 14) recognized on the input image may show errors due to misrecognition or image distortion. If a plurality of location names are identical or similar even if the location name of the input image does not exactly match the location name of the actual map, as shown in FIG. 16, most of the intersections are concentrated in one place and the density of the intersections is high in a specific area have. Based on this assumption, the provider 213 can use the density-based clustering to find a set of significant intersections, that is, a region 1608 having a high density of intersections. For example, density-based clustering is based on the density of objects, and it is known to perform clustering in such a manner that regions with low density are regarded as noise and clusters with high density are clustered based on the density of objects (for example, density-based spatial clustering of applications with noise), OPTICS (Ordering points to identify the clustering structure, etc.).

In step S1304, the providing unit 213 calculates an average value of the positions (latitude / longitude) of the intersections in the set of significant intersections acquired in step S1303, and calculates the center point (latitude / longitude) Can be obtained. As shown in FIG. 16, the average value of the intersection points in the region 1608 where the distribution of the intersection points is concentrated may be the center point on the map, and this may be regarded as the center coordinates corresponding to the center of the input image on the real map 1620 . For example, the calculator 213 calculates the distance between the intersections, calculates the average value of the remaining intersections excluding the noise when the distance between the intersections exceeds a certain threshold, regards the noise as noise, .

Among the place names on the actual maps acquired through the DB search for the place names recognized in the input image, the misidentified place names may be included. If many place names are misunderstood, that is, when there is a lot of noise, the accuracy of the map recognition becomes poor. Therefore, in order to solve this problem, it is necessary to distinguish the misidentified place names from the known place names. In particular, if map recognition is performed based on the density of recognized place names, it is difficult to distinguish misidentified place names. Thus, in this embodiment, a method of distinguishing misidentified place names is proposed in order to provide more accurate and noise-resistant map recognition results.

In step S1305, the providing unit 213 searches for a nominal straight line for a place name retrieved from the place name DB on the basis of the center point on the actual map acquired in step S1304, that is, A straight line can be obtained.

In step S1306, the provisioning unit 213 distinguishes the misidentified place name from the authenticated place name using the slope difference between the first nominal straight line projected on the actual map and the second nominal straight line obtained on the actual map, Can be removed. 17, the providing unit 213 compares the slopes of the first nominal straight line (nominal straight line of the input image) and the second nominal straight line (nominal straight line on the actual map) with respect to each place name, Any place name that exceeds the range can be regarded as noise, and the place name considered as noise can be removed. In FIG. 17, when the first nominal straight line 1703 and the second nominal straight line 1704 are compared with each other in the case of location name 5, it can be seen that the tilt error is very large. Accordingly, in this embodiment, the accuracy of the map recognition result for the input image can be improved by eliminating the misrecognized place name of the input image.

In step S1307, the providing unit 213 may obtain a boundary in which the input image is represented by an actual map using the distance between the center point and the place name of the input image, and the image size of the input image. 18, the providing unit 213 obtains the distance ImgD between the center point and the place name of the input image 1810 and the width ImgW and the height ImgH of the input image 1810 based on the center point of the input image 1810. Specifically, ), And calculate the distance MapD between the center point and the place name of the actual map 1920 as shown in Fig. The providing unit 213 uses the distance ImgD between the center point and the place name of the input image, the width ImgW and height ImgH of the input image, and the distance MapD between the center point and the place name of the actual map, You can calculate the width (MapW) and height (MapH) of the actual map you are referring to.

The width (MapW) and height (MapH) of the actual map can be defined by the proportional expressions as shown in the following equations (1) and (2).

19, the providing unit 213 calculates the width MapW and the height MapH on the actual map 1920 proportional to the input image 1910, Can be obtained.

Thus, the providing unit 213 can provide a map area having a border with the previously calculated map center point and a scale map corresponding to the size of the output screen, as an image recognition result. For example, a map area 2020 shown in FIG. 20 may be provided as a map image recognition result for the input image in FIG. 5, and a map area 2020 corresponding to the recognition result may correspond to a location name recognized in the input image The POI 2006 may be included. Accordingly, the user terminal providing the input image can receive the map information including the recognized name from the input image from the map recognition system and display it as the recognition result of the input image.

Therefore, the map recognition system according to the present invention recognizes the place name through the OCR technology in the map image inputted by inputting the map image, and based on the recognized place name, displays the actual map area (latitude / longitude and boundary area) Can be found. In particular, the map recognition system according to the present invention can easily and precisely find the region referred to by the input image by applying the concept of the nominal straight line, and can provide a noise-resistant recognition result.

21 is a block diagram for explaining an example of the internal configuration of a computer system in an embodiment of the present invention. The computer system 2100 includes at least one processor 2110, a memory 2120, a peripheral interface 2130, an input / output subsystem 2140, A power circuit 2150, and a communication circuit 2160. [ At this time, the computer system 2100 may correspond to a user terminal.

The memory 2120 can include, for example, a high-speed random access memory, a magnetic disk, SRAM, DRAM, ROM, flash memory or non-volatile memory. have. The memory 2120 may include software modules, a set of instructions, or various other data required for operation of the computer system 2100. At this point, accessing the memory 2120 from other components, such as the processor 2110 or the peripheral device interface 2130, may be controlled by the processor 2110.

Peripheral device interface 2130 may couple the input and / or output peripheral devices of computer system 2100 to processor 2110 and memory 2120. Processor 2110 may execute a variety of functions and process data for computer system 2100 by executing a software module or set of instructions stored in memory 2120. [

Input / output subsystem 2140 may couple various input / output peripherals to peripheral interface 2130. For example, input / output subsystem 2140 may include a controller for coupling a peripheral, such as a monitor, keyboard, mouse, printer, or a touch screen or sensor, as needed, to peripheral interface 2130. According to another aspect, the input / output peripheral devices may be coupled to the peripheral device interface 2130 without going through the input / output subsystem 2140.

The power circuitry 2150 may provide power to all or a portion of the components of the terminal. For example, the power circuitry 2150 may include one or more power supplies, such as a power management system, a battery or alternating current (AC), a charging system, a power failure detection circuit, a power converter or inverter, And may include any other components for creation, management, distribution.

Communication circuitry 2160 may enable communication with other computer systems using at least one external port. Or as described above, the communication circuit 2160 may communicate with other computer systems by transmitting and receiving an RF signal, also known as an electromagnetic signal, including RF circuitry, as needed.

21 is merely an example of the computer system 2100, and the computer system 2100 may include additional components not shown in FIG. 21, Lt; RTI ID = 0.0 > components. ≪ / RTI > For example, in addition to the components shown in FIG. 21, a computer system for a communication terminal in a mobile environment may further include a touch screen, a sensor, and the like, and various communication methods (WiFi, 3G, LET , Bluetooth, NFC, Zigbee, etc.). Components that may be included in computer system 2100 may be implemented in hardware, software, or a combination of both hardware and software, including one or more signal processing or application specific integrated circuits.

The methods according to embodiments of the present invention may be implemented in the form of a program instruction that can be executed through various computer systems and recorded in a computer-readable medium.

The program according to the present embodiment can be configured as a PC-based program or an application dedicated to a mobile terminal. The map recognition app according to the present embodiment may be implemented as an independently operating program or as an in-app form of a specific application (e.g., a map service program) to operate on the specific application . ≪ / RTI >

In addition, the methods according to embodiments of the present invention can be performed by an application associated with the map recognition system by controlling the user terminal. Further, such an application can be installed in a user terminal through a file provided by a file distribution system. For example, the file distribution system may include a file transfer unit (not shown) for transferring the file at the request of the user terminal.

As described above, according to the embodiment of the present invention, by using the OCR technology, the place name is recognized in the map image and the map area referred to by the map image is searched based on the recognized place name, In addition, it can recognize all map images such as ordinary paper maps and maps. In addition, according to the embodiment of the present invention, it is possible to accurately recognize the map area referred to by the map image by utilizing the database including the location information without using the database of the entire terrain information of the map image by recognizing the map image based on the place name Can be found. According to the embodiment of the present invention, it is possible to ensure the accuracy of the map recognition result by providing a strong recognition technology for noise by distinguishing the misidentified place names recognized from the map images and the recognized landmarks.

The apparatus described above may be implemented as a hardware component, a software component, and / or a combination of hardware components and software components. For example, the apparatus and components described in the embodiments may be implemented within a computer system, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA) , A programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For ease of understanding, the processing apparatus may be described as being used singly, but those skilled in the art will recognize that the processing apparatus may have a plurality of processing elements and / As shown in FIG. For example, the processing unit may comprise a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as a parallel processor.

The software may include a computer program, code, instructions, or a combination of one or more of the foregoing, and may be configured to configure the processing device to operate as desired or to process it collectively or collectively Device can be commanded. The software and / or data may be in the form of any type of machine, component, physical device, virtual equipment, computer storage media, or device , Or may be permanently or temporarily embodied in a transmitted signal wave. The software may be distributed over a networked computer system and stored or executed in a distributed manner. The software and data may be stored on one or more computer readable recording media.

The method according to an embodiment may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions to be recorded on the medium may be those specially designed and configured for the embodiments or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. For example, it is to be understood that the techniques described may be performed in a different order than the described methods, and / or that components of the described systems, structures, devices, circuits, Lt; / RTI > or equivalents, even if it is replaced or replaced.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

200: Map recognition system
211:
212:
213: Offering

Claims (15)

In a computer-implemented map recognition method,
Recognizing a character in an input image using a character recognition technique;
Searching for a place name on the map and a location of the place name corresponding to the character; And
Acquiring a map area matching the input image using a straight line connecting a center point of the input image and a center point of the character and a location of the location name
Lt; / RTI >
The step of acquiring the map area comprises:
Obtaining center coordinates on a map matching the center point of the input image using an intersection between the straight lines projected at a location of the place name on the map including the place name; And
Acquiring a boundary region matching a size of the input image with reference to the center coordinates;
/ RTI > The method according to claim 1,
Wherein the step of acquiring the boundary region matching the size of the input image comprises:
Obtaining a boundary that matches the size of the input image using the distance between the center point of the input image and the center point of the character and the distance between the center coordinate and the location of the place name
And a map recognizing method. The method according to claim 1,
The step of recognizing the character comprises:
Recognizing the character in the input image using an optical character reader (OCR)
And a map recognizing method. The method according to claim 1,
Wherein obtaining the center coordinates comprises:
Projecting the straight line to a location of the location on the map containing the location name to obtain an intersection between the straight lines;
Obtaining a set of significant intersections through density-based clustering for the obtained intersections; And
Calculating an average value of positions of intersections belonging to the set and recognizing the average value as the center coordinates
/ RTI > The method according to claim 1,
Wherein the step of acquiring the boundary region matching the size of the input image comprises:
Calculating a size of the input image based on a center point of the input image;
Calculating a character distance that is a distance between a center point of the input image and a center point of the character;
Calculating a nominal distance that is a distance between the center coordinate and the location of the nominal name; And
Calculating a size of a map area that is proportional to the size of the input image around the center coordinates using the character distance and the nomination distance
/ RTI > The method according to claim 1,
The step of acquiring the map area comprises:
Comparing the straight line connecting the center coordinates and the location of the place name with the straight line to determine whether the place name is misrecognized
Further comprising:
Wherein the step of acquiring the boundary region matching the size of the input image comprises:
And recognizing the mistaken place name as noise and acquiring the boundary area using the location of the recognized place name
And a map recognizing method. The method according to claim 6,
The step of determining whether or not the place name is mistaken is performed by:
If the slope difference between the straight line and the second straight line is within the permissible range, it is determined that the landmark is a well-known place name, and if the slope difference between the straight line and the second straight line is out of the allowable range,
And a map recognizing method. A recognition unit for recognizing a character in an input image using a character recognition technique;
A search unit for searching for a place name on the map and a location of the place name corresponding to the character; And
Acquiring a map area matching the input image using a straight line connecting a center point of the input image and a center point of the character and a location of the place name,
Lt; / RTI >
Wherein the providing unit comprises:
Acquiring a center coordinate on a map which is matched with a center point of the input image by using an intersection between the straight lines projected on a location of the place name on the map including the place name and obtaining the map area based on the center coordinate,
Acquiring a boundary region matching the size of the input image based on the center coordinates
The map recognition system comprising: 9. The method of claim 8,
Wherein the providing unit comprises:
Obtaining a boundary that matches the size of the input image using the distance between the center point of the input image and the center point of the character and the distance between the center coordinate and the location of the place name
The map recognition system comprising: 9. The method of claim 8,
Wherein,
Recognizing the character in the input image using an optical character reader (OCR)
The map recognition system comprising: 10. The method of claim 9,
Wherein the providing unit comprises:
Projecting the straight line to a position of the place name on the map including the place name to obtain an intersection point between the straight lines,
Obtaining a set of significant intersections through density-based clustering for the obtained intersections,
Calculating an average value of positions of intersections belonging to the set and recognizing the average value as the center coordinates
The map recognition system comprising: 10. The method of claim 9,
Wherein the providing unit comprises:
Calculating a size of the input image based on a center point of the input image,
Calculating a character distance which is a distance between a center point of the input image and a center point of the character,
Calculating a nominal distance that is a distance between the center coordinate and the position of the nominal name,
Calculating the size of the map area that is proportional to the size of the input image around the center coordinates using the character distance and the nomination distance
The map recognition system comprising: 10. The method of claim 9,
Wherein the providing unit comprises:
Comparing the straight line connecting the center coordinates and the location of the place name with the straight line to determine whether the place name is misrecognized,
And acquiring the boundary area using the location of the recognized name according to the result of the determination of whether or not the image is mistranslated
The map recognition system comprising: 14. The method of claim 13,
Wherein the providing unit comprises:
If the slope difference between the straight line and the second straight line is within the permissible range, it is determined that the landmark is a well-known place name, and if the slope difference between the straight line and the second straight line is out of the allowable range,
The map recognition system comprising: A computer readable medium comprising instructions for controlling a computer system to provide a map recognition function,
The command includes:
Recognizing a character in an input image using a character recognition technique;
Searching for a place name on the map and a location of the place name corresponding to the character; And
Acquiring a map area matching the input image using a straight line connecting a center point of the input image and a center point of the character and a location of the location name
The method comprising: controlling the computer system by a method comprising:
The step of acquiring the map area comprises:
Obtaining center coordinates on a map matching the center point of the input image using an intersection between the straight lines projected on the location of the place name on the map including the place name; And
Acquiring a boundary region matching a size of the input image with reference to the center coordinates;
≪ / RTI >

Images