WO2016003193A1 - Method and system for recognizing map image using toponyms and straight lines, and recording medium - Google Patents

Abstract

Disclosed are a method and a system for recognizing a map image using toponyms straight lines. The method for recognizing a map may comprise the steps of: recognizing text on an inputted image by means of a text recognition technology; searching, on a map, for a toponym and a location therefor corresponding to the text; acquiring a region on the map matching the inputted image by means of a straight line connecting the central point of the inputted image and the central point of the text, and the location of the toponym.

Description

Map Image Recognition Method, System and Recording Media

Embodiments of the present invention relate to a technique of recognizing a map image and finding a map area indicated by the recognized image.

In the map recognition method, a person may directly recognize the area indicated by the map image by looking at the map image, but this is inconvenient for a person to manually find and recognize the area indicated by the map image.

Another method is the map recognition method based on the map terrain, which has extracted the terrain information from the input map image after constructing the database of the terrain information of the map in advance and then searching the extracted terrain information from the database. You can find a map area that contains terrain information.

For example, Korean Patent Laid-Open Publication No. 10-2013-0052970 (published May 23, 2013), “Map service providing apparatus and method using image recognition technology,” receives a map image, extracts feature points from a map image, and extracts the extracted points. A technology for providing map information on a final image that matches a map image using feature points is disclosed.

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

Provides a method and system for recognizing map images without being affected by the type or shape of the map.

It provides a method and system for recognizing names in a map image using optical character reader (OCR) technology.

The present invention provides a method and system for providing recognition results of map images based on a point of interest (POI).

It provides a method and system that can discern misperceptions of names and provide accurate map recognition results.

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 corresponding to the text and the location of the place name; And acquiring a map area matching the input image by 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.

A recognition unit for recognizing a character in the input image by using a character recognition technology; A search unit for searching for a place name on the map corresponding to the text and the location of the place name; And a providing unit which obtains a map area matching the input image by 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 and providing the result as a recognition result of the input image. To provide.

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 character recognition technology; Searching for a place name on the map corresponding to the text and the location of the place name; And acquiring a map area matching the input image by 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. Provides possible storage media.

According to an exemplary embodiment of the present invention, a point of interest (POI) is recognized in a map image by using an optical character reader (OCR) technology, and the map area indicated by the map image is found based on the recognized name. It is able to recognize all map images such as general paper maps and directions as well as precise electronic maps without being affected by the form.

According to an embodiment of the present invention, by recognizing a map image based on a place name, the map area indicated by the map image can be accurately found by using a database including the place name information without using a database of the topographic information of the map image. have.

According to an exemplary embodiment of the present invention, by distinguishing a misrecognized name and a recognized name among the names recognized in the map image, a recognition technology that is strong against noise may be provided to ensure accuracy of the map recognition result.

1 illustrates an overview of a user terminal and a map recognition system according to an embodiment of the present invention.

2 is a block diagram illustrating an internal configuration of a map recognition system according to an embodiment of the present invention.

3 is a flowchart illustrating 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 exemplary diagrams for describing a specific process of name recognition according to an embodiment of the present invention.

FIG. 13 is a flowchart illustrating a process of obtaining a map area indicated by an input image according to an embodiment of the present invention.

14 to 20 are exemplary diagrams for describing a specific process of obtaining a map area according to an embodiment of the present invention.

21 is a block diagram for explaining an example of an internal configuration of a computer system according to one embodiment of the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

The present exemplary embodiments relate to a technology for finding an actual map area indicated by an input image by receiving a map image, and may be applied to various map service areas such as a map search service, a location check service, and a route finder / route guide service.

1 illustrates an overview of a user terminal and a map recognition system according to an embodiment of the present invention. 1 illustrates a map recognition system 100 and a user terminal 101. In FIG. 1, an arrow may mean that data may be transmitted and received between the map recognition system 100 and the user terminal 101 through a wired / wireless network.

The user terminal 101 is a PC, a smart phone, a tablet, a wearable computer, or the like, and accesses a web / mobile site related to the map recognition system 100 or a service-only application (map recognition). It may mean all terminal devices capable of installing and executing the app). In this case, the user terminal 101 may perform overall service operations such as service screen configuration, data input, data transmission, 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 which is a client. In particular, the map recognition system 100 receives a map image from the user terminal 101, recognizes name information in the input map image through OCR technology, and uses an actual map area (latitude) that the map image refers to based on the recognized name. It can provide platform services to find (hardness and boundary area). In this case, the map recognition system 100 may be implemented in an application form on the user terminal 101, but is not limited thereto. The map recognition system 100 may be implemented in a form of a service platform that provides a service requiring map recognition in a client-server environment. It is also possible.

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

As shown in FIG. 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 recognizer 211, a searcher 212, and a provider 213. In other embodiments, the map recognition system 200 may include more components than the components of FIG. 2.

The memory 240 is a computer-readable recording medium and may include a permanent mass storage device such as random access memory (RAM), read only memory (ROM), and a disk drive. In addition, program code for the operating system 241 and the map recognition routine 242 may be stored in the memory 240. 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 separate 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, a memory card, and the like. In other embodiments, the software components may be loaded into the memory 240 via the network interface 230 rather than the computer readable recording medium.

The bus 220 may enable communication and data transmission 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 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 through a wireless or wired connection.

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

nomination Latitude Hardness Gangnam-gu Office 37.517319 127.047498 Gangnam Station 37.497984 127.027639 Maria Sisters Doti Memorial Hospital 37.598214 126.928786 Myongji College 37.584667 126.925398 A constant 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 to the processor 210 by the memory 240 or the network interface 230 and via the bus 220. The processor 210 may be configured to execute program codes for the recognizer 211, the searcher 212, and the provider 213. Such program code may be stored in a recording device such as memory 240.

The recognizer 211, the searcher 212, and the provider 213 may be configured to perform the steps S310 to S330 of FIG. 3.

In operation S310, the recognition unit 211 may receive a map image from the user terminal as an input image, and then recognize the place name in the received map image. In this case, the user terminal may acquire a map imaged by various methods such as camera shooting, screen capture, and directions, and may input it as an input image to the map recognition system 200. In other words, as an input image for map recognition, not only an electronic map, but also a map, a paper map such as a tourist map, a map imaged by a camera or a screen capture, etc. may be used regardless of the form or type of map. Accordingly, the recognition unit 211 may extract the text area from the map image and perform OCR on the extracted text area to recognize the text on the map image as a place name.

In operation S320, the search unit 212 may search for and obtain an actual location on a map from a geographical name DB with respect to the geographical name recognized in operation S310. In other words, the search unit 212 may search for a place name recognized in the map image through the OCR in a place name DB in which location information for each place name is stored, and acquire a longitude and latitude which are locations of the place name.

In operation S330, the provider 213 may provide an actual map area corresponding to the map image as a map recognition result based on the location information of each name acquired through the name DB search in step S320. That is, the provider 213 may provide map information including a place name recognized by the OCR as a recognition result of the map image. For example, the provider 213 compares the location on the map image with the location on the map image with respect to the name recognized in the map image and the location on the map obtained by searching the name DB, and the center point (latitude / longitude) of the area indicated by the map image. Boundary area can be calculated, and the map image recognition result can be shown by obtaining a scale suitable for the size of the output screen with the calculated center point and the boundary area.

The specific process of recognizing a place name in a map image is as follows.

4 is a flowchart illustrating a process of recognizing a place name in an embodiment of the present invention. In the name recognition process according to an embodiment, each step may be performed by the recognition unit 211 of the map recognition system 200 described with reference to FIGS. 2 and 3.

In operation 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, and first input a character from the input image to recognize a place name. The area can be extracted. Hereinafter, it is assumed that the directions shown in FIG. 5 are input to the input image.

Since there are many corners in the case of letters, if the corners are concentrated in a narrow area, the text area can be extracted on the assumption that the letters are likely to be letters. For example, the recognizer 211 may detect a corner in the input image using a corner detector such as a Harris corner detector. 6 illustrates a result of detecting a corner in an input image using a Harris corner detector. Subsequently, the recognition unit 211 may generate a grid-shaped binary corner grid map and process marking on a cell in which a corner exists in the binary corner grid map. 7 shows the result of marking a grid cell in which a corner exists in a binary corner grid map. Subsequently, the recognizer 211 may perform noise removal and region expansion on the character region marked in the binary corner grid map using a binary image morphology. FIG. 8 illustrates a result of performing noise removal and region expansion on the marking image of FIG. 7. Next, referring to FIG. 9, the recognizer 211 may detect an outline in a binary corner grid map and bundle the detected outline into a rectangular area, wherein a rectangle 901 smaller than the minimum size is junk. (junk) Can be processed. In other words, as shown in FIG. 9, after enclosing the outlines into rectangles, the rectangle 902 satisfying the minimum size may be detected as the effective area, that is, the character area. At this time, the recognition unit 211 expands the rectangle detected as the text area by a predetermined cell (for example, one space) and determines the extended rectangle area 1002 as the final text area as shown in FIG. 10. Can be.

4, in operation S402, the recognition unit 211 may perform OCR on the character region recognized in operation S401 to recognize a character read in the region as a place name. In other words, the recognition unit 211 may obtain a place name by performing OCR on the rectangular area 1002 determined as the final character area of FIG. 10. At this time, in order to increase the OCR accuracy, the post-processing may be performed by correcting the search word to increase the accuracy of the OCR result. FIG. 11 illustrates a result of performing OCR on a character region detected in an input image. Accordingly, the recognizer 211 may acquire names (names, POIs) of major places listed in the input image.

As described above, in the present embodiment, by obtaining a place name for map recognition using OCR technology, all forms of map recognition such as general paper maps and maps, as well as electronic maps, are possible.

Next, a detailed process of obtaining a map area (center point and boundary area) indicated by the input image is as follows.

The provider 213 may calculate a center point and a boundary area of the area indicated by the input image in order to provide a map recognition result. To this end, first, the search unit 212 may obtain a place name on the actual map by searching for a place name recognized as an OCR in a place name DB. 12 illustrates location names on an actual map 1220 obtained through a name database search for a name recognized in an input image. Thus, the provider 213 may perform map image recognition based on the place name acquired through the recognizer 211 and the place name searched through the search unit 212.

FIG. 13 is a flowchart illustrating a process of obtaining a map area indicated by an input image according to an embodiment of the present invention. In the process of acquiring the map area according to an exemplary embodiment, each step may be performed by the providing unit 213 of the map recognition system 200 described with reference to FIGS. 2 and 3.

In operation S1301, the provider 213 may acquire a geographical name straight line for the geographical name recognized in the input image. In this case, as illustrated in FIG. 14, the provider 213 may acquire a 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 of the place name recognized in the input image may be obtained. A straight line 1403 that connects to the first named straight line will be referred to as.

In operation S1302, the provider 213 may obtain an intersection point between the first named straight lines by projecting the first named straight lines on the map area including the named positions searched through the named DB search. In other words, as illustrated in FIG. 15, the provider 213 inclines the slope of the first place name straight line 1503 obtained in step S1301 to each place name acquired through the search of the place name DB in the actual map 1520. After mapping the straight lines with the straight lines, an intersection point between the first named lines 1503 may be obtained.

In operation S1303, the provider 213 may perform density-based clustering on the intersection points obtained in operation S1302 to obtain a set of significant intersection points among intersection points between the first straight lines. . If the place name in the input image and the place name on the actual map coincide, the intersection point between the first place name straight lines will coincide with the center coordinates of the input image. However, an error may appear between a place name (FIG. 12) and a place name recognized in the input image (FIG. 14) acquired through a search of a place name DB due to a missearch or an image distortion. Although the names of the names in the input image and the names of the places on the actual map do not exactly match, if a number of names are identical or similar, as shown in FIG. have. Based on these assumptions, the provider 213 may use 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 an algorithm known to perform clustering in such a manner that low-density areas are regarded as noise and clusters high-density areas based on the density of an object (e.g., density-based spatial clustering). of applications with noise), or OPTICS (Ordering points to identify the clustering structure).

In step S1304, the providing unit 213 calculates an average value of the positions (latitude / longitude) of the intersection points in the set of significant intersection points obtained in step S1303 to determine the center point (latitude / longitude) of the area indicated by the input image. Can be obtained. As shown in FIG. 16, the average value of the intersection points in the area 1608 where the distribution of the intersection points is concentrated may be the center point on the map, which is viewed as a center coordinate corresponding to the center of the input image on the actual map 1620. Can be. For example, the provider 213 calculates the distance between the intersections, and when the distance between the intersections exceeds a certain threshold, considers the noise, calculates an average value of the remaining intersections except noise, and calculates the center coordinates on the map. You can do

The names on the real map acquired through the name DB search for names recognized in the input image may include names that are misrecognized. In the case of a large number of names being misidentified, that is, when there is a lot of noise, map recognition accuracy is inferior. In particular, when map recognition is performed based on the density of recognized names, it is difficult to distinguish misidentified names. Accordingly, the present embodiment proposes a method for distinguishing misidentified names in order to provide more accurate and noise resistant map recognition results.

In operation S1305, the provider 213 may designate a geographical name straight line for the name retrieved from the geographical name DB based on the center point on the actual map acquired in operation S1304, that is, a second geographical name that connects the center point and the geographical location on the actual map. A straight line can be obtained.

In step S1306, the providing unit 213 distinguishes the misidentified names from the recognized names by using the slope difference between the first straight names projected on the real map and the second straight lines acquired on the real map. Can be removed. As shown in FIG. 17, the providing unit 213 compares the slopes of the first place name straight line (the name straight line of the input image) and the second place name straight line (the name straight line on the real map) to allow the difference in the slope. A place name that is out of range can be considered as noise and the place name considered to be noise can be removed. In FIG. 17, when the first place name straight line 1703 and the second place name straight line 1704 are compared, it is understood that the tilt error is very large. Therefore, in the present exemplary embodiment, the accuracy of the map recognition result for the input image may be improved by removing the incorrectly recognized name for the input image.

In operation S1307, the provider 213 may acquire a boundary in which the input image is represented by an actual map by using the distance between the center point of the input image and the place name and the image size of the input image. In detail, as illustrated in FIG. 18, the provider 213 may use the width ImgW and the height ImgH based on the distance ImgD between the center point and the place name of the input image 1810 and the center point of the input image 1810. ) And the distance MapD between the center point of the actual map 1920 and the place name as shown in FIG. 19. 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 between the center point and the place name (MapD) 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 the height MapH of the actual map may be defined by Equation 1 and Equation 2 by proportional expressions.

As shown in FIG. 19, the provider 213 calculates a width MapW and a height MapH on an actual map 1920 that is proportional to the input image 1910, thereby indicating a map area indicated by the input image 1910. The boundary of can be obtained.

Accordingly, the providing unit 213 may provide a map area having a scale that is previously calculated with respect to the size of the output screen with the map center point previously calculated with respect to the input image as an image recognition result. For example, the map region 2020 illustrated in FIG. 20 may be provided as a map image recognition result of the input image of FIG. 5, and the map region 2020 corresponding to the recognition result corresponds to a place name recognized in the input image. POI 2006 may be included. Accordingly, the user terminal providing the input image may receive map information including a place name recognized in the input image from the map recognition system and display the map information as a recognition result of the input image.

Therefore, the map recognition system according to the present invention receives a map image, recognizes a place name from the input map image through OCR technology, and the actual map area (latitude / longitude and boundary area) referred to by the map image based on the recognized place name. I can find you. In particular, the map recognition system according to the present invention can easily and accurately find the area indicated by the input image by applying the nomination straight line concept and can provide a strong recognition result against noise.

21 is a block diagram for explaining an example of an internal configuration of a computer system according to one embodiment of the present invention. Computer system 2100 includes at least one processor 2110, memory 2120, peripheral interface 2130, I / O subsystem 2140. , At least, the power circuit 2150 and the communication circuit 2160. In this case, the computer system 2100 may correspond to a user terminal.

The memory 2120 may include, for example, high-speed random access memory, magnetic disk, SRAM, DRAM, ROM, flash memory, or nonvolatile memory. have. The memory 2120 may include a software module, an instruction set, or other various data necessary for the operation of the computer system 2100. In this case, accessing the memory 2120 from another component such as the processor 2110 or the peripheral interface 2130 may be controlled by the processor 2110.

Peripheral interface 2130 may couple input and / or output peripherals of computer system 2100 to processor 2110 and memory 2120. The processor 2110 may execute a software module or an instruction set stored in the memory 2120 to perform various functions and process data for the computer system 2100.

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

The power circuit 2150 may supply power to all or part of the components of the terminal. For example, power circuit 2150 may be a power management system, one or more power sources such as batteries or alternating current (AC), charging systems, power failure detection circuits, power converters or inverters, power status indicators or power sources. It can include any other components for creation, management, distribution.

The communication circuit 2160 may enable communication with another computer system using at least one external port. Alternatively, as described above, the communication circuit 2160 may include an RF circuit to transmit and receive an RF signal, also known as an electromagnetic signal, to enable communication with another computer system.

21 is merely an example of a computer system 2100, and the computer system 2100 may include some components shown in FIG. 21, or may include additional components not shown in FIG. It may have a configuration or arrangement that combines two or more components. For example, the computer system for a communication terminal in a mobile environment may further include a touch screen or a sensor, in addition to the components shown in FIG. 21, and various communication schemes (WiFi, 3G, LET) in the communication circuit 2160. , Bluetooth, NFC, Zigbee, etc.) may include a circuit for RF communication. Components included in computer system 2100 may be implemented in hardware, software, or a combination of both hardware and software, including integrated circuits specialized for one or more signal processing or applications.

Methods according to an embodiment of the present invention may be implemented in program instruction form that can be executed by various computer systems and recorded in a computer readable medium.

The program according to the present embodiment may 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 in a program form that operates independently, or may be configured in an in-app form of a specific application (for example, a map service program, etc.) to operate on the specific application. It can be implemented to.

In addition, the methods according to the embodiment of the present invention may be performed by the application associated with the map recognition system to control the user terminal. In addition, such an application may be installed in the user terminal through a file provided by the file distribution system. For example, the file distribution system may include a file transmitter (not shown) for transmitting the file at the request of the user terminal.

As described above, according to an embodiment of the present invention, by using the OCR technology, by recognizing a place name in a map image and finding a map area indicated by the map image based on the recognized place name, an accurate electronic map is not affected by the type or form. In addition, all map images such as general paper maps and directions can be recognized. In addition, according to an embodiment of the present invention, by recognizing the map image based on the place name, the map area indicated by the map image is accurately identified by using a database including the place name information without using a database of the topographic information of the map image. You can find it. In addition, according to an exemplary embodiment of the present invention, by distinguishing a misrecognized name and a recognized name among the names recognized in the map image, a recognition technology that is strong against noise may be provided to ensure the accuracy of the map recognition result.

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 devices and components described in the embodiments are, for example, processors, controllers, arithmetic logic units (ALUs), digital signal processors, microcomputers, field programmable gate arrays (FPGAs). Can be implemented using one or more general purpose or special purpose computers, such as 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 the execution of the software. For convenience of explanation, one processing device may be described as being used, but one of ordinary skill in the art will appreciate that the processing device includes a plurality of processing elements and / or a plurality of types of processing elements. It can be seen that it may include. For example, the processing device may include a plurality of processors or one processor and one controller. In addition, other processing configurations are possible, such as parallel processors.

The software may include a computer program, code, instructions, or a combination of one or more of the above, and configure the processing device to operate as desired, or process it independently or collectively. You can command the device. Software and / or data may be any type of machine, component, physical device, virtual equipment, computer storage medium or device in order to be interpreted by or to provide instructions or data to the processing device. Or may be permanently or temporarily embodied in a signal wave to be transmitted. The software may be distributed over networked computer systems so that they may be stored or executed in a distributed manner. Software and data may be stored on one or more computer readable recording media.

The method according to the embodiment may be embodied in the form of program instructions that can be executed by various computer means and recorded in a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the media may be those specially designed and constructed for the purposes of the embodiments, or they may be of the kind well-known and available to those having skill in the computer software arts. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical media such as CD-ROMs, DVDs, and magnetic disks, 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 not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Although the embodiments have been described by the limited embodiments and the drawings as described above, various modifications and variations are possible to those skilled in the art from the above description. For example, the described techniques may be performed in a different order than the described method, and / or components of the described systems, structures, devices, circuits, etc. may be combined or combined in a different form than the described method, or other components. Or even if replaced or substituted by equivalents, an appropriate result can be achieved.

Therefore, other implementations, other embodiments, and equivalents to the claims are within the scope of the claims that follow.

Claims (15)

In the computer-aided map recognition method, Recognizing a character in the input image using a character recognition technique; Searching for a place name on the map corresponding to the text and the location of the place name; And Obtaining a map area matching the input image by 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; Map recognition method comprising a. The method of claim 1, Recognizing the character, Recognizing the character in the input image using an optical character reader (OCR) Map recognition method characterized in that. The method of claim 1, Acquiring the map area, Obtaining a center coordinate on a map that matches a center point of the input image by using an intersection point between the straight lines projected on a location of the place name on a map including the place name; And Obtaining a boundary area matching the size of the input image by using a 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. Map recognition method comprising a. The method of claim 3, Obtaining the center coordinates, Obtaining the intersection point between the straight lines by projecting the straight lines to locations of the top names on the map including the top names; Obtaining a set of significant intersection points through density-based clustering with respect to the obtained intersection points; And Calculating an average value of positions of intersections belonging to the set and recognizing the coordinates as the center coordinates; Map recognition method comprising a. The method of claim 3, Acquiring the boundary area, 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 named distance, which is a distance between the center coordinates and the named location; And Calculating a size of a map area proportional to the size of the input image based on the center coordinates using the text distance and the geographical distance; Map recognition method comprising a. The method of claim 3, Acquiring the map area, Comparing the first straight line with a second straight line connecting the center coordinates and the location of the place name to determine whether the place name is misidentified More, Acquiring the boundary area, As a result of the determination of the misrecognition, regard the misrecognized place name as noise and obtain the boundary area by using the position of the recognized place name Map recognition method characterized in that. The method of claim 6, Determining whether or not the name is misidentified, If the difference between the inclination of the first straight line and the second straight line is within the allowable range, it is determined as a recognized name and if the difference in the inclination between the first and the second straight line is out of the allowable range, it is determined to be a misidentified place name. Map recognition method characterized in that. A recognition unit for recognizing a character in the input image by using a character recognition technology; A search unit for searching for a place name on the map corresponding to the text and the location of the place name; And Providing unit to obtain a map region matching the input image by 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 as a recognition result of the input image Map recognition system comprising a. The method of claim 8, The recognition unit, Recognizing the character in the input image using an optical character reader (OCR) Map recognition system characterized in that. The method of claim 8, The providing unit, Obtaining a center coordinate on a map that matches a center point of the input image by using an intersection point between the straight lines projected on the location of the place name on the map including the place name, Acquiring a boundary area matching the size of the input image by using a 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; Map recognition system characterized in that. The method of claim 10, The providing unit, Projecting the straight line to a location of the place name on a map including the place name to obtain an intersection point between the straight lines, Obtaining a set of significant intersection points through density-based clustering with respect to the obtained intersection points, Calculating the average value of the position of the intersection belonging to the set and recognizing it as the center coordinate Map recognition system characterized in that. The method of claim 10, The providing unit, The size of the input image is calculated 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, Calculate a place name distance that is a distance between the center coordinates and the location of the place name, Calculating a size of a map area proportional to the size of the input image based on the center coordinates using the text distance and the geographical distance; Map recognition system characterized in that. The method of claim 10, The providing unit, After comparing the second straight line connecting the center coordinates and the location of the place name and the first straight line to determine whether the place name is misunderstood, Acquiring the boundary area by using a recognized location of a place name according to a result of the determination of the misrecognition; Map recognition system characterized in that. The method of claim 13, The providing unit, If the difference between the inclination of the first straight line and the second straight line is within the allowable range, it is determined as a recognized name and if the difference in the inclination between the first and the second straight line is out of the allowable range, it is determined to be a misidentified place name. Map recognition system characterized in that. A computer readable medium containing instructions for controlling a computer system to provide a map recognition function, the computer readable medium comprising: The command is Recognizing a character in the input image using a character recognition technique; Searching for a place name on the map corresponding to the text and the location of the place name; And Obtaining a map area matching the input image by 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; And control the computer system by a method comprising: a computer readable storage medium.

Images