Drawing recognition method and drawing recognition device

Abstract

A drawing recognition method and device are provided that can accurately extract symbols and annotations from a drawing and associate the two to digitize them. [Solution] A drawing recognition method for extracting symbols and annotations contained in a drawing file, which includes a drawing file formation process for forming a drawing file S2 for symbol extraction from an original drawing file S1, a symbol extraction process for extracting symbols from the drawing file S2 for symbol extraction, a annotation search area setting process for setting annotation search areas SA centered on each of the multiple symbols extracted in the symbol extraction process, and a annotation extraction process for extracting annotations corresponding to each symbol from figures detected in the annotation search area SA centered on each symbol extracted in the annotation search area setting process.

Description

[Technical field]

[0001] The present invention relates to a drawing recognition method and a drawing recognition device, and more particularly to a drawing recognition method and a drawing recognition device for extracting, from various drawings, various symbols and characters or the like that are written in the vicinity of the symbols and that supplement the specifications of facilities, equipment, or the like represented by the symbols, in association with each other. [Background technology]

[0002] Currently, it is common to create various drawings using CAD software. When drawings created using CAD software are provided, they may be provided not as CAD data but as data converted into PDF format or as paper-based drawings (hereinafter simply referred to as paper-based drawings, etc.), and it may be necessary to obtain various information described in these drawings. For example, architectural design drawings contain a large amount of information such as equipment symbols (hereinafter simply referred to as symbols), characters and figures related to the symbols (hereinafter simply referred to as side notes), wiring, etc., and it may be necessary to extract symbols and side notes. However, architectural design drawings are written in a state where symbols, side notes, and wiring are overlapped or very close to each other, so it is difficult to extract symbols and side notes with high accuracy, and techniques have been developed for extracting symbols and side notes with high accuracy from paper-based drawings, etc. (see Patent Documents 1 to 5). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2004-259076 A [Patent Document 2] JP 2006-227824 A [Patent Document 3] Patent No. 7234719 [Patent Document 4] JP 2001-92967 A [Patent Document 5] Japanese Patent Application Publication No. 11-126216 Summary of the Invention [Problem to be solved by the invention]

[0004] The techniques of Patent Documents 1 to 5 extract figures and characters in a drawing by template matching, but in a drawing that contains a mixture of wiring, symbols, etc., it is difficult to perform appropriate template matching, and it is difficult to accurately extract symbols, etc. In particular, when a symbol and a side note are described in association with each other, it is difficult to accurately extract the symbol or side note in the associated state.

[0005] In view of the above circumstances, an object of the present invention is to provide a drawing recognition method and a drawing recognition device that can accurately extract symbols and annotations from a drawing and associate the two with each other to convert them into data. [Means for solving the problem]

[0006] <How to recognize drawings> The drawing recognition method of the first invention is as follows: The drawing recognition device A drawing recognition method for extracting symbols and annotations contained in a drawing file, comprising the steps of: The drawing recognition device A drawing file forming step of forming a drawing file for symbol extraction to be used for symbol extraction from the drawing file, a symbol extraction step of extracting symbols from the drawing file for symbol extraction formed in the drawing file forming step, a side note search area setting step of setting side note search areas centered on each of the multiple symbols extracted in the symbol extraction step in the drawing file for symbol extraction, and a side note extraction step of extracting side notes corresponding to each symbol from figures detected in the side note search areas set in the side note search area setting step, In the sidenote search area setting step and / or the sidenote extraction step, a sidenote template size is determined, which is the size of the sidenote template that maximizes the similarity by performing a matching process between the sidenote template and a figure detected in the sidenote search area set for the representative symbols extracted in the symbol extraction step while changing the size of the sidenote template registered in the sidenote template list in the sidenote search area set for the representative symbols, and in the sidenote extraction step, a sidenote included in the sidenote search area is extracted using the sidenote template of the determined extraction template size. It is characterized by: Second InventionIn the drawing recognition method of the first invention, the side note extraction step extracts a plurality of figures included in the side note search area as side note candidates, and among the plurality of side note candidates, the side note candidate that is closest to the symbol is linked to the symbol. Third Invention In the drawing recognition method of the first invention, the side note extraction step extracts a plurality of figures included in the side note search area as side note candidates, and for the extracted plurality of side note candidates, a side note candidate to be linked to the symbol that sets the side note search area is determined based on a management list in which the association between symbols and side notes is stored. <Drawing recognition device> Fourth Invention The drawing recognition device is a drawing recognition device that extracts symbols and annotations included in a drawing file, and the drawing recognition device includes: a drawing file forming unit that forms a drawing file for symbol extraction used for symbol extraction from the drawing file; a symbol extraction unit that extracts symbols from the drawing file for symbol extraction formed by the drawing file forming unit; an annotation search area setting unit that sets an annotation search area centered on each of the multiple symbols extracted by the symbol extraction unit in the drawing file for symbol extraction; and an annotation extraction unit that extracts annotations corresponding to each symbol from a figure detected in the annotation search area set by the annotation search area setting unit. The annotative extraction unit and / or the annotative search area setting unit has a function of performing a matching process between an annotative template registered in a annotative template list and a figure detected in the annotative search area set for the representative symbols extracted by the symbol extraction unit while changing the size of the annotative template and the figure detected in the annotative search area set for the representative symbols, and determining an extraction template size that is the size of the annotative template that maximizes the similarity, and the annotative extraction unit has a function of extracting an annotative template included in the annotative search area by using the annotative template of the determined extraction template size. It is characterized by: Fifth invention The drawing recognition device is Fourth Invention In the above-mentioned embodiment, the annotative extraction unit has a function of extracting a plurality of figures included in the annotative search area as annotative candidates, and a function of linking the annotative candidate among the plurality of annotative candidates that is closest to the symbol to the symbol. Sixth Invention The drawing recognition device is Fourth InventionIn the present invention, the side note extraction unit has a function of extracting multiple figures included in the side note search area as side note candidates, and has a function of determining a side note candidate to be linked to the symbol that set the side note search area from which the side note candidate was extracted, based on a management list in which the association between symbols and side notes is stored. Effect of the Invention

[0007] <How to recognize drawings> First Invention According to this, it is possible to increase the accuracy of extracting side notes, and to appropriately link related symbols and side notes and store them. Second Invention According to this, a symbol can be easily linked to a side note that is highly related to this symbol. Third Invention According to this, it is possible to increase the accuracy of linking a symbol with a side note that is highly related to this symbol. <Drawing recognition device> Fourth Invention According to this, it is possible to increase the accuracy of extracting side notes, and to appropriately link related symbols and side notes and store them. Fifth invention According to this, a symbol can be easily linked to a side note that is highly related to this symbol. Sixth Invention According to this, it is possible to increase the accuracy of linking a symbol with a side note that is highly related to this symbol. [Brief description of the drawings]

[0008] [Figure 1] FIG. 2 is a flow diagram of a drawing recognition method according to the present embodiment. [Diagram 2] 1 is a schematic block diagram of a drawing recognition device 1 of the present embodiment. [Diagram 3] 13A is a diagram showing an example of an original drawing file S1, and FIG. 13B is a diagram showing an example of a symbol extraction drawing file S2. [Figure 4](A) is a diagram showing an example of a state in which an annotated search area SA is set for each symbol included in the drawing file S2 for symbol extraction, and (B) is a diagram showing an example of a state in which an annotated search area SA is set for a selected symbol included in the drawing file S2 for symbol extraction. [Diagram 5] 13A is a diagram showing an example of an extracted symbol file S4, FIG. 13B is a diagram showing an example of a side note template list TP, and FIG. 13C is a diagram showing an example of a management list CR. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] The drawing recognition method of this embodiment is a method for extracting symbols and annotations from drawing files such as construction drawings, and is characterized by its ability to extract annotations with high accuracy while maintaining the association between symbols and annotations.

[0010] The drawing file from which symbols and the like are extracted by the drawing recognition method of this embodiment is not particularly limited. Examples of drawing files include drawing files (drawing files in which images are composed of pixel data) in which drawings printed on paper are digitized by scanning, and drawing files (drawing files in which symbols and the like in the data each have information) created by converting drawings drawn by CAD. For example, the former file includes raster format drawing files such as raster PDF files and PNG files, and the latter file includes vector format drawing files such as vector PDF files and SVG files. The drawing file from which symbols and the like are extracted by the drawing recognition method of this embodiment may be either the raster format drawing file or the vector format drawing file described above. In the following, the drawing file from which symbols and the like are extracted is simply called the original drawing file.

[0011] In the following description, a case where the drawing from which the symbols are extracted is a construction drawing will be described as a representative example, but the drawing from which the symbols are extracted by the drawing recognition method of this embodiment is not particularly limited. In the following description, since the drawing from which the symbols are extracted is a construction drawing, the term "symbol" refers to a symbol that diagrammatically represents an electrical / mechanical component used in the facilities of a building. In addition, the term "side note" refers to a character or symbol that supplements the specifications of the electrical / mechanical component represented by the symbol described above and is written adjacent to the symbol.

[0012] <Drawing recognition device 1 of this embodiment> First, a drawing recognition device 1 for implementing the drawing recognition method of this embodiment will be described. As shown in FIG. 2, the drawing recognition device 1 may have a display function for displaying drawing files formed by each unit described later on a display DS, and an input function for inputting necessary information and instructing necessary operations using an input device IS such as a keyboard or a mouse.

[0013] <Data Entry Section 2> As shown in FIG. 2, the device 1 for implementing the drawing recognition method of this embodiment (hereinafter simply referred to as drawing recognition device 1) has a data input unit 2 for creating an original drawing file S1 (see FIG. 3(A)). This data input unit 2 has a function of inputting a drawing file from which the original drawing file S1 is created. For example, if the original drawing file is a vector format drawing file such as a vector PDF file or a raster format drawing file such as a raster PDF file, the data input unit 2 has a function (data receiving function) of receiving drawing data from a storage medium such as a USB or receiving it via a line such as the Internet. Note that if the original drawing file S1 is a drawing file, the drawing file received by the data input unit 2 can be used as the original drawing file S1 as is. In addition, if the drawing from which the original drawing file S1 is to be created is a drawing printed on paper, etc., the data input unit 2 has a function of converting the drawing into data by scanning or the like, and creating the original drawing file S1 saved as a raster format drawing file such as a raster PDF file. The original drawing file S1 received or created by the data input unit 2 is transmitted to the storage unit 10 and stored therein.

[0014] <Drawing file creation section 3> 2, the drawing recognition device 1 has a drawing file forming unit 3. The drawing file forming unit 3 has a function of forming a symbol extraction drawing file S2 from an original drawing file S1 received or created by the data input unit 2. The drawing file forming unit 3 has a function of transmitting the created symbol extraction drawing file S2 to a storage unit 10, and the symbol extraction drawing file S2 transmitted to the storage unit 10 is stored in the storage unit 10.

[0015] There is no particular limitation on the method by which the drawing file forming unit 3 forms the symbol extraction drawing file S2 from the original drawing file S1. For example, the drawing file forming unit 3 can form the symbol extraction drawing file S2, which is a PNG file, by performing background deletion processing (erasing thin lines exceeding a threshold value by image processing, erasing filled-in areas, or background processing by manually specifying characteristic areas) from the original drawing file S1.

[0016] <Symbol Extraction Part 4> As shown in FIG. 2, the drawing recognition device 1 has a symbol extraction unit 4. The symbol extraction unit 4 has a function of extracting a symbol from the drawing file S2 for symbol extraction created by the drawing file creation unit 3. The method by which the symbol extraction unit 4 extracts a symbol is not particularly limited, but the symbol can be extracted by a known method such as pattern matching based on the extracted symbol file S4 (see FIG. 5(A)) stored in the storage unit 10. The pattern matching can be performed using pattern matching using AI (artificial intelligence), but the means for performing the pattern matching is not particularly limited. The symbol extraction unit 4 also has a function of forming an extracted symbol file S4 for each extracted symbol, in which symbol data obtained by cutting out an image of an area including the extracted symbol is associated with location information of the area (i.e., information on the coordinates of the area on the drawing file S2 for symbol extraction). Each of the formed extracted symbol files S4 is transmitted to the storage unit 10 and stored therein.

[0017] In addition, when symbol extraction is performed by pattern matching using AI (artificial intelligence), information on the confidence level of the symbol extraction (expressed as a number: the closer to 1, the higher the confidence level) is also included in the extracted symbol file S4. In addition, the extracted symbol file S4 may be an image of an area including an extracted symbol, and the file name of the extracted symbol file S4 may include the position information and the confidence level, and the image of the area may be associated with the position information and the confidence level. If this method is adopted, it becomes possible to sort the extracted symbol files S4 in descending (or descending) order of confidence level on the display DS, which is desirable in that extracted symbol files S4 that have been erroneously detected can be efficiently deleted. For example, in the case of an image of a rectangular area, the file name of the extracted symbol file S4 may be set as 0.9224@17560×4782_17634×4854_0.png. In the file name mentioned above, "0.9224" is the confidence level, and "17560x4782_17634x4854" is the X-axis and Y-axis coordinates (position information) of the diagonal corners of the rectangular area image.

[0018] <Search area setting section 5> As shown in FIG. 2, the drawing recognition device 1 has a side note search area setting unit 5. The side note search area setting unit 5 has a function of setting an area (side note search area SA) for searching side notes associated with a symbol in the symbol extraction drawing file S2. Specifically, the side note search area setting unit 5 has a function of setting a certain area centered on each symbol as a side note search area SA in the symbol extraction drawing file S2 for all symbols extracted in the symbol extraction unit 4. Specifically, based on information included in each extracted symbol file S4, the side note search area setting unit 5 has a function of setting a certain area centered on each symbol as a side note search area SA of each symbol in the symbol extraction drawing file S2 (see FIG. 4). When setting the side note search area SA of each symbol, the side note search area setting unit 5 sets a range that is assumed to include both each symbol and side notes related to that symbol as a side note search area SA in the symbol extraction drawing file S2. For example, the side search area SA may be a range calculated based on the size of each extracted symbol with a constant magnification factor in the vertical and horizontal directions with the center of each symbol as a reference position. In addition, when a management list CR (see FIG. 5(C)) in which side notes corresponding to each symbol (i.e., used for each symbol) are registered in advance is stored in the storage unit 10 (may be stored in the side search area setting unit 5), a certain range calculated based on the number of characters (number of characters of side note character strings) registered in the management list CR may be set as the side search area SA. The information on the side search area SA includes the coordinates of the side search area SA (for example, when a rectangular area is set as the side search area SA, the coordinate information of the corners, etc.). When the information on the side search area SA is calculated, the information on the side search area SA is transmitted from the side search area setting unit 5 to the storage unit 10 and stored in the storage unit 10 in association with the extracted symbol information of each symbol for which the side search area SA is set. The information on the side search area SA may include information on the corresponding extracted symbol.

[0019] FIG. 5C shows a list of a plurality of annotations corresponding to one symbol, and the management list CR stores such an annotation list in association with each symbol.

[0020] <sidenote extraction part 7> As shown in FIG. 2, the drawing recognition device 1 has a side note extraction unit 7. The side note extraction unit 7 has a function of extracting side notes from the side note search area SA formed by the side note search area setting unit 5, and a linking function of linking the extracted side note with a symbol. Specifically, the side note extraction unit 7 performs pattern matching using the side note template list TP for figures included in the side note search area SA set by the side note search area setting unit 5 for all symbol files S4, and extracts figures that are highly similar to the side note template as side note candidates. Then, when there is only one side note candidate extracted, the side note candidate is linked to the symbol as a side note related to the symbol for which the side note search area SA is set, and the side note candidate and the symbol are transmitted to the storage unit 10 as symbol data and stored therein.

[0021] In addition, when there are multiple side note candidates in the side note search area SA, the side note extraction unit 7 has a function of linking the side note candidate that is considered to be most related to the symbol from the multiple side note candidates to the symbol to create symbol data. The method by which the side note extraction unit 7 selects the side note candidate that is considered to be highly related is not particularly limited, but for example, the side note candidate that is closest in distance between the symbol and the side note candidate (for example, the distance from the center of the symbol to the center of the side note candidate) may be linked to the symbol.

[0022] <Extraction and linking of symbols and annotations> The operation of extracting symbols and annotations by the above-mentioned drawing recognition device 1 (that is, the drawing recognition method of this embodiment) will be described (see FIGS. 1 and 2).

[0023] <Drawing file creation process> 1 and 2, the drawing file forming unit 3 receives an original drawing file S1 that is formed or received by the data input unit 2 and stored in the memory unit 10. The drawing file forming unit 3 forms a symbol extraction drawing file S2 from the original drawing file S1 (see FIG. 3(B)). The formed symbol extraction drawing file S2 is transmitted to and stored in the memory unit 10, but the symbol extraction drawing file S2 may also be directly transmitted from the drawing file forming unit 3 to the symbol extraction unit 4 or the side note extraction unit 7.

[0024] <Symbol extraction process> 1 and 2, when the symbol extraction unit 4 receives the symbol extraction drawing file S2 from the storage unit 10 (or when the symbol extraction drawing file S2 is transmitted from the drawing file formation unit 3 to the symbol extraction unit 4), the symbol extraction unit 4 extracts symbols from the symbol extraction drawing file S2 by pattern matching using AI or a known pattern matching method based on the symbol extraction drawing file S2, and forms a symbol file S4. Specifically, when a symbol is extracted from the symbol extraction drawing file S2, an extracted symbol file S4 is formed, which includes symbol data cut out from an image of an area including the extracted symbol, location information of the area, a confidence level, and the like. This extracted symbol file S4 is transmitted to the storage unit 10 and stored therein.

[0025] The extracted symbol file S4 may be sent directly to the side search area setting unit 5. Furthermore, all extracted symbol files S4 may be transmitted to storage unit 10 or ancillary search area setting unit 5 once extraction of all symbols has been completed, or each time a symbol is extracted and an extracted symbol file S4 is formed, extracted symbol file S4 may be transmitted to storage unit 10 or ancillary search area setting unit 5. Furthermore, when a certain number of extracted symbol files S4 are formed, the certain number of extracted symbol files S4 may be transmitted collectively to storage unit 10 or ancillary search area setting unit 5.

[0026] <Search area setting process> As shown in Figures 1 and 2, when the sidenote search area setting unit 5 receives the extracted symbol file S4 from the memory unit 10 (or when the extracted symbol file S4 is transmitted from the symbol extraction unit 4 to the sidenote search area setting unit 5), the sidenote search area setting unit 5 sets a sidenote search area SA in the extracted symbol file S4 for each symbol. That is, the sidenote search area setting unit 5 sets a certain area centered on the symbol as the sidenote search area SA in the extracted symbol file S4 based on the information contained in the extracted symbol file S4 (see Figure 4). Then, information on the set sidenote search area SA is transmitted from the sidenote search area setting unit 5 to the memory unit 10 and stored therein.

[0027] The information on the side note search area SA may be directly transmitted from the side note search area setting unit 5 to the side note extraction unit 7 . Furthermore, the information on the annotated search area SA may be transmitted to the memory unit 10 or the annotated extraction unit 7 when the formation of the information on the annotated search area SA for all symbols is completed, or the information on the annotated search area SA may be transmitted to the memory unit 10 or the annotated extraction unit 7 each time the information on the annotated search area SA for each symbol is formed. Moreover, when the information on the annotated search area SA for a certain number of symbols is formed, the information on a certain number of the annotated search areas SA may be transmitted collectively to the memory unit 10 or the annotated extraction unit 7.

[0028] <sidenote extraction process> 1 and 2, when the information of the sidenote search area SA is acquired from the storage unit 10 (or when the information of the sidenote search area SA is transmitted from the sidenote search area setting unit 5), the sidenote extraction unit 7 acquires the sidenote template list TP stored in the storage unit 10. Note that the sidenote extraction unit 7 may acquire the sidenote template list TP stored in the storage unit 10 in advance.

[0029] When the sidenote template list TP is acquired, the sidenote extraction unit 7 matches the figures included in the sidenote search area SA with the sidenote template list TP for all symbols to extract sidenote candidates. If there is one sidenote candidate and the similarity (confidence in AI matching) is a certain level or higher, or if multiple sidenote candidates are extracted but only one has a certain level or higher similarity, the sidenote candidate is determined to be a sidenote of the symbol for which the sidenote search area SA is set. The sidenote candidate determined to be a sidenote of the symbol is linked to the symbol for which the sidenote search area SA is set, and is transmitted to and stored in the storage unit 10 as symbol data.

[0030] Furthermore, when multiple side note candidates with a certain degree of similarity or higher are extracted, the side note extraction unit 7 determines that the side note candidate that is considered to be most related to the symbol is the side note of the symbol, links this side note candidate to the symbol with the side note search area SA set, and transmits and stores it as symbol data in the storage unit 10. For example, it determines that the side note candidate that is closest (shortest) to the symbol is the side note that is considered to be highly related to the symbol, links this side note candidate to the symbol with the side note search area SA set, and transmits and stores it as symbol data in the storage unit 10.

[0031] Since symbols and annotations are extracted in the above-described manner, the precision of extraction of symbols and annotations can be increased, and related symbols and annotations can be appropriately linked and stored.

[0032] <About the Sidenote Template List TP> The font, color, size, etc. of the annotative notes stored in the annotative note template list TP (see FIG. 5(B)) used for matching the annotative notes is not particularly limited. The characters constituting the annotative notes may be registered as a whole, or each character constituting the annotative note (for example, one alphanumeric character) may be registered. A plurality of annotative notes having the same constituent characters or numbers expressed in a plurality of fonts may be included in the annotative note template list TP.

[0033] Furthermore, a management list CR that stores the number of characters of the side note used in the symbol and the like may be provided separately from the side note template list TP (see Fig. 2 and Fig. 5(C)), and this management list CR may be stored in the storage unit 10. The side note extraction unit 7 may be provided with a function (verification function) that uses the management list CR to determine whether the side note selected by matching is appropriate. By providing such a management list CR and verification function, it is possible to prevent the side note extraction unit 7 from selecting figures that are not suitable for a symbol as side note.

[0034] For example, when multiple symbols are written adjacent to each other, the sidenotes of the adjacent symbols (hereinafter referred to as false sidenotes) may be included in the sidenote search area SA. In this case, depending on the state in which the sidenotes are written in the drawing, the false sidenotes may have a higher matching reliability than sidenotes that are actually related to the symbols, or the distance between the false sidenotes and the symbols may be closer than the distance between the actual sidenotes and the symbols. In particular, when only one alphanumeric character is used as the sidenote template, such a situation is likely to occur. Therefore, if a sidenote is selected by matching the figure included in the sidenote search area SA with the sidenote template, and then a verification function is used to verify whether the sidenote is suitable for the symbol, the sidenote extraction unit 7 can prevent the selection of a sidenote that is not suitable for the symbol.

[0035] <About the side note extraction unit 7> The annotative extraction unit 7 may have a function of changing the size of the annotative template when matching the figure included in the annotative search area SA with the annotative template list TP. If the annotative extraction unit 7 has such a function, even if the size of the figure and the annotative template list TP are different, the annotative can be appropriately extracted. In other words, even if the scale of the drawing that is the source of the original drawing file S1 is different from the scale of the stored annotative template list TP, the matching accuracy between the figure and the annotative template list TP can be improved, and the annotative can be appropriately extracted.

[0036] <When using the extraction template size> When the annotative extraction unit 7 has a function of matching the figures included in the annotative search area SA with the annotative template list TP while changing the size of the annotative template, the matching may be performed while changing the size of the annotative template for all figures included in the annotative search area SA, or the matching may be performed using the extraction template size. That is, the annotative search area setting unit 5 may be provided with a function of determining the extraction template size (that is, the annotative search area setting step may be provided with a step of determining the extraction template size), and the annotative extraction unit 7 may perform matching using the extraction template size set by the annotative search area setting unit 5. As shown in FIG. 4(A), the annotative search area setting unit 5 sets the annotative search area SA for all symbols, and then selects a plurality of representative symbols from the symbols extracted by the symbol extraction unit 4. Then, as shown in FIG. 4(B), the extraction template size is determined using the figures detected in the annotative search area SA (annotative search area SA(1), annotative search area SA(2)) of the selected symbol. Then, when the extraction template size determined from the annotative search area setting unit 5 is transmitted to the annotative extraction unit 7 (or the extraction template size is temporarily stored in the storage unit 10 and the extraction template size is transmitted from the storage unit 10 to the annotative extraction unit 7), the annotative extraction unit 7 performs pattern matching between the figures included in the annotative search area SA and the annotative template for all the annotative search areas SA using the annotative template adjusted to the determined extraction template size. This allows annotative to be appropriately extracted from figures present in the annotative search area SA, and makes it easier to prevent figures other than annotative from being erroneously extracted as annotative. As a method for determining the extraction template size, for example, when matching is performed while changing the size of the figure detected in the annotative search area SA set by the annotative search area setting unit 5 with the annotative template for a plurality of representative symbols, the size of the annotative template that has the highest similarity can be set as the extraction template size.

[0037] The function of setting the extraction template size may be provided in the annotative extraction unit 7, not in the annotative search area setting unit 5. That is, a step of determining the extraction template size may be provided in the annotative extraction step. In this case, the annotative extraction unit 7 selects a plurality of representative symbols from the symbols extracted by the symbol extraction unit 4. Then, the annotative extraction unit 7 determines the extraction template size for the selected symbols by using figures detected in the annotative search area SA set by the annotative search area setting unit 5.

[0038] In addition, the method of selecting the representative symbol to be used when determining the size of the extraction template is not particularly limited. For example, the annotated search area setting unit 5 or the annotated extraction unit 7 may automatically select the symbol by a method such as selecting symbols in descending order of confidence when the symbol is extracted by the symbol extraction unit 4. In addition, the worker may check the image of the extracted symbol (i.e., the image included in the extracted symbol file S4 or the image in the extraction drawing file S2) and the confidence level, and select the representative symbol. [Industrial Applicability]

[0039] The drawing recognition method of the present invention is suitable as a method for extracting symbols and characters from drawings containing a large number of symbols, characters, and lines, such as construction drawings. [Explanation of symbols]

[0040] 1 Drawing recognition device 2 Data Entry Section 3. Drawing File Creation Department 4 Symbol Extraction 5. Side note search area setting section 7 Paragraph extraction part 10 Storage section S1 Original drawing file S2 Drawing file for symbol extraction S4 Extracted Symbol File SA Sidenote Search Area TP Sidenote Template List CR Management List

Claims

1. A drawing recognition method in which a drawing recognition device extracts symbols and annotations contained in a drawing file, comprising: The drawing recognition device a drawing file forming step of forming a drawing file for symbol extraction used for symbol extraction from the drawing file; a symbol extraction step of extracting a symbol from the symbol extraction drawing file formed in the drawing file formation step; a side search area setting step of setting a side search area having each of the plurality of symbols extracted in the symbol extraction step as a center in the symbol extraction drawing file; a side note extraction step of extracting side notes corresponding to each symbol from the figure detected in the side note search area set in the side note search area setting step; In the side note search area setting step and / or the side note extraction step, In the sidenote search area set for the representative symbols extracted in the symbol extraction step, a matching process is performed between the sidenote template registered in the sidenote template list and a figure detected in the sidenote search area set for the representative symbols while changing the size of the sidenote template, and a template size for extraction is determined, which is the size of the sidenote template that maximizes the similarity; In the side note extraction step, A side note included in the side note search area is extracted using a side note template of the determined extraction template size. A drawing recognition method comprising:

2. In the side note extraction step, Extracting a plurality of figures included in the side note search area as side note candidates; Among the plurality of side note candidates, the side note candidate having the shortest distance from the symbol is associated with the symbol.

2. The drawing recognition method according to claim 1.

3. In the side note extraction step, Extracting a plurality of figures included in the side note search area as side note candidates; For the extracted plurality of side note candidates, a side note candidate to be linked to the symbol that sets the side note search area from which the side note candidate is extracted is determined based on a management list in which the association between the symbol and the side note is stored.

2. The drawing recognition method according to claim 1.

4. A drawing recognition device for extracting symbols and annotations included in a drawing file, comprising: The drawing recognition device includes: a drawing file forming unit for forming a symbol extraction drawing file used for symbol extraction from the drawing file; a symbol extraction unit that extracts a symbol from the symbol extraction drawing file formed by the drawing file formation unit; an ancillary search area setting unit for setting an ancillary search area having a center on each of the plurality of symbols extracted by the symbol extraction unit in the symbol extraction drawing file; a side note extraction unit that extracts side notes corresponding to each symbol from a figure detected in the side note search area set by the side note search area setting unit, The side note extraction unit and / or the side note search area setting unit, The function includes a function of performing a matching process between the sidenote template registered in the sidenote template list and a figure detected in the sidenote search area set for the representative symbols extracted by the symbol extraction unit while changing the size of the sidenote template and the sidenote template registered in the sidenote template list, and determining an extraction template size that is the size of the sidenote template that maximizes the similarity; The side note extraction unit is The side note search area includes a side note search area that includes a side note template having a size determined by the side note search area. A drawing recognition device characterized by the above.

5. The side note extraction unit is A function of extracting a plurality of figures included in the side note search area as side note candidates; and a function of linking, among the plurality of side note candidates, a side note candidate that is closest to the symbol with the symbol.

5. The drawing recognition device according to claim 4.

6. The side note extraction unit is A function of extracting a plurality of figures included in the side note search area as side note candidates, The function of determining, for the extracted plurality of side note candidates, a side note candidate to be linked to the symbol that sets the side note search area from which the side note candidate is extracted, based on a management list in which the association between the symbol and the side note is stored.

5. The drawing recognition device according to claim 4.

Images