JPH09128425A - Method and device for recognizing construction drawing - Google Patents

Abstract

PROBLEM TO BE SOLVED: To accurately and automatically recognize outline, skeleton, and especially wall which are important information in order to know the room arrangement from a handwritten construction drawing. SOLUTION: The outline of a part consisting of the black or white dots of image picture data obtained by reading the picture of the handwritten construction drawing is extended to measure the number of horizontal and that of vertical black or white dots to prepare horizontal and vertical dot numbers measuring and arranging data. Further, based on the prepared both-direction dot numbers measuring and arranging data, the outline and the skeleton of the construction drawing are recognized. In addition, the limiting of the recognizing object area so as to be subdivided based on the recognized outline and skeleton to prepare the black or white dot numbers measuring and arranging data again, and the recognition of the outline and the skeleton for each of the limited ranges, are repeated until an outline or skeleton is no longer newly recognized.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a construction drawing recognizing method and a recognizing apparatus therefor, which are widely used in the construction industry such as building and equipment industries.

[0002]

2. Description of the Related Art In recent years, using CAD systems, etc., construction drawings including houses, buildings, etc., construction drawings including water pipes, gas pipes, piping drawings for power / communication cables, etc. can be easily created, and the data thereof can be obtained. It has been practiced to memorize and store the information when design changes, extension and remodeling are performed. However, the data of the construction drawings are not compatible with each other due to the created system, and cannot be used due to the passage of time or the change of the contractor. In addition, when an extension or renovation of a house is performed, it is often the case that there are only old construction drawings drawn on paper, and it is necessary to redraw the entire floor plan including the portions that do not change the floor plans and the like.

Therefore, it has been attempted to read a construction drawing drawn on paper and recognize and store it as data that can be processed by a computer, but there is no special method or device for that purpose, and the construction drawing is scanned by an image scanner. Then, the image data is read into a personal computer or the like, and line segment recognition or pattern recognition is performed using a general figure recognition function. Alternatively, the graphic recognition function can be upgraded by using a high-performance graphic editor to assist, and even if the automatic recognition function is somewhat imperfect, basic vector diagrams such as straight lines and arcs can be converted by raster-to-vector conversion, for example. Some of them can be automatically recognized.

[0004]

However, such a conventional drawing recognition apparatus requires a high degree of operation knowledge and is limited in usage to those who are familiar with a personal computer or the like and specialized operators. It was never easy to use for the industry people who frequently use it.

Although a basic diagram such as a straight line or an arc can be automatically recognized, a graphic symbol (for example, a wall or a pillar) peculiar to a construction drawing, which is a combination of the basic diagrams, is individually recognized. I couldn't do that. Therefore, when the recognized drawing is corrected, it must be performed for each line segment, which requires much labor.

Further, the construction drawings of houses and buildings used in the construction industry have a single thickness even if each line segment on the drawing appears to the human eye as a continuous line of the same size. The trajectory is fluctuating as well. In addition, even if it should be a continuous line, it may be broken in some places. These imperfections occur not only at the time of drawing, but also due to aging of paper, errors in reading, and the like. Therefore, for example, if the limit of the thickness that can be recognized as a line segment is too small, it is recognized that the line segment is broken even with a slight blur.
Also, thick line segments may be recognized as rectangles.

[0007] This is of course not only the quality of the original drawing, but also many drawings with low contrast (the boundary between black and white is not clear) like a so-called blueprint using photosensitive paper.
Furthermore, since the fine points characteristic of the blue printing appear on the surface, it is difficult to perform highly accurate automatic recognition with a conventional drawing recognition device, and the correction requires a lot of trouble, so that it is hardly practical. Was.

By the way, in a construction drawing (architectural drawing) of a house, a partition wall plays a central role in the drawing, and by recognizing which part in the drawing is the wall, the floor plan of the construction drawing can be roughly estimated. I can understand. Therefore, recognizing the position and length of the wall in the drawing is the most important matter in recognizing the construction drawing.

[0009] Furthermore, most construction drawings are floor plans separated by horizontal and vertical walls. When this construction drawing is expressed by hand, one wall or partition is often described by a line close to one horizontal or vertical line. Therefore, when recognizing a handwritten construction drawing, whether or not the horizontal line and the vertical line can be reliably recognized is an important key.

However, the conventional straight line recognition has the following problems. (1) In the contour tracking method, if there are many scratches or irregularities, it is recognized as a broken straight line, or it is recognized as a straight line divided into two or three lines, and cannot be recognized accurately. (2) In the projected feature extraction method obtained from the frequency distribution of black dots, when a straight line in the horizontal and vertical directions is found when the line is thin, if the line is slightly inclined, the feature cannot be extracted. I could not recognize it.

The present invention has been made in view of the above points, and encodes image image data obtained by reading a construction drawing drawn on paper with a straight line that is broken or slightly inclined by handwriting, or its run length. An object of the present invention is to enable automatic and accurate recognition of contours and skeletons, especially walls, which is important information for knowing the floor plan of the construction drawing, from the encoded image data.

[0012]

In order to achieve the above object, the present invention provides the following construction drawing recognition method and construction drawing recognition apparatus. A construction drawing recognition method according to the present invention extends a contour of a portion consisting of black or white dots of image image data obtained by reading an image of a construction drawing, and extends the contour in the horizontal and vertical directions of black or white in the image image data. The number of white dots is measured to create dot number measurement array data in the horizontal and vertical directions, and the outline and skeleton of the construction drawing are recognized based on the created dot number measurement array data in both directions.

Further, after recognizing the outline and skeleton of the construction drawing based on the horizontal and vertical direction dot number measurement array data created as described above, the range and the range limited based on the recognized outline and skeleton are recognized. The number of black or white dots in the horizontal and vertical directions of the image image data is measured, and the dot number measurement array data in the horizontal and vertical directions are created again. Based on the created dot number measurement array data in both directions, the above limitation is applied. The recognition of the outline and the skeleton of the construction drawing within each range may be repeated until the new outline or the skeleton cannot be recognized.

Further, the construction drawing recognition apparatus according to the present invention comprises an image data input means for inputting image image data obtained by reading an image of a construction drawing, and a portion consisting of black or white dots of the image image data input by the means. Expansion means for expanding the contour, and dot number measurement for measuring the number of black or white dots in the horizontal and vertical directions of the image image data whose contour is expanded by the means to create dot number measurement array data in the horizontal and vertical directions Arrangement data creating means and contour / skeleton recognizing means for recognizing the contour and skeleton of the construction drawing based on the dot number measurement arrangement data in both directions created by the means are provided. The image data input means may be an image reading means for reading an image of a construction drawing and inputting the image data.

Alternatively, the image data input means inputs the encoded image data obtained by encoding the run length of the image image data obtained by reading the image of the construction drawing, and the dot number measurement array data creating means outputs the encoded image data. Original image image data from the input coded image data. Expanding means for expanding the contour of a portion consisting of black or white dots, and the number of black or white dots in the horizontal and vertical directions of the image image data whose contour is expanded by the means. May be measured to generate dot number measurement array data in the horizontal and vertical directions. In this case, the image data input means may be image data receiving means for receiving and inputting the encoded image data by communication.

Further, in these construction drawing recognition devices, the range of the image data is limited based on the contour and the skeleton recognized by the contour / skeleton recognizing means, and the dot number measurement array data is set for each range. The creation means again creates the dot number measurement array data in the horizontal and vertical directions, and based on the created dot number measurement array data in both directions, the contour / skeleton of the construction drawing within each limited range to the contour / skeleton recognition means. It is advisable to provide a means for repeating the recognition of (1) until the new contour or skeleton cannot be recognized.

In these construction drawing recognition devices,
Display means for displaying the result recognized by the skeleton recognition means may be provided. The display means preferably has means for displaying the image data input by the image data input means simultaneously with the recognition result. The means for simultaneously displaying the image data and the recognition result may be a means for superimposing and displaying the image image data and the recognition result.

Alternatively, there may be provided display selection means for changing display contents so as to selectively display the image image data input by the image data input means and the recognition result. Also, the operator confirms the above recognition result,
It is desirable to provide a recognition result confirmation means for confirming the recognition result by an instruction from the outside.

According to the method for recognizing a construction drawing according to the present invention, the contour of a portion consisting of black or white dots in the construction drawing is expanded, and from the image image data whose contour is expanded, black or white in the horizontal and vertical directions is obtained. The number of dots is measured to create horizontal and vertical direction dot number measurement array data (histogram), and the outline and skeleton of the construction drawing are recognized based on the dot number measurement array data in both directions. For example, a drawing with a relatively low contrast, a drawing with a lot of noise, an old construction drawing, or a construction drawing with lines broken or slightly inclined, or a construction drawing with poor image quality, can be The outline and skeleton can be recognized.

Further, based on the contour and skeleton recognized by this method, the range to be recognized is limited, and the number of black or white dots in the horizontal and vertical directions of the image image data of the construction drawing is limited for each range. It is necessary to measure and re-create the horizontal and vertical dot number measurement array data, and to recognize the outline and skeleton of the construction drawing within each limited range based on the dot number measurement array data in both directions. By repeating the process until the contour or the skeleton cannot be recognized, the skeleton such as a short wall can be surely recognized, and the contour or the skeleton of a portion that does not actually exist can be erroneously recognized.

Further, according to the construction drawing recognition apparatus of the present invention, the above construction drawing recognition method can be easily implemented, and the construction drawings and the comparisons in which the lines are discontinuous or slightly inclined are described. It is possible to accurately and automatically recognize the contours and skeletons of walls, etc. even from construction drawings with poor image quality, and obtain the recognition data. Construction drawings such as floor plans can be easily and quickly created.

The encoded image data obtained by encoding the run length of the image image data obtained by reading the image of the construction drawing is input, and the outline of the portion consisting of black or white dots of the original image image data is expanded from the encoded image data. However, it is also possible to create horizontal and vertical dot number measurement array data by measuring the number of black or white dots in the horizontal and vertical directions of the image image data whose contour has been expanded, and thereby the data amount of the image data. Can be compressed, so the memory capacity for storing it can be reduced. Further, it becomes easy to receive the image data of the construction drawing from the outside by a facsimile function or the like and perform the recognition processing.

The recognition result can be confirmed by displaying the result recognized by the contour / skeleton recognition means on the display means. In this case, by displaying the image image data whose contour has been expanded by the expansion means at the same time as the recognition result, it is possible to find an erroneously recognized part or a part that could not be recognized. At this time, if the image image data and the recognition result are displayed in an overlapping manner, it becomes easier to find and correct the erroneously recognized portion or the unrecognized portion.

Alternatively, it is also possible to selectively display the image image data in which the outline of the construction drawing is expanded and the recognition result, and compare and examine the display contents. Then, the operator can confirm and confirm the recognition result.

[0025]

Embodiments of the present invention will be specifically described below with reference to the drawings. FIG. 1 is a block diagram showing a schematic configuration of an example of a construction drawing recognition apparatus for carrying out a construction drawing recognition method according to the present invention, in which a hardware configuration and a function of software processing by a microcomputer are shown in a mixed manner.

This apparatus comprises an overall control unit 1, an image reading unit 2, a communication control unit 3, a memory 4, an automatic skew correction unit 5,
Dot number measurement array data creation unit 6, contour / skeleton recognition unit 7, remapping control unit 8, display unit 9, operation input unit 1
0, external storage device 11, printing device 12, expansion processing unit 1
3 and a bus 14 for connecting them. It should be noted that interface units required between these units (or devices) and the bus 14 are not shown.

The overall control unit 1 is a microcomputer (C) for controlling the operation and function of the entire construction drawing recognition apparatus.
PU, ROM, RAM, etc.
PU ”), the automatic skew correction unit 5 and the dot number measurement array data creation unit 6 according to the present invention.
The functions of the contour / skeleton recognition unit 7, the remapping control unit 8, and the expansion processing unit 13 can also be realized by software processing of the CPU.

The image reading unit 2 is an image data input means for scanning a construction drawing such as a set architectural drawing, reading the image, and inputting image image data, and a scanning optical system and an image sensor such as CCD. It is a known image scanner including its drive circuit and the like. It also includes a circuit for binarizing the read image image data at a predetermined resolution to obtain white dot and black dot image data.

The communication control unit 3 receives the image data from the image reading unit 2 instead of receiving the image data from the image reading unit 2 and receives and inputs the image image data or the encoded image data in which the run length is encoded by communication from the outside. As a means, it is also possible to transmit the outline and skeleton data of the construction drawing recognized by this device to an external device. Specifically, it includes a FAX modem and personal computer communication control means.

The memory 4 stores image image data read by the image reading unit 2, image image data or coded image data received by the communication control unit 3,
The image data skew-corrected by the automatic skew correction unit 5, the image image data whose contour is expanded by the expansion processing unit 13, the dot number measurement array data created by the dot number measurement array data creation unit 6, the contour / skeleton recognition unit 7 A large-capacity RAM or a memory such as a hard disk for storing the recognition result of the contour and skeleton recognized by, the image data remapped by the remapping control unit 8, and the like.

The automatic skew correction section 5 adjusts the angle of the image data stored in the memory 4 to correct the horizontal and vertical line segments so as to match the horizontal and vertical reference directions of the apparatus. Yes, a known automatic skew correction technique can be used. The image data corrected by the automatic skew correction unit 5 is stored in the memory 4 again.

The expansion processing unit 13 expands the contour of a portion (a straight line portion, an isolated island, etc.) consisting of black or white dots of the image data stored in the memory 4 vertically, horizontally, or diagonally by a predetermined dot to make a thick line. Perform the process. The image data whose contour has been expanded is stored in the memory 4 again. That is, it is a means for expanding the outline of the portion of the image data consisting of black or white dots, the details of which will be described later.

The dot number measurement array data creation unit 6 converts the skew-corrected image data stored in the memory 4, the image data whose contour has been expanded, and the image data remapped by the remapping control unit 8 described later. On the other hand, the image data is limited to two directions, horizontal and vertical, and the number of black or white dots is measured (counted) in each dot width unit, and the result is the dot number measurement array data in the horizontal and vertical directions ( It is a dot number measurement array data creating means for creating a histogram) and storing it in the memory 4.

When the read construction drawing is a positive drawing (a drawing whose brightness is lower than that of the ground), the number of black dots is measured, and a negative drawing (a drawing whose brightness is higher than that of the ground) is used. In that case, the number of white dots is measured.

The contour / skeleton recognizing section 7 recognizes the contour and skeleton of the construction drawing based on the dot number measuring array data in the horizontal and vertical directions created by the dot number measuring array data creating section 6, and in particular the wall A contour / skeleton recognition means for extracting wall data such as position, length, thickness, and type,
The details will be described later.

If it is difficult or uncertain to recognize (extract) a wall with the referenced dot number measurement array data,
A request for resetting the creation range of the number-of-dots measurement array data in the horizontal and vertical directions of the drawing is sent to the overall control unit 1, the creation range is changed and set, and the number-of-dots measurement array data creation unit 6 creates the number-of-dots measurement array data again. Let it. Further, when the wall recognition result does not satisfy the predetermined condition and the appearance as the house drawing cannot be maintained, the expansion request of the image data is sent to the overall control unit 1, and the expansion processing unit 13 performs the expansion process of the image data. Let it run.

The remapping control unit 8 limits the range of the construction drawing by the part recognized as a wall by the contour / skeleton recognition unit 7, considers other recognition information for that part, and remaps it. Then, the image data for making the dot number measurement array data creation unit 6 create the dot number measurement array data again for each limited range is created.
At this time, image data is created in which noise of the original or noise read by the image reading unit 2 is also removed. This data is also stored in the memory 4.

The display unit 9 receives the image data of the construction drawing input from the image reading unit 2 or the communication control unit 3 and skew-corrected by the automatic skew correction unit 5, and the image data whose contour is expanded by the expansion processing unit 13. Horizontal or vertical black or white dot number measurement array data created by the dot number measurement array data creation unit 6, wall data recognized by the contour / skeleton recognition unit 7, and remapping by the remapping control unit 8 It is for displaying image data and the like, and is, for example, a CRT or a liquid crystal display.

FIGS. 2 and 3 show examples of the display state of the screen 9a of the display unit 9. FIG.
7 is a display example of image data (recognition result) obtained by remapping data of a contour and a skeleton (in this example, a wall) of a construction drawing recognized by the remapping control unit 8. In this display example, double solid lines indicate both sides of the wall, and thin lines indicate the core line of the wall and its extension.

FIG. 3 shows image data of a construction drawing whose contour is expanded by the expansion processing unit 13 (in FIG. 3, the contour expansion of the image is shown inconspicuous for convenience of illustration),
An example in which the image data of the wall, which is the remapped recognition result, is displayed at the same time will be shown. In this case, the image image data obtained by expanding the outline of the construction drawing is displayed in halftone so that the two can be easily distinguished (see FIG. 3).
For the sake of convenience of illustration, the image data of the wall, which is the recognition result, is shown by a solid line.

When the display section 9 is a color display device, the discriminability can be improved by displaying the two images in different colors. For example, the input image image data whose contour has been expanded is light blue, and the image data of the recognition result is displayed in orange or green, so that the operator can easily identify the part of the recognition result.

Alternatively, it is also possible to divide the screen 9a of the display unit 9 and display the input image image data whose contour has been expanded and the image data of the recognition result in contrast to each of the divided screens. Alternatively, the input image image data whose contour has been expanded and the image data of the recognition result re-mapped on the same screen may be selectively displayed. In that case, a display selection means (keys or the like) may be provided in the operation input unit 10 described later.

Further, the display unit 9 also displays a screen for the operator to confirm the recognition result. That is, the image data of the re-mapped recognition result is displayed, and a display such as "Is this recognition result OK? (YES / NO)" is performed. This allows the operator to confirm whether the wall has been correctly recognized.

The operation input unit 10 is for inputting various operation instructions, function selection commands, edit data, and the like, and is a keyboard, a mouse, a touch panel, or the like. The operation input unit 10 also has a function as a display selection unit,
The display state of the display unit 9 can be changed to a display state desired by the operator. For example, by operating a key, it is possible to display the input image data of the construction drawing whose contour has been expanded and the image data of the remapped recognition result in a superimposed manner, or to display only one of them.

Further, in response to the display "Is this recognition result OK? (YES / NO)", the operation input unit 10 inputs a key or the like for inputting information of "YES" or "NO". It also has a means. Then, if "YES" is selected, the recognition process ends, and if "NO" is selected, the process proceeds to the re-recognition process or the correction process. Thereby, the operator can confirm the content of the recognition result and determine it.

The external storage device 11 stores the input image data, the image data whose contour has been expanded by the expansion processing unit 13, the black dot number measurement array data created by the dot number measurement array data creation unit 6, the outline / skeleton. The wall data recognized by the recognition unit 7, the image data of the recognition result remapped by the remapping control unit 8, and the like are stored in a storage medium such as a floppy disk (FD) or magneto-optical disk (OMD) that can be taken out to the outside. This is a storage device. The printing device 12 is a printer or a plotter that prints or renders the above various data on paper and outputs the data.

Here, the definitions of "contour" and "skeleton" and "outer wall" and "inner wall" in construction drawings (mainly architectural drawings) will be described with reference to Tables 1 and 2 and FIG.

[0048]

[Table 1]

[0049]

[Table 2]

The "outline" means the "outside outline", and only the portion facing the outside of the outer peripheral wall as indicated by a circle in Table 1 (the double line shown in FIG. Case 1 which means the outer line part) and the entire wall (FIG. 4)
(B) is a case indicated by a bold line).

"Skeleton" means all of the walls (FIG. 4 (b)
(C) both cases indicated by bold lines)
There are two cases, and a case 3 meaning a wall excluding the outer contour (only a portion indicated by a thick line in FIG. 4C). In these definitions, unless otherwise specified, they are treated as the normal meaning of Case 1.

The "outer wall" means only the portion facing the outside of the outer peripheral wall as in the case of the outer contour (see FIG. 4).
Case 4 meaning the portion indicated by the line outside the double line shown in FIG. 4A), and Case 5 meaning the entire wall in contact with the outside (the portion indicated by the thick line in FIG. 4B). There are cases.

The "inner wall" is a wall excluding the outer wall (wall = outer wall + inner wall) in both cases 4 and 5, as shown by a circle in Table 2, whereas in case 4 the case is shown in FIG. 4 (c) and the thick line in FIG. 4 (c), and the case 5 is the thick line in FIG. 4 (c).
Also in these definitions, unless otherwise specified, it is treated as the normal meaning of Case 5.

Next, the procedure for recognizing a construction drawing (mainly a construction drawing of a house or a building) by the construction drawing recognizing apparatus shown in FIG. 1 will be described with reference to the flowcharts of FIGS. 5 to 8 and FIGS.
This will be described with reference to 1. 6 to 8, each step is indicated by “S”. Further, in this embodiment, it is assumed that the recognized construction drawing is a positive drawing.

FIG. 5 is a flowchart showing the main routine of the construction drawing recognition process. When the process of FIG. 5 is started, the construction drawing set in the image reading unit 2 of FIG. 1 is read, its image data is input, and the skew is automatically corrected by the automatic skew correction unit 5.

Then, in the subroutine of step A, a wall recognition process is executed on the input image data by the dot number measurement array data creation unit 6, the contour / skeleton recognition unit 7, and the like. This processing will be described later in detail. Note that data obtained by encoding image image data may be input from the communication control unit 3. Thereafter, the contour / skeleton recognition unit 7 judges in step B whether or not the vector data formed by the straight line of the recognition result by the wall recognition processing in step A can maintain the appearance as a drawing of the building. If so, the process proceeds to step D, where the position and size of the wall that can be recognized at that time are output as the recognition result, and this process ends.

If the appearance of the building as a drawing cannot be maintained in the judgment in step B, it is judged whether or not the judgment is made five times or more. If not, the process proceeds to step C and the expansion processing unit 13 is executed. By this, a binary image expansion process for expanding a contour by adding a predetermined number of black dots in the horizontal and vertical directions to a portion made up of black dots of the image data is performed, and the process returns to step A, and the image in which the contour is expanded. The wall recognition processing and the appearance determination processing as a drawing of the building are performed again on the data.

In this way, when the vector data resulting from the wall recognition processing for the input image data cannot maintain the appearance of the drawing of the building, the image data to be recognized is subjected to binary image expansion processing to be thickened, and again. The wall recognition process is performed, and it is repeated whether the vector data resulting from the recognition result can maintain the appearance of the drawing of the building.

If the vector data obtained by the recognition result of the wall in step A can maintain the appearance of the drawing of the building by the time the judgment in step B is performed five times, the process proceeds to step D and the recognition can be performed at that time. The position and size of the opened wall are output as the recognition result, and this processing ends. However, if the vector data resulting from the recognition result of the wall cannot maintain the appearance of the drawing of the building even after repeating the determination in step B five times or more, error processing such as error display is performed as unrecognizable image data. , This process ends.

The numerical value used in the above judgment may be set to an appropriate value according to the contents of the construction drawing to be recognized. Further, if the predetermined number of black dots are expanded in the diagonal direction by the binary image expansion processing by the expansion processing unit 13 in step C, the straight line portions may be slightly faint or the straight lines may not be correctly connected as in the handwritten drawing. However, the straight line can be corrected to a recognizable level.

FIG. 25 is an explanatory diagram of the image processing when it is determined whether the image data of the wall recognition result can maintain the appearance as a house drawing. In this determination, only the straight lines that have a relationship in which both ends of the straight line recognized from the image data of the wall recognition result are connected to other straight lines are left or branched, and the remaining number of straight lines is, for example, 8 or more. At that time, it is judged that the appearance as a house drawing could be maintained.

That is, a single straight line is deleted as shown in FIG. 25A, and a branch line in which one other straight line is connected to the middle of the single straight line is cut off as shown in FIG. 25B. And delete it, and in this case the rest is a straight line, so delete it as well.

Then, for example, as shown in (c), when the number of straight lines whose both ends are connected to another straight line is eight (this number is set in advance) or more, a building drawing is obtained. We judge that we can keep the appearance. In the image (c), the straight line portion indicated by L is deleted because the right end is not connected to another straight line.

In the binary image expansion processing in step C of FIG. 5, the width of the number of black dots in the image to be expanded at one time is determined by the image density. For example, 400 DPI
In the case of a (dot / inch) image, it is expanded by 2 dots in the horizontal and vertical directions. Further, it may be extended by 2 dots diagonally.

Further, this expansion process will be described with a concrete image. FIG. 26 is a diagram showing an example of image image data after skew correction after input. When the wall recognition processing in step B is performed on this image data, only straight lines having a width less than a predetermined width can be recognized. Therefore, in step C, the binary image expansion processing is performed to expand the contour of the black dot portion of the image data by a predetermined dot (not shown). When the wall recognition processing in step A is performed again on the image data, the result is as shown in FIG. 27, and the straight lines showing most of the walls can be recognized. There are some parts that have been recognized without being identified.

In the judgment processing in step B for the image data of the recognition result shown in FIG. 27, it is judged whether or not the appearance can be maintained as the drawing of the building. First, from this image data, the straight line portion having both ends shown in (a) and (b) of FIG. Obtain the image data as shown. In this image data, both ends of all straight lines are connected to other straight lines, but the total number of straight lines is seven.

Therefore, since the total number of straight lines is not more than 8 which is set in advance, it is judged that this image data cannot maintain the appearance as a drawing of the building, and the image data that has been subjected to the binary image expansion processing first is selected. The binary image expansion process is performed again in step C, and the black dot portion is expanded by a predetermined number of dots. For example, two black dots are added in each of the horizontal, vertical, and diagonal directions of the black dot portion for expansion, and image data as shown in FIG. 29 is obtained.

Then, the wall recognition processing in step A is performed again on the image data after the contour is expanded, and the image data of the recognition result as shown in FIG. 30 is obtained.
In this image data, there are still some branch lines where some straight lines are not yet connected, but due to the expansion of the black dots, most of the straight lines that were not connected in the first process are connected.

Further, with respect to this image data, it is judged again in step B whether or not the appearance can be maintained as the drawing of the building, and the image data as shown in FIG. 31 is obtained.
In that image data, the image data with the branch lines deleted remains, and the total number of straight lines with both ends connected to other straight lines is 17, and this time it is 8 or more, so it is effective as a building drawing. Judge that there is. Then, the position and size of the wall of the image data shown in FIG. 30 is stored in the memory 4 or the external storage device 11 as the recognition result of the wall from the construction drawing by the process in the above step D, or output such as display on the display unit 9. do.

In this way, even with respect to a drawing in which lines are cut in places due to scratches or irregularities due to handwriting, the incomplete portion of the image can be corrected, so that the wall recognition processing can be performed more accurately. it can.

Next, the wall recognition processing in step A of FIG. 5 will be described. FIG. 6 is a flowchart showing the contents of the subroutine of the processing for recognizing the position of the wall. First,
In step 3, the entire image data that has been automatically skew-corrected or the image data whose contour has been expanded is to be investigated. Then, in step 4, the nest variable is 0 (initial value: meaning the entire image is targeted). “Nest variable” represents the stage of narrowing down the analysis range of construction drawings from the top down. The larger the value of the nested variable, the deeper the analysis (the more advanced the part).

In step 5, a process of limiting the region to be investigated of the position of the wall is performed. Specifically, the instruction of the investigation area is shown immediately before this processing, and here, only preparation for the processing of the subsequent steps 6 to 9 (standardization of the interface) is performed. The shape of each survey target area is a rectangular diagram. At first, since the nest variable is 0, the whole drawing is to be investigated.

In step 6, horizontal black dot number measurement array data is created. In this method, the number of black dots in the horizontal direction is counted (measured) for each one dot width in the vertical direction of the image data, and the counted data is held.
Next, in step 7, a wall extraction (recognition) process is performed based on the horizontal black dot number measurement array data created in step 6. The processing procedure will be described later.

In step 8, as in step 6, vertical black dot number measurement array data is created. That is, the number of black dots in the vertical direction is counted (measured) for each horizontal dot width of the image data, and the counted data is held. In step 9, a wall extraction (recognition) process is performed based on the black dot number measurement array data in the vertical direction.

Then, in step 10, it is judged whether there is a wall candidate for dividing the area. If there is at least one wall candidate that divides the region in the horizontal or vertical direction, the process proceeds to step 11. If there is no such wall candidate, the process proceeds to step 13. For example, a wall candidate Wd that divides a region into a survey target region Sa as shown in FIG.
To determine if is present. In step 11, the nest variable is incremented by 1 and reset. This indicates that a wall is recognized from the current analysis area, and the analysis area is limited to a small area in the newly partitioned current area using the wall.

Then, in step 12, the area to be investigated is subdivided. Specifically, at the core line (center line) of the wall candidate recognized in steps 7 and 9,
For example, as shown in FIG. 9A, the investigation target area is defined by the core lines indicated by the thin lines of the wall candidates W and Wd.
Into two parts. Further, the position of the survey target is set in the first subdivided area (for example, the upper left area).

The order of analysis in the newly subdivided region group does not require a special order. For example, the analysis is performed in the order of small x, y coordinate values of the region start position. And so on. FIG. 9B shows an example of the nest No. of each area subdivided by the wall candidates and the analysis processing order. The solid line indicates the core line (center line) of the wall candidate.
,, Indicate the nest number, and small numbers 1 to 8 indicate the processing order.

Thereafter, the flow returns to step S5 to repeat the above-mentioned processing. If there is no wall candidate to be divided in step 10, the process proceeds to step 13 to determine whether there is any remaining homogeneous nest area (the area of the same nest No. in FIG. 9B). to decide. If there is any remaining, the object to be investigated is advanced to the next area of the homogeneous nest in step 15, and the process returns to step 5.

If there is no remaining homogeneous nest area, the routine proceeds to step 14, where it is determined whether the nest variable is 0 or not. If the nest variable is not 0, the nest variable is decremented by 1 at step 16 and the process returns to the processing of the nest area one level higher. At step 13, it is determined whether there is a nest area remaining at that level. If there is, in step 15 the search target is advanced to the next nest area, and the process returns to step 5.

If the nest variable is 0 in step 14,
Proceeding to step 17, the position and size of each wall are determined based on the recognition data of the wall candidates for each area obtained in steps 7 and 9, and the wall recognition data is stored in the memory 4. The storage method will be described later. Then, in step 18, the recognition data is displayed on the display unit 9 as necessary, printed by the printing device 12, or stored in the external storage device 11, and the process ends.

Next, the procedure of the wall extraction (recognition) processing in steps 7 and 9 of FIG. 6 will be described with reference to FIG. 7. Prior to that, a construction drawing (house floor plan), which is a construction drawing, will be described. 10 and 11 show specific examples of the image data after the outline is expanded and the horizontal and vertical direction black dot number measurement array data created from the entire area thereof. In these drawings, (a) is image data of architectural drawings, (b) is horizontal black dot number measurement array data, and (c) is vertical black dot number measurement array data. Further, FIG. 10 (c)
FIG. 12 is an enlarged view of the vertical black dot number measurement array data shown in FIG.

In the architectural drawing of FIG. 10, the symbol of the wall is represented by both sides of the wall and the core, and in the architectural drawing of FIG. 11, the symbol of the wall is filled (black) within the thickness of the wall.
Is represented by In this black dot number measurement array data, the width of the thinnest black line is one dot width, and the length of each black line is horizontal or vertical for each one dot width of the image data of the architectural drawing shown in FIG. It corresponds to the counted value of the number of black dots in the direction.

As is clear from these figures, most (90% or more) of the line segments constituting the architectural drawing are drawn in the horizontal direction or the vertical direction. Has become. Therefore, a peak appears at the position where the wall exists in the black dot number measurement array data in the horizontal direction and the vertical direction.

When the processing of the flow shown in FIG. 7 is started, first, in step 21, a direction crossing the designated direction (vertical direction if the black dot number measurement array data creation in the horizontal direction is designated, and vertical direction if designated in the vertical direction). If it is horizontal)
Next, it is confirmed how many times the loop of the wall recognition process can be performed at predetermined intervals corresponding to the reference unit length of the construction drawing. here,
This unit length is half a space or 1 meter which is the minimum wall interval in the case of a general house.
cm).

For the array data of the number of black dots in the horizontal direction, a dimension slightly longer than the image width in the vertical direction is defined as the width size L. A dimension slightly longer than the width is automatically set as the width size L. Further, the half size is set to h, and this value is determined by inputting the scale data and half length of the drawing in advance or by automatic calculation by calculation or the like. L / h is calculated from the width size L and the half space size from h, and the value rounded up to the decimal point is defined as the number of executions n of the large loop of the wall recognition process. The range indicated by h in FIG. 12 is the processing range in one large loop.

Next, in step 22, the count value i of the large loop number counter is initialized (i ← 1).
Then, in step 23, the count value i of the number counter exceeds the number of possible large loop executions n (i> n).
Is determined. If so, the analysis of the area is terminated. If not, in step 24, it is positioned at the highest peak (indicated by P in FIG. 12) as the first analysis process within the i-th half, and that point is defined as xp. By performing the analysis processing every half period in this way, it is highly possible that the peak value therein is a part of the wall.

Next, in step 25, it is determined whether or not the height of the peak (maximum value), which is the first condition as an object of the wall, is equal to or longer than a half (h). As a result, if the height of the peak is less than half a minute, the recognition of the wall is unknown, and the process proceeds to step 34 in order to proceed to the analysis of the next half a point. When the height of the peak is half or more, the process proceeds to the next analysis step 26. In this step 26, the left and right sides (for example, 2 W width) are checked from the position of the highest peak, and the range of wall thickness (positions on both sides: W ₁ , W ₂ and thickness We = | W ₁ −W ₂ |)
To narrow down. Here, W means the thickness of the wall, and is used, for example, with the same value as Wmax.

As a narrowing-down method, the peak positions at both ends or one side of the highest peak position having a value of (maximum peak value−min) * rate + min or more are determined by the positions W ₁ and W _{2 on} both surfaces of the wall.
Or highest peak position xp is a method to narrow the position W ₂ of the other surface when the position W ₁ of one side of the wall.

FIG. 13 is an explanatory diagram of this narrowing-down processing. FIG. 13A shows an example in which the positions W ₁ and W ₂ of both sides of the wall exist on both sides of the highest peak position xp. In this case, the highest peak position xp is estimated as a candidate for the center line position of the wall.

FIG. 13B shows an example in which the highest peak position xp is the position W ₁ on _one surface of the wall, and the position W ₂ on the other surface exists on one side. In this case, it can be estimated that the longer peak position is a candidate for the outer wall position of the outer contour indicated by the double line in FIG. 2 and the shorter peak adjacent thereto is a candidate for the inner wall position.

Here, the rate is set small in the first half of the analysis (when the value of the nest variable is small) and large in the second half (when the value of the nest variable is large) (for example, at first, rater =
0.70). As shown in (c) of FIG. 13, min is 2 W on both sides of the position xp of the maximum peak P that is currently focused on.
Is the minimum value of the black dot number measurement data within the width of about 4 W widened.

In this way, the validity as a wall is confirmed in steps 27 and 28 based on the result narrowed down in step 26 in FIG. First, in step 27, it is determined whether or not the wall thickness We exceeds its maximum value Wmax (for example, 30 cm). Proceed to.
If not, the process proceeds to step 28, where it is determined whether or not the wall thickness We is less than a minimum value Wmin (for example, 2.5 cm).

As a result, if the wall thickness We is less than the minimum value Wmin, the process proceeds to step 30; otherwise, the process proceeds to step 29. In step 30, the information is obtained on the assumption that a peak other than a wall (for example, a tatami mat, a window, a sliding door, etc.) has been recognized. In step 29, it is determined from the candidate area of the wall whether or not the condition as a wall is satisfied by a bisecting search method described later. Information such as the positions W ₁ and W ₂ and the thickness We is saved (stored), and the process proceeds to step 32.

If the condition as a wall is not satisfied in step 29, the process proceeds to step 32. In step 32, it is determined whether both side positions (coordinates) W ₁ and W ₂ of the wall are inside the area currently being processed. If not, the process proceeds to step 34.

In step 33, the current processing area is subdivided, and W ₁ ,
W ₂ and We are saved (stored). Also, (W ₁ + W ₂ ) /
2 is the center line position of the wall. In step 34, the count value i of the large loop number counter is incremented by 1 in order to perform the next half-ahead process, and the process returns to step 23 to repeat the above-described processing.

In this way, the analysis processing is performed every half a period from one end (leading element) of the target black dot number measurement array data, and when the analysis is completed up to the opposite end, the analysis of the current range is completed. The two directions of the horizontal direction and the vertical direction are separately analyzed with respect to the black dot number measurement array data, and the next analysis range is limited to a range that can be recognized as a wall in the current analysis. Therefore, the result of analyzing the array data of the number of black dots in the horizontal and vertical directions is combined to perform the round robin classification.

In this embodiment, it is considered that the center line position of the wall is arranged so that the interval between the adjacent wall is an integral multiple of a half unit. Then, a range up to a characteristic peak can be effectively used as analysis data. Conversely, if no feature corresponding to a wall is found within a certain range to be analyzed, even in both the horizontal and vertical directions, the analysis ends. A single analysis range initially covers the entire drawing, and is then limited to a range demarcated by walls that have been discovered since then, making it easier to find wall peaks and to analyze details in detail. So that

Next, the halving search method for judging “whether the condition as a wall is satisfied” in step 29 of FIG. 7 will be described with reference to the flowchart of FIG. When the processing of the flow shown in FIG. 8 is started, first, in step 41, initialization of the halving search method is performed. In other words, the number n of the area division elements for the wall analysis is set to 1, and the smallest No. of the array elements of the division elements for which the wall or the non-wall is undetermined.
Is set to 0, and S is set as a divided array element of the survey area.

[0], E

[0] Substitute the input start and end image addresses for each and set the initial settings.

Thereafter, the flow advances to step 42. If the start address S [k] of the investigation area is equal to the end address E [k], the flow shifts to step 53;
Proceed to 3. In step 43, the target area of the image data is divided, and the original area is divided into two equal parts except for errors of decimal numbers or less.

That is, the start and end image addresses S1 and E1 of the first half area to be divided are set as S1 = S
[K], E1 = (1/2) (S [k] + E [k]),
Start and end image addresses S2, E of the latter half area
2 as S2 = (1/2) (S [k] + E [k]) + 1, E
Let 2 = E [k].

As a result, as shown in FIG. 14, for example, in the image data of the construction drawing, the original area width of the line (indicated by a dashed line) where the wall candidate exists is initially divided into two equal parts at the position of one. I do. Thereafter, until the presence or absence of the wall can be determined, the second time at the position 2 shown in FIG.
The wall inspection of steps 44 and 45 is performed in the subdivided area by repeating the halving such as the fourth time at the fourth and fourth positions. In steps 44 and 45,
It is checked whether or not each of the equally-divided areas P1 and P2 is filled with a wall.

Here, as a result of analyzing the black dot number measurement array data in the designated area (from the start address to the end address), the height of the peak of the black dot (while keeping the thickness of the wall wide) is designated. The following (1) to (3) are compared with the width (length) of the region.

: When 5% or less, v = 0: Judge as non-wall part: When 95% or more, v = 1: Judge as wall part: Other than the above, v = 2: Neither can be judged As shown in the figure, it is as shown in FIG.

In step 46, if it is not possible to determine whether a wall exists in the first half area P1 divided in step 43 (v = 2), the flow proceeds to step 47; otherwise, the flow proceeds to step 49. Step 47
In, the storage array elements S [k], E [k], and v [k] of the area range before being divided in step 43 are converted into the latter half of the area data (start and end image addresses S2, E2 is replaced with the determination result v2).

In step 48, new storage array elements S [n], E [n], v [n] are set as step 4
The first half area data (start and end image addresses S1, E1 and determination result v1) divided by 3 are saved, and the process proceeds to step 51. In step 49, the storage array elements S [k], E [k], and v [k] of the area range before the division in step 43 are replaced with the first half area data (start and end image addresses) divided in step 43. S1 and E1 are replaced with the determination result v1).

In step 50, new storage array elements S [n], E [n], v [n] are set as step 4
The second half area data (start and end image addresses S2, E2 and determination result v2) divided by 3 are saved, and the process proceeds to step 51. In step 51, the variable n indicating the new storage array element No. is incremented by 1 so as to indicate the new storage array element of the area address, and then the process proceeds to step 52.

In step 52, the classification code v in the k element indicating the smallest No. of the divided elements for which the wall portion or the non-wall portion is undetermined is a content for which it is not known whether or not a wall exists (v = 2 In the case of ()), the process returns to step 42 and the process of further subdividing is repeated. Otherwise, go to step 53. In step 53, it is determined that one content that cannot be determined whether or not a wall exists has been resolved, and the index k is incremented by one, and then the process proceeds to step 54.

In step 54, the number n of the area dividing elements for the wall analysis is equal to k indicating the smallest No. of the array elements of the dividing elements whose walls or non-walls are undetermined. It is determined whether or not they are equal, and if they are equal, it is determined that the division processing for wall recognition has been completed, and the flow proceeds to step 55.
If they are not equal, the process returns to step 52.

In step 55, sorting is performed in the order of the start addresses (ascending order) so that the divided area address data (array) is arranged in the ascending order.
Move to That is, S

[0] to S [n-1], E

[0] to E [n-1], v

The data [0] to v [n-1] are sorted in ascending order using S [] as a key.

In step 56, when the wall portion and the non-wall portion are continuous, the degeneracy process (represented by one range) is performed and the process ends. That is, continuous v
If the value of [] is 0 or 1, S [], E
[] Compress the data. At this time, if an array element having contents (v = 2) for which it is not known whether or not a wall exists is included, if the element before and after that element indicates a wall, the data is changed to wall data. If it indicates a non-wall, it is changed to non-wall data and processed.

FIG. 16 shows an example of analyzing the wall position in the image data by the above-mentioned halving search processing. In FIG. 16A, a wall image image (shaded portion) W and its investigation target area are indicated by broken lines, and this investigation area is located along the position of the previously recognized wall candidate. Is set.
And S

[0] = 0 is the first start address of the investigation area, E

[0] = 15 is the first end address. The numbers in the middle such as 4, 5, 7 are the start or end address (all are image addresses) of the target area after division.

FIG. 16B shows the start address S, end address E, and judgment result v regarding the presence / absence of a wall of each target area at each investigation stage of variables n = 1 to 10, the confirmation status, the sorting status, Also, the result of the degeneration process is shown together with the value of k. And finally, the image address 5
Recognizing the presence of walls at ~ 12.

Next, an example of a simple construction drawing wall recognition will be described with reference to FIG. FIG. 17 shows a nested variable (ne
(st) and the actual state of the wall recognized as the region division state. First, with the nest variable = 0, the wall is extracted with the entire construction drawing as the wall position survey target. As a result, it is assumed that the outline of the house in the construction drawing and the positions of the horizontal and vertical wall candidates can be recognized as indicated by the solid line in (A). However, among the recognized wall candidates, the actual wall is only the portion shown in (a), but it is not yet known.

Then, next, the nest variable = 1 is set, and
A wall is extracted by limiting the investigation target area for each rectangular area demarcated by the core line of the recognized wall candidate shown in FIG.
As a result, in (B), wall candidates indicated by thick lines are newly recognized in the four investigation target regions indicated by,, and among the previously recognized wall candidates, actual walls are indicated in (a). That is, it is confirmed that the part is only the part which has been changed, and the state of the wall shown in (b) is recognized.

Further, by setting the nest variable = 2, the four regions in which the new wall candidate is recognized in (B) are divided by the newly recognized wall to further limit the region to be investigated. Extract the wall. As a result, a wall candidate indicated by a thick line is newly recognized in the two investigation target areas indicated by (C), and a state of the wall illustrated by (c) is recognized.

Thereafter, the nest variable is set to 3, and the two regions in which the new wall candidate is recognized in (C) are divided by the newly recognized wall, respectively, to further limit the region to be investigated. Extract the wall. As a result, if it is not possible to extract a new wall candidate in any of the divided regions, the investigation of the wall position is thereby terminated,
It is determined that the wall position shown in (c) is the final wall recognition result, and the data is stored in the memory.

As described above, until no new wall candidate is extracted in any of the divided inspection target areas, the inspection target area is subdivided and the wall is extracted. Thereby,
Even a small wall can be reliably recognized, and a portion where a wall actually exists and a portion where no wall exists among wall candidates can be accurately determined.

Here, an example of a concrete construction drawing recognition procedure according to the flowchart of FIG.
This will be described with reference to FIGS. 18 to 20
Is a series of figures, which are divided into three figures for convenience of illustration. S3 to S18 in these figures are the same as those in FIG.
It corresponds to each step of S3 to S18. In addition, an area division diagram and an actual wall state at each stage are also shown.

In the following description, steps are abbreviated as “S”. In S3 of FIG. 18, the entire drawing is to be investigated, and the nest variable is set to 0 in S4. In S5, the search target is limited. However, since the nest variable is 0, the whole drawing is also set as the search target. In steps S6 and S7, the black dot number measurement array data in the horizontal direction is created and the wall is extracted. However, a wall other than the contour cannot be found, and the black dot number measurement array data in the vertical direction is created in S8 and S9. Is extracted, and a wall other than the contour is found in two places. Therefore, YES is determined in S10, the nest variable is set to 1 in S11, the area is subdivided (at each wall position) in S12, and the process returns to S5 to limit the investigation target area to the leftmost area.

Then, in S6 and S7, the wall was found in two places. In S8 and S9, the wall could not be found, but in S10, the result was YES. The processing is repeatedly executed until the result of the determination in S14 of NO becomes NO and the nesting processing is completed, and wall extraction processing is sequentially performed on three divided areas obtained by dividing the vertically long area on the left side by two newly discovered walls.

In this example, no new wall is found, and the nest variable is decremented by 1 in step S16 in FIG. 19 to return it to 1, and a vertically elongated region in the middle is used as a region to be investigated, and a wall is similarly extracted. In this example, no new wall candidate is found. Therefore, the investigation target area is changed to the right vertically elongated area in S15 and S5, and one wall is found in S6 and S7.

Then, YES is obtained in S10 of FIG.
In step S11, the nesting variable is set to 2 and the "nesting process" is started, and the vertical region on the right is divided by a newly discovered wall, and the wall extraction process for each of the divided regions is sequentially performed. As a result, no new wall is found in any of the divided areas, and S1
At 3 the answer is NO and the nesting process is terminated, and the nest variable is decremented to 1 at S16. Since the area of the nest variable 1 does not remain, the nest variable is further returned to 0, but the area still remains. Absent. Therefore, it is determined that the wall extraction process has been completed, the position and size of each wall are determined based on the recognition data of the wall candidates extracted in S17, and the data is stored in the memory.

Next, information (analysis result data) such as the position and size of the wall corresponding to the outline and skeleton of the construction drawing recognized as described above is stored in the memory 4 and the external storage device 11 shown in FIG. For an example of the content stored on the medium,
This will be described with reference to FIG. In FIG. 21, (A) is the number of nests, (B) is the specific nest information, (C) is the horizontal wall information, (D) is the vertical wall information, (E) is the model of the horizontal wall, (F) ) Indicates a vertical wall model.

The number of nests indicates the depth of nesting (parent-child relationship) of child nest pointers. If no wall is recognized, the number of nests is zero. The unique nest information includes a nest No., a NEXT sibling pointer, a child nest pointer, the number of walls (horizontal and vertical directions), and a wall information pointer (horizontal and vertical directions).

The NEXT sibling pointer has the next address of the simultaneous hierarchical nest information. Therefore, the nest number in the unique nest information at the location indicated by the pointer has the same value as that of the processing. The child nest pointer has the address of the leading data of the hierarchy nest information one level lower. Therefore, the nest number in the specific nest information at the location indicated by this pointer is a value obtained by adding +1 to that of the processing.

The horizontal wall information shown in (C) is stored with the address indicated by the horizontal wall information pointer in the unique nest information shown in (B) as the head address. The wall information includes a NEXT pointer indicating the position of the start address of the next horizontal wall information, and the starting point coordinates (x coordinate: a,
y coordinate: b), horizontal (x-direction) size of wall: c, vertical (y-direction) size of wall: wall thickness d. These a ~
By d, the model of the horizontal wall shown in (E) can be stored and reproduced.

Similarly, the address indicated by the vertical wall information pointer in the unique nest information is set as the head address.
The vertical wall information shown in (D) is stored. The wall information includes a NEXT pointer indicating the position of the start address of the next vertical wall information, the starting point coordinates of the wall (x coordinate: e, y coordinate: f), the vertical (y direction) size of the wall: g, the wall Horizontal (x-direction) size: Consists of wall thickness h. With these e to h, the model of the vertical wall shown in (F) can be stored and reproduced.

By the way, FIGS. 10 and 11 show examples in which the black dot number measurement array data in the horizontal direction and the vertical direction is prepared with respect to the image data of an actual architectural drawing by using the whole drawing as an investigation area. In the next step of recognizing a wall candidate based on the black dot count measurement array data, the area of the drawing is divided by the recognized wall candidate, and black in the horizontal and vertical directions based on image data in which the investigation target area is limited. FIGS. 22 to 24 show examples of creating dot number measurement array data.
Shown in

FIGS. 23 and 24 are examples in which the investigation target area is further subdivided than in FIG. In this way, until no new wall candidates are found, the investigation target area is subdivided, and the horizontal and vertical black dot number measurement array data based on the image data is created, and the wall is extracted.

In this embodiment, since the construction drawing of the positive image is targeted for recognition, the number of black dots in the horizontal and vertical directions of the binarized image data is measured (counted) to calculate the black dot number array data. However, when the construction drawing of the negative image is to be recognized, the number of white dots in the horizontal and vertical directions of the binarized image data is measured (counted) and the white dot number measurement array data is created. Then, the wall can be recognized in the same manner.

Further, the recognition data concerning the outline and skeleton of the construction drawing recognized as described above can be converted into CAD vector data, and compatibility of CAD data between different models can be obtained.

Further, in this embodiment, a binary image expansion process is performed in which the contour of the portion consisting of black dots is expanded by a predetermined number of dots in both the horizontal and vertical directions or in the oblique direction,
As a result, the broken lines are combined, and even if the straight line is slightly inclined, the image data in a state in which the projective feature can be extracted is used for the recognition processing of the wall and the like, and therefore the following advantages are obtained.

(1) Even if a wall is described by a thin horizontal and vertical single line, it can be surely recognized. (2) As a tool for drawing a line, even an architectural drawing described with a stationery such as a pencil in which a black line is coarse and discontinuous can be reliably recognized. (3) Even in drawings written freehand without using a ruler, etc., if the fluctuation of the line is offset in the description of the wall,
If the correctness in the horizontal and vertical directions is good, it can be recognized.

When it is difficult to correct the skew in the handwritten drawing, it is preferable to describe the handwritten drawing on the graph paper and perform the skew correction by using the grid of the graph paper. If it is unavoidable to leave it to the user's manual work, a manual may be attached to draw attention to creating a facing drawing that requires as little skew correction as possible when reading the scanner.

[0135]

As described above, according to the construction drawing recognition method and the recognition apparatus of the present invention, a handwritten drawing in which a line which has been difficult to be recognized accurately or a straight line is slightly inclined is described. , It is possible to easily and accurately recognize the contour and skeleton of a construction drawing, such as blueprint, which has a relatively low contrast, a drawing with a lot of noise, or an old construction drawing, which has a poor description or poor image quality. .

In particular, the target range is limited so as to subdivide the recognition target based on the outline and skeleton recognized first for the entire drawing, and the horizontal direction of the image image data of the construction drawing is limited for each range. And vertical black or white dot number measurement array data are created, and based on the dot number measurement array data in both directions, recognizing the outline and skeleton of the construction drawing within each of the above-mentioned limited ranges, a new outline Alternatively, if the process is repeated until the skeleton cannot be recognized, the skeleton such as a short wall can be surely recognized, and there is no risk of erroneously recognizing the outline or skeleton of a portion that does not actually exist.

Further, if the recognized data is loaded into a personal computer or the like and used, a construction drawing such as a sketch at the time of extension and renovation can be easily and quickly created.
Furthermore, the image data of the construction drawing is input as run-length encoded image data by facsimile communication or the like,
It is also possible to recognize the outline and skeleton of the construction drawing.

Further, by analyzing whether or not there is a peak value of the dot number measurement array data at a half interval corresponding to the minimum wall interval in a general construction drawing or at intervals corresponding to 1 m, the accuracy of wall recognition is improved. Can be increased. Further, it is possible to recognize the wall and its core wire or the inner wall and the outer wall.

Further, by displaying the result recognized by the contour / skeleton recognition means, the recognition result is confirmed,
Can be confirmed. In this case, the image data of the construction drawing whose contour has been expanded after input is displayed simultaneously with the recognition result or selectively, so that the displayed contents are compared and examined to find erroneously recognized parts or unrecognized parts. be able to. If the image image data whose input contour has been expanded and the recognition result are displayed in a superposed manner, it becomes easier to find and correct an erroneously recognized portion or a portion that cannot be recognized.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a schematic configuration of an example of a construction drawing recognition device for implementing a construction drawing recognition method according to the present invention.

FIG. 2 is a diagram showing a display example of image data of a re-mapped recognition result on a display unit 9 of FIG. 1;

FIG. 3 is a diagram showing an example in which input image data of a construction drawing whose skew has been corrected and whose contour has been expanded is displayed by being superimposed on image data of a recognition result.

FIG. 4 is a diagram for explaining the definition of an outer contour, an outer wall, an inner wall, and a skeleton in a construction drawing.

FIG. 5 is a flowchart showing a main routine of construction drawing recognition processing by the construction drawing recognition device shown in FIG. 1;

FIG. 6 is a flowchart showing details of a subroutine of wall position recognition processing of step A in FIG.

FIG. 7 is a flowchart of a subroutine of extraction (recognition) processing of walls of steps 7 and 9 in FIG. 6;

FIG. 8 is a flowchart for executing a bisection search method for recognizing the position of a wall.

FIG. 9 is a diagram illustrating an example of a wall candidate in a survey target region, a region division by the wall candidate, and a nest N of a region group subdivided by the wall candidate.
o. FIG. 4 is an explanatory diagram showing an example of the order of analysis processing.

FIG. 10 is a diagram showing a specific example of image data of an architectural drawing (floor floor plan) and black dot number measurement array data in the horizontal and vertical directions created from the entire area thereof.

FIG. 11 is a diagram showing another specific example.

FIG. 12 is an enlarged view showing the arrangement data of the black dot number measurement array in the vertical direction shown in FIG.

FIG. 13 is an explanatory diagram of a process of narrowing both sides of the wall to both sides or one side of the peak in step 26 of FIG.

14 is an explanatory diagram of region width division processing in step 43 of FIG. 7. FIG.

15 is an explanatory diagram of the determination by wall survey of the target area in steps 44 and 45 of FIG.

16 is an explanatory diagram showing an example of analysis of a wall sample (wall candidate) by the equally divided search process shown in FIG. 7. FIG.

FIG. 17 is an explanatory diagram of a wall recognition example of a simple construction drawing according to the present invention.

FIG. 18 is an explanatory diagram showing an example of a specific construction drawing recognition processing procedure according to the flowchart of FIG. 5;

FIG. 19 is an explanatory view continued from FIG. 18;

FIG. 20 is an explanatory view continued from FIG. 19;

FIG. 21 is an explanatory diagram showing an example of the contents of analysis result data stored in a memory;

22 is a diagram showing an example of image data of the architectural drawing shown in FIG. 10 in which the investigation target area is limited, and the array data of the number of black dots measured in the horizontal and vertical directions based on the image data.

FIG. 23 is a diagram showing an example of image data in which the investigation target area is further limited from FIG. 22, and an example of the arrangement data of the number of black dots in the horizontal and vertical directions based on the image data.

24 is a diagram showing an example of image data of another portion in which the investigation target area is further limited from FIG. 22 and black dot count measurement array data in the horizontal and vertical directions based on the image data.

FIG. 25 is an explanatory diagram of image processing for determining whether or not the image data in step B of FIG. 5 can maintain the appearance as a drawing of the building.

26 is a diagram showing an example of image data to be processed by the construction drawing recognition processing by the construction drawing recognition apparatus shown in FIG.

27 is a diagram showing image data obtained when the wall recognition process in step A of FIG. 5 is performed after the binary image expansion process is performed on the image data shown in FIG. 26.

28 is a diagram showing image data obtained when the determination process in step B of FIG. 5 is performed on the image data shown in FIG. 27.

FIG. 29 is a diagram showing image data obtained when the binary image expansion processing in step C of FIG. 5 is performed on the image data shown in FIG. 28.

30 is a diagram showing image data obtained when the wall recognition processing in step A of FIG. 5 is performed on the image data shown in FIG. 29.

31 is a diagram showing image data obtained when the determination process in step B of FIG. 5 is performed on the image data shown in FIG. 30.

[Explanation of symbols]

 1: Overall control unit 2: Image reading unit 3: Communication control unit 4: Memory 5: Automatic skew correction unit 6: Dot count measurement array data creation unit 7: Contour / skeleton recognition unit 8: Remapping control unit 9: Display unit 10: Operation input unit 11: External storage device 12: Printing device 13: Expansion processing unit 14: Bus

Claims (12)

[Claims] 1. The number of black or white dots in the horizontal and vertical directions of the image image data obtained by expanding the outline of a portion consisting of black or white dots of the image image data obtained by reading an image of a construction drawing and expanding the outline. A method for recognizing a construction drawing in which horizontal and vertical dot number measurement array data is created, and the contour and skeleton of the construction drawing are recognized based on the created dot number measurement array data in both directions. 2. The number of black or white dots in the horizontal and vertical directions of the image image data obtained by expanding the contour of the portion consisting of black or white dots of the image image data obtained by reading the image of the construction drawing is measured. Then, the dot number measurement array data in the horizontal and vertical directions is created, the contour and skeleton of the construction drawing are recognized based on the created dot number measurement array data in both directions, and the limitation is made based on the recognized contour and skeleton. The number of black or white dots in the horizontal and vertical directions of the image image data is measured for each range, and the dot number measurement array data in the horizontal and vertical directions is created again, and based on the created dot number measurement array data in both directions. And recognizing the outline and skeleton of the construction drawing within each of the limited ranges described above are repeated until a new outline or skeleton cannot be recognized. A method for recognizing construction drawings. 3. An image data inputting means for inputting image image data obtained by reading an image of a construction drawing, an expanding means for expanding the contour of a portion of the image image data input by the means, which is composed of black or white dots, Dot number measurement array data creation means for creating horizontal and vertical dot number measurement array data by measuring the number of black or white dots in the horizontal and vertical directions of the image image data whose contour has been expanded by the means, and by the means A construction drawing recognizing device, comprising: a contour / skeleton recognizing means for recognizing a contour and a skeleton of a construction drawing based on the generated dot number measurement array data in both directions. 4. The construction drawing recognizing apparatus according to claim 3, wherein the image data input means is an image reading means for reading an image of a construction drawing and inputting image data of the image. 5. Image data input means for inputting encoded image data obtained by encoding run lengths of image image data obtained by reading an image of a construction drawing, and original image image data from the encoded image data input by the means. Expansion means for expanding the contour of a portion consisting of black or white dots, and measuring the number of black or white dots in the horizontal and vertical directions of the image image data whose contour is expanded by the means to measure the number of dots in the horizontal and vertical directions. It has a dot number measurement array data creating means for creating array data, and a contour / skeleton recognizing means for recognizing a contour and a skeleton of a construction drawing based on the dot number measuring array data in both directions created by the means. A construction drawing recognition device. 6. The construction drawing recognition apparatus according to claim 5, wherein said image data input means is image data receiving means for receiving and inputting said encoded image data by communication. 7. The construction drawing recognition device according to claim 3, wherein the range of the image data is limited based on the contour and the skeleton recognized by the contour / skeleton recognition means. The dot number measurement array data creating means for each range again creates the dot number measurement array data in the horizontal and vertical directions, and the contour / skeleton recognizing means based on the created dot number measurement array data in both directions. A construction drawing recognizing device comprising: means for repeating recognition of the contours and skeletons of the construction drawings within the respective limited ranges until a new contour or skeleton cannot be recognized. 8. The construction drawing recognition device according to claim 3, further comprising display means for displaying a recognition result by the contour / skeleton recognition means. . 9. The construction drawing recognizing device according to claim 8, wherein the display means has means for displaying image image data whose contour is expanded by the expanding means at the same time as the recognition result. Recognition device. 10. The construction drawing recognition apparatus according to claim 9, wherein the means for displaying the image image data at the same time as the recognition result is means for displaying the image image data in which the contour has been expanded, overlapping the recognition result. The construction drawing recognition device characterized by being. 11. The construction drawing recognition device according to claim 8, further comprising display selection means for changing display contents so as to selectively display image image data whose contour is expanded by said expansion means and said recognition result. A construction drawing recognition device characterized in that 12. The construction drawing recognition device according to claim 8, further comprising a recognition result confirmation means for confirming the recognition result displayed on the display means by an external instruction. Characterizing construction drawing recognition device.