JP3571128B2 - Method and apparatus for recognizing dimensions of drawings - Google Patents

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a method and an apparatus for recognizing dimension values in drawings having dimension information including dimension auxiliary lines, dimension lines, and dimension values, such as construction drawings such as architectural drawings and various design drawings. About.
[0002]
[Prior art]
In recent years, CAD systems and the like have been used to easily create architectural drawings of houses and buildings or construction drawings including water pipes, gas pipes, piping drawings of power / communication cables, and the like, and to store the data. It is used for design changes and extension / remodeling. However, the data of the construction drawing is not compatible due to the created system and cannot be used due to elapse of the period or change of the contractor.
In addition, when renovating or remodeling a house, there are many cases where there is only an old architectural drawing drawn on paper, and it has been necessary to redraw all parts including the floor plan of the renovation and remodeling, etc.
[0003]
Therefore, attempts have been made to read construction drawings such as architectural drawings drawn on paper and recognize and store the data as data that can be processed by a computer. The image data is read by a scanner, the image data is input to a personal computer or the like, and line segment recognition and pattern recognition are performed using a general graphic recognition function. In addition, even if the automatic recognition function is somewhat incomplete, the basic diagram such as a straight line or an arc can be obtained by performing raster-to-vector conversion even if the automatic recognition function is somewhat incomplete by using a high-performance graphic editor to assist. Some are made automatic recognition possible.
[0004]
[Problems to be solved by the invention]
However, such construction drawings and various design drawings contain a lot of dimensional information composed of auxiliary dimension lines, dimensional lines, and numerical values. This is important information indicating the actual size of each part drawn in the drawing. However, the conventional drawing recognition device could not automatically recognize this dimensional information, especially its numerical value.
Therefore, the operator manually inputs the dimension values one by one from a keyboard or the like.
[0005]
Even in the case where the numerical value is read using the OCR, it is necessary to specify each reading area in which the numerical value is described.
Therefore, when the contents of the drawing having the dimensional information are converted into a database that can be processed by a computer, there is a problem that inputting the dimensional values is complicated in the conventional technology, and an input error may occur.
[0006]
SUMMARY OF THE INVENTION The present invention has been made in view of the above points, and enables automatic and accurate recognition of dimensional values, which are important information, from image information of a drawing having dimensional information such as a construction drawing. The purpose is to:
[0007]
[Means for Solving the Problems]
In order to achieve the above object, the present invention provides a dimension numerical value recognizing method and a dimension numerical value recognizing apparatus as shown in the following drawings.
The method for recognizing the dimensions of drawings according to the present invention is as follows.For dimension value recognition deviceEnter the image information of the drawing that has the dimension information consisting of the dimension extension line, dimension line, and dimension value,Using the size numerical value recognition device, the number of black or white dots in the horizontal and vertical directions in the image of the drawing is measured to create horizontal and vertical dot number measurement array data, and the created number of dots in both directions. Analyzing the measurement array data, recognizing the portion having the characteristic of the dimension area as the dimension area, and creating and analyzing the dot number measurement array data in the recognized dimension area for the image information.Extracts each dimension extension line in the input image information, searches for the dimension line existing between the extracted dimension extension lines, and searches for the area in which the character is located with respect to the dimension line that was searched. , Dimension near the dimension line on the side where it is determined that there is a characterauxiliaryCharacter recognition processing is performed on a region between lines to recognize a numerical value.
[0008]
Further, the drawing numerical value recognition apparatus according to the present invention comprises: image information input means for inputting image information of a drawing having dimension information including a dimension auxiliary line, a dimension line, and a dimension value;The number of black or white dots in the horizontal and vertical directions in the image of the drawing is measured to create horizontal and vertical dot count measurement array data, and the created dot count measurement array data in both directions is analyzed to measure the size area. Recognize a portion having the characteristic of a size area, and create and analyze dot number measurement array data in the recognized size area for the image information.Means for extracting each dimension auxiliary line from the input image information, and dimensions extracted by the meansauxiliaryMeans for searching for a dimension line existing between the lines; means for searching in which area the character is located with respect to the searched dimension line; and means for searching for a dimension line determined to have a character by the means. Means for performing a character recognition process on an area between the auxiliary dimension lines in the vicinity to recognize a numerical value.
[0009]
Therefore, the area in which the dimension value is described can be automatically searched, and the dimension value can be reliably recognized by OCR or the like, so that the dimension value can be manually input or the reading area can be individually specified. You don't have to.
[0010]
Further, in the dimension numerical value recognition device of this drawing, the dimension data obtained by collecting the data of the dimension line that could be searched, the data of the two dimension auxiliary lines corresponding to the dimension line, and the dimension values recognized for the dimension line. It is preferable to provide a dimension list creating means for creating lists for the number of dimension lines.
As a result, the dimension value and the dimension line can be associated one-to-one.
[0011]
Further, it is preferable to provide a calculating means for calculating a dimension value related to another dimension line in the vicinity from the already recognized dimension value based on the information of the dimension list created by the dimension list creating means.
As a result, it is possible to calculate the dimension values of other dimension lines in the vicinity from the recognized dimension values without performing all the dimension values by character recognition processing such as OCR, thereby shortening the recognition time and reducing the recognition accuracy. Can be improved.
[0012]
The image information input means is:Any image reading means that reads an image of a drawing and inputs the image image information can easily recognize the numerical values of the dimensions drawn on the paper.
Further, if the image information input means is an image information receiving means for receiving and inputting the image information of the drawing by communication, the image information input means receives the image information of the drawing from another device at a remote place, and Can be easily recognized.
[0013]
Further, if a display means for displaying the recognized dimension value and the image of the input image information at the same time is provided, it is possible to easily confirm the recognition result and find erroneous recognition.
If a recognition result confirming means for confirming the recognized dimension value displayed on the display means by an external instruction is provided, the operator can confirm the recognition result and then confirm it by the instruction.
[0014]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, embodiments of the present invention will be specifically described with reference to the drawings.
FIG. 1 is a block diagram showing a schematic configuration of a dimension numerical value recognizing apparatus for carrying out the dimension numerical value recognizing method of the drawing according to the present invention, in which a hardware configuration and a function of software processing by a microcomputer are mixedly shown.
[0015]
This apparatus includes an overall control unit 1, an image reading unit 2, a communication control unit 3, a memory 4, an automatic skew correction unit 5, a dimension position recognition unit 6, a dimension list creation 7, a dimension value recognition unit 8, a display unit 9, an operation unit It comprises an input unit 10, an external storage device 11, a printing device 12, and a bus 13 for connecting them. It should be noted that an interface unit required between these units (or devices) and the bus 13 is not shown.
[0016]
The overall control unit 1 is a microcomputer (comprising a CPU, a ROM, a RAM, etc., but abbreviated as “CPU”) for controlling the operation and functions of the entire apparatus. The functions of the dimension position recognizing section 6, dimension list creating section 7, and dimension value recognizing section 8 according to the present invention can also be realized by software processing of the CPU.
[0017]
The image reading unit 2 is an image information input unit that scans a drawing having set dimension information, reads the image, and inputs image image information. The image reading unit 2 includes a scanning optical system, an image sensor such as a CCD, and a driving circuit therefor. And the like. Further, it also includes a binarization circuit which binarizes the read image image information at a predetermined resolution to obtain image data of white dots and black dots.
[0018]
The communication control unit 3 is an image information receiving unit that receives and inputs image image information or encoded image data in which the run length is encoded by communication from outside, instead of taking in image information from the image reading unit 2. At the same time, the dimensional value recognized by this device or dimensional information including the dimensional value can be transmitted to an external device. Specifically, it includes a FAX modem and personal computer communication control means.
[0019]
The memory 4 includes image image information read by the image reading unit 2, image image information or encoded image data received by the communication control unit 3, image data skew-corrected by the automatic skew correction unit 5, and a dimension position recognition unit. 6 is a large-capacity RAM or a hard disk memory for storing the dimension area recognized by 6, the information of the dimension list created by the dimension list creating means 7, the dimension value recognized by the dimension value recognition unit 8, and the like.
[0020]
The automatic skew correction unit 5 adjusts the angle of the image data stored in the memory 4 so as to correct the horizontal and vertical line segments so as to match the horizontal and vertical reference directions (X, Y directions) of the apparatus. And 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.
[0021]
The dimension position recognizing unit 6 provides an area (hereinafter, referred to as a “dimensional area”) for the image data or encoded image data that has been subjected to the automatic skew correction and stored in the memory 4, in which the dimension information in the image data exists. Is a dimension position recognizing means for recognizing the dimension, extracting a dimension auxiliary line for each dimension area, and recognizing the dimension position.
[0022]
The dimension list creating unit 7 searches for a dimension line between the dimension auxiliary lines extracted by the dimension position recognizing unit 6, and extracts data of the extracted dimension line and data of two dimension auxiliary lines corresponding to the dimension line. , Is a dimension list creating means for creating a dimension list in which dimension values (recognized by a dimension value recognition unit 8 described later) relating to the dimension line are put together.
[0023]
The dimension numerical value recognizing unit 8 searches each dimension line of the dimension list created by the dimension list creating unit for the area in which the character is located, and determines the vicinity of the dimension line determined to have the character. Is a dimension numerical value recognizing means for performing a character recognition process by OCR on an area between dimension lines to recognize a numerical value. Further, it has a function of a calculating means for calculating, based on the information of the dimension list, the dimension values related to other nearby dimension lines from the dimension values already recognized.
The details of the processing of the dimension position recognition unit 6, dimension list creation unit 7, and dimension numerical value recognition unit 8 will be described later.
[0024]
The display unit 9 receives the image data of the drawing input from the image reading unit 2 or the communication control unit 3 and skew-corrected by the automatic skew correction unit 5, the dimension area and the dimension auxiliary line recognized by the dimension position recognition unit 6, and the dimension. It is for displaying the dimension line searched by the list creation unit 7 and the dimension value recognized by the dimension value recognition unit 8, and is, for example, a CRT or a liquid crystal display. In particular, it has a function of displaying the dimension value recognized by the dimension value recognition unit 8 or the dimension information including the dimension line and the dimension auxiliary line simultaneously with the image of the input image information of the drawing.
[0025]
In this case, the recognized dimensional information and the dimensional information of the image of the input drawing image information can be displayed adjacent to each other or can be displayed in a superimposed manner.
It is preferable that the image is displayed in halftone and the dimension value of the recognition result is displayed in high contrast so that the two can be easily distinguished.
Further, when the display unit 9 is a color display device, discrimination can be improved by displaying the two images in different colors.
In addition, when the possibility of erroneous recognition of the recognized dimension value is high (predetermined value or more), it is possible to display that the possibility of erroneous recognition is high by blinking and displaying the dimension value.
[0026]
Further, the display unit 9 also displays a screen for the operator to confirm the recognition result. That is, the numerical value of the recognition result is displayed, and a display such as "Is this recognition result OK? (YES / NO)" is performed.
As a result, the operator can confirm whether or not the dimension value has been correctly recognized.
[0027]
The operation input unit 10 is for inputting various operation instructions, function selection instructions, 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, and can change the display state of the display unit 9 to a display state desired by the operator. For example, by inputting a key, the input image image of the drawing and the dimensional information of the recognition result can be superimposed and displayed, or only one of them can be selected and displayed.
[0028]
Further, the operation input unit 10 also has input means such as keys for inputting information of "YES" or "NO" in response to the display of "Is this recognition result OK? (YES / NO)". . Then, if "YES" is selected, the displayed recognition result is determined and the recognition processing is terminated, and if "NO" is selected, the processing shifts to re-recognition processing or correction processing. Thereby, the operator can confirm the content of the recognition result and determine it.
[0029]
The operation input unit 10 is provided with a mouse as a pointing device, and the auxiliary dimension line and the dimension line of the input image image of the drawing displayed on the display unit 9 are traced with a mouse cursor to thereby obtain the auxiliary dimension line and the dimension line. It is also possible to provide a function for inputting the position information of the user.
[0030]
The external storage device 11 sends the dimension values recognized by the dimension value recognition unit 8 and information of the dimension list created by the dimension list creation unit 7 to an external device such as a floppy disk (FD) or a magneto-optical disk (OMD). This is a storage device for storing in a removable storage medium.
The printing device 12 is a printer or a plotter that prints or draws an input image image of a drawing or recognized dimensional information on paper and outputs it.
[0031]
Here, the dimension information of the drawingaboutexplain. In general, a description indicating a length, a size, a position, an angle, and the like on a drawing is dimensional information. In construction drawings (mainly architectural drawings), dimensional information indicating the length is usually represented by a combination of dimensional figures as shown in FIG. That is, a dimension line is drawn in a direction perpendicular to the two dimension auxiliary lines drawn from both ends of a portion for which the dimension of the target graphic is to be indicated, and the dimension numerical value is described in a central portion above the auxiliary line. . That is, the dimension value and the dimension line correspond one-to-one.
[0032]
FIG. 2A shows an example in which the dimension information is arranged above the figure, and FIG. 2B shows an example in which the dimension information is arranged below the figure. Both differ in the position of the dimension line with respect to the dimension extension line, but in both cases the dimension value is above the dimension line (the right side if the dimension line is vertical), and the one closer to the dimension line is below the number . However, in some cases, the dimension value may be described below the dimension line (left side when the dimension line is vertical).
[0033]
FIG. 3 is a display example in which a long dimension is divided into a plurality of portions to show individual dimensions. When the dimension information shown in FIG. 3A is decomposed, it becomes as shown in FIG.
FIG. 4 shows an example of a floor plan of an architectural drawing having actual dimensional information.
[0034]
Next, a procedure of a process of recognizing dimension values of a construction drawing (mainly an architectural drawing of a house, a building or the like) by the dimension value recognizing device of the drawing shown in FIG. 1 will be described with reference to the flowcharts of FIGS. In the flowchart of FIG. 5, each step is indicated by “S”. In the example described here, the construction drawing to be recognized is a positive drawing.
[0035]
FIG. 5 shows a main routine of a process relating to the present invention by the overall control unit (CPU) 1 of the apparatus for recognizing dimensions of construction drawings according to the present invention.
First, in step 1, an image of a construction drawing set in the image reading unit 2 is read, and binary image data is input and stored in an image data storage area of the memory 4. Alternatively, the image data (image image data or encoded image data obtained by encoding the run length thereof) of the construction drawing may be received and input from outside by the communication control unit 3.
[0036]
In step 2, the automatic skew correction unit 5 corrects the input image data stored in the memory 4 so that the horizontal and vertical line segment directions coincide with the horizontal and vertical reference directions (X and Y directions) of the apparatus. This is performed in order to improve the recognition accuracy in the subsequent dimension information recognition processing in steps 3 and 4. This automatic skew correction may be performed by some conventionally known methods, and a detailed description thereof will be omitted.
[0037]
Next, the process proceeds to a subroutine of step 3, in which a dimension area recognition process is performed on the entire image data on which automatic skew correction has been performed. This process is a process of determining an area where dimension information exists in the input construction drawing image data (referred to as “dimension area”).StepsThis is performed by the dimension position recognizing unit 6 in FIG. 1 together with the dimension auxiliary line extraction processing in 4, which will be described later in detail.
[0038]
When the dimension area is determined after the dimension area recognition processing, the process proceeds to the subroutine of step 4 to execute the dimension auxiliary line extraction processing. This process is a process for extracting only the dimension auxiliary line existing there as shown in FIG. 7 for each dimension area determined in the process of step 3, and the details will be described later.
[0039]
When the recognition of the dimension lines of all the dimension areas is completed, the process proceeds to step 5, where the dimension list creating section 7 searches for dimensions and creates a dimension list. That is, as shown in FIG. 8, a dimension line b existing between a pair of dimension auxiliary lines aa is searched. In this search, by scanning (scanning) the inside of each dimension area recognized in step 3, a black dot row having a predetermined length or more that is continuous in a direction orthogonal to the dimension auxiliary line is set as a dimension line candidate, and both ends thereof are set. Searches for what touches the dimension extension line.
[0040]
Then, a dimension list is created by combining the searched dimension line and two corresponding dimension auxiliary lines. This dimension list contains dimension values that you will recognize later.Tocombine.
This process is repeated until the search for the dimension line is completed. When the search is completed, the process proceeds to step 7, where the dimension value recognition unit 8 performs the dimension value recognition process. This process is a process of recognizing a dimension value for each dimension line of the dimension list created in step 5 and adding it to the dimension list, the details of which will be described later with reference to FIG.
[0041]
In step 8, the dimensional value of the recognition result may be displayed on the display unit 9, or all dimensional information including the dimension line and the dimension auxiliary line may be displayed.
Then, it is determined whether or not to be determined in step 9, that is, whether or not the determination key of the operation input unit 10 has been pressed (or an instruction using a mouse cursor may be performed).StepsThe process proceeds to step 10, where the recognition result at that time is determined, stored in the determined recognition result storage area of the memory 4, and the processing ends.
[0042]
If the confirmation key is not pressed in step 9, it is determined in step 11 whether or not the recognition result is to be corrected, that is, whether or not the correction input selection key has been pressed (or may be indicated by a mouse cursor). In step 13, a screen for correction input including the image image of the construction drawing input on the display unit 9 is displayed. When the operator inputs correction data (including numerical values, etc.) (including addition, correction, and deletion) by using the operation input unit 10, the correction data is stored in the memory 4, and the correction result is displayed at step 8 on the display unit. 9 is displayed. Until the correction is completed, the processing of steps 8, 9, 11, 13, 14, 11 is repeated.
[0043]
If it is determined in step 11 that the correction is not to be made, it is determined in step 12 whether reprocessing is to be performed (whether a reprocessing instruction is given). The processing from area recognition processing to step 10 or 14 is repeated.StepsIf no reprocessing instruction is given in step 12 (a termination instruction is given or a predetermined time has elapsed without giving any instruction), the processing ends.
[0044]
Although not shown in this flowchart, the determined recognition result is stored in the storage medium of the external storage device 11 in FIG. 1, printed on paper by the printing device 12, or transmitted from the communication control unit 3 to the host computer or the like. Can also be sent to
[0045]
Next, details of the dimension numerical value recognition processing in step 7 of FIG. 5 will be described with reference to the flowchart of FIG.
When this processing is started, an area U above the center of the dimension line b is cut out as shown in FIG. 9 for each dimension line in the dimension list, and a scan is performed to determine whether or not there is a character image. Whether or not there is a character image is determined based on whether or not black dots are densely packed at a predetermined density. If the density is equal to or less than the predetermined density, it is determined to be noise (garbage).
[0046]
If there is no character image, an area L below the center of the dimension line b is cut out as shown in FIG. 9, and a scan is performed to determine whether a character image is present there. If there is no character image there, an error message is displayed on the display unit 9 and the process ends. The content of the error message is, for example, "The numerical value cannot be recognized. Check the original image for the numerical value." There are actual numbers, but they could not be recognizedin case of,The correction input can be made in step 14 and the like in FIG.
[0047]
When there is a character image in either the area U above the dimension line or the area L below the dimension line, as shown in FIG. 10, the vicinity of the dimension line b on that side (preset width) OCR is applied to the region S between the pair of dimension auxiliary lines aa to recognize a character string (character code).
[0048]
The recognized character string is converted into a numerical value and stored as the numerical value of the corresponding dimension line in the dimension list.
The above processing is repeated until OCR is applied to the area S of all the dimension lines in the dimension list, and when the processing is completed, the process returns to the main routine of FIG.
[0049]
Next, the dimension area recognition processing in step 3 and the dimension auxiliary line extraction processing in step 4 in the main routine of FIG. 5 will be described.
First, a flowchart of the subroutine of the dimension area recognition processing is shown in FIG.Steps(B) to (f) on the right side of FIG. FIG. 11B is a simplified illustration of image data (construction drawing data) of a construction drawing that has been input and skew-corrected.
[0050]
For this image data, first, in step 21, the number of black dots in the horizontal direction (X direction) is measured for each dot line, and the horizontal dot number measurement array data, that is, as shown in FIG. Create a horizontal dot histogram for the entire drawing.
The number of black dots is counted when the construction drawing read is a positive drawing (a drawing whose brightness is lower than the ground brightness), and when the construction drawing is a negative drawing (a drawing whose brightness is higher than the ground brightness). Measure the number of white dots.
[0051]
AndStepsIn step 22, a search is made for a portion where the characteristics of the size area can be seen from the black dot number measurement array. Then, the range in which this feature is seen is set as a temporary dimension area (horizontal direction) as shown by halftone dots in (d).
[0052]
These processes will be further described with reference to FIG.Of FIG.(A) shows a configuration example of the dimension data, which is composed of a plurality of lead lines a, a plurality of dimension lines b, and a dimension letter c. Although the inner end of the lead line a may be in contact with the building or may be separated therefrom, there are a plurality of dimension lines b near the outer end part that are separated from the building to some extent and are parallel at substantially constant intervals, The line width is thin. This dimension line extends horizontally at the top or bottom of the building and vertically at the right or left side. The illustrated example is on the upper side and extends in the horizontal direction.
[0053]
Therefore, the dot histogram which is the array of the number of black dots in the horizontal direction of the dimension data is as shown in FIG.
That is, a plurality of portions B in which long lines indicating that the number of black dots (the number of black runs) is extremely large are concentrated at a substantially constant interval in a narrow range in the Y direction. This is due to the dimension line b. In A, a short line indicating that the number of black dots is extremely small is a portion formed by a leader line and closely appears in the Y direction and appears as a thick line in the vertical direction. C is a dimension character portion, and a number of relatively short lines appear adjacent to each other in the Y direction between the portions of B.
[0054]
These are the characteristics of the dimension area. Therefore, by scanning this dot histogram, a range of the width W from the outermost long linear B portion to the predetermined width d set in advance on the building side from the innermost B portion is temporarily determined. Dimension area.
[0055]
Returning to FIG. 11, in step 23, the array data of the number of black dots measured in the vertical direction, that is, the vertical dot histogram of the entire drawing is created. Then, in step 24, by performing the same processing as in the horizontal direction in step 22, a portion where the characteristic of the size area is seen is searched from the black dot number measurement array, and the range is shown by adding halftone dots to (e). Is a temporary dimension area (vertical direction).
[0056]
Then, in the final step 25, the temporary dimension areas in the vertical and horizontal directions are synthesized, and each area outside the area where the two areas overlap with each other is deleted, and as shown in FIG. Is determined by recognizing various dimensional areas. In this example, there are four dimension areas located at the top, bottom, left, and right of the building. The coordinate data of the four corners of each dimension area is stored in a memory. Thereafter, the process returns to the main routine of FIG.
[0057]
Next, FIG. 13 shows a flowchart of a subroutine of the dimension auxiliary line extraction processing in step 4 of FIG. 5, which will be described with reference to FIGS.
When the dimension auxiliary line extraction processing shown in FIG. 13 is started, first, in step 31, coordinate data of the four dimension areas recognized earlier is read in order.
[0058]
StepsAt 32, the position of the read dimension area with respect to the building is determined.
If the discrimination result is left or right, the process proceeds to step 33, where the horizontal black dot number measurement array data is created based on the image data in the size area. If the result of the determination is upward or downward, the process proceeds to step 34, where the vertical black dot number measurement array data is created based on the image data in the size area.
[0059]
For example, as shown in FIG. 14, when the horizontal black dot number measurement array data in the left dimension area 21 is created for the image 20 of the building in the image data, the black dot number measurement array as shown in FIG. (Dot histogram) is obtained. In this black dot number measurement array, a narrow peak appears at a certain position of each dimension auxiliary line.
[0060]
ThereforeStepsIn step 35, the black dot number measurement array is scanned to detect the width of the line where the number of black dots is equal to or greater than the threshold value and the peak value of the number of black dots between them. The scanning direction is the Y direction (vertical direction) for the horizontal black dot number measurement array, and the X direction (horizontal direction) for the vertical black dot number measurement array.
[0061]
Then, as shown in FIG. 16, for example, as shown in FIG. 16, scanning is performed in the Y direction with respect to the horizontal black dot number measurement array. The width D and the peak value of the number of black dots therebetween (the number of black dots on the second detected line in the illustrated example) are detected and stored.
[0062]
When the width D is detected, that is, when the number of black dots is equal to or more than the threshold value and the line cannot be detected for the first time (line where the number of black dots is less than the threshold value is scanned), When the scanning for the black dot number measurement array in the size area is completed, the process proceeds to step S36.
[0063]
In this case, it is determined whether or not there is a line in which the number of black dots is equal to or larger than the threshold value. If there is, the process proceeds to step 37, where the width (D shown in FIG. 5 or less, and set to 1/10 or less). If it is narrow, it is determined to be a dimension auxiliary line, and the X coordinate (when scanning in the X direction) or the Y coordinate (when scanning in the Y direction) is added to the dimension auxiliary line information list in the memory 4 in step 38.
[0064]
For example, in the case of the left and right dimension areas, the Y-direction scanning position of the midpoint P of the width (the range in which the number of black dots in the array is greater than or equal to the threshold) D shown in FIG. Let it be the Y coordinate. In the case of the upper and lower dimension areas, the X-direction scanning position at the same midpoint of the width D is set as the X coordinate of the dimension auxiliary line.
[0065]
Thereafter, the process proceeds to step 39 in FIG. 13 to determine whether or not the scanning for the black dot number measurement array in one dimension area has been completed. If not completed, the process returns to step 35 to repeat the subsequent processing. When you finish scanningStepsProceed to 40 to determine whether or not the dimension auxiliary line extraction processing for all dimension areas has been completed.StepsReturning to 31, the coordinate data of the next dimension area is read, and the above processing is repeated.
[0066]
When the dimension auxiliary line extraction processing is completed for all dimension areas of the building, up, down, left and right, the process exits this subroutine and returns to the main routine of FIG.
According to this method, it is possible to recognize the coordinates of the point indicated by the dimension line of almost 100% with a simple algorithm. In addition, the processing speed is faster than the contour extraction and thinning processing. A3 drawing can be extracted within one second.
[0067]
Furthermore, since the analysis is performed by using the dot histogram, it is resistant to noise and blur, and the coordinate data of the dimension auxiliary line can be acquired with high accuracy. Further, since the memory usage increases only one-dimensionally even if the drawing becomes large, for example, about 6 Kbytes for the A4 drawing and about 24 Kbytes for the A0 drawing.
[0068]
Here, with respect to a floor plan of a house, which is an actual architectural drawing, a specific example of the above-described dimension area recognition processing and dimension auxiliary line extraction processing will be described with reference to FIGS.
FIG. 17 is image image data obtained by reading a floor plan of a house.
In order to perform the dimension area recognition process on the image data, the number of black dots in the horizontal and vertical directions is counted, and the horizontal black dot number measurement array data shown in FIG. ), Black dot number measurement array data (dot histogram) in the vertical direction is created.
[0069]
From the horizontal and vertical black dot count measurement array data, a portion where the feature of the dimension area is found is searched, and the dimension area (dimension information exists) indicated by hatching the image image data in FIG. Range). In this example, there are dimension areas at four locations, up, down, left, and right with respect to the image of the building.
[0070]
As shown in FIG. 19, each of the image data in the left and right dimension areas of the building has the number of black dots in the horizontal direction. The measurement array data is created, and the vertical direction black dot number measurement array data is created for each image data in the upper and lower dimension areas of the building.
[0071]
Then, as shown in the vertical black dot number measurement array of the one dimension area in FIG. 20, the center point of each part where the black run whose black dot number is equal to or more than the threshold exists with a sufficiently narrow width with respect to the peak. Are recognized as the X coordinate of the dimension auxiliary line (Y coordinate in the case of the array of black dots in the horizontal direction) and stored in the dimension auxiliary line information list.
[0072]
The additional function of the dimension numerical value recognition unit 8 in FIG. 1 uses the recognized dimension numerical values stored in the dimension list and the position data of the dimension line and the dimension auxiliary line to relate to other dimension lines in the vicinity. Calculate dimensionsThereforeYou can also ask.
The dimension list is created in the memory 4 for each area obtained by two dimension auxiliary lines. An example of a method of calculating a dimension value will be described with reference to FIG.
[0073]
First, the dimension value “1000” related to the dimension lines A and B is"1500", And then add them to calculate (1000 + 1500 = 2500) as a dimension value related to the dimension line C.
Furthermore, after performing the OCR on the area corresponding to the dimension line C, the numerical value of the dimension line C may be determined by comparing the result with the calculation result. After performing all the OCR on the area of the dimension line, the calculation is performed by this calculation method.Display, The operator can confirm it.
[0074]
FIG. 22 shows a display example of the recognized dimension values. By displaying the recognized dimension values (enclosed in a frame) as close to the original image as possible (up, down, left and right), comparison can be facilitated.
[0075]
【The invention's effect】
As described above, according to the method and apparatus for recognizing dimensional values of drawings according to the present invention, dimensional values, which are important information, can be accurately and rapidly obtained from image information of drawings having dimensional information such as construction drawings. Can be automatically recognized.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a schematic configuration of an apparatus for implementing a method of recognizing dimensions and numerical values in the drawings according to the present invention.
FIG. 2 is a diagram showing a description example of dimension information in a construction drawing.
FIG. 3 is a diagram showing an example of the division of the dimensions.
[Fig. 4] Dimension informationHavingIt is a figure which shows the example of a construction drawing.
FIG. 5 is a flowchart of a main routine of a process related to recognition of a numerical value of a drawing by the apparatus shown in FIG. 1;
FIG. 6 is a flowchart of a subroutine of a dimension numerical value recognition process in step 7 in FIG. 5;
FIG. 7 is an explanatory diagram of dimension extraction line extraction.
FIG. 8 is an explanatory diagram of a dimension line search.
FIG. 9 is an explanatory diagram of an area for checking which side of a dimension line has a character image.
FIG. 10 is an explanatory diagram of an area for performing character recognition (OCR).
11 is a diagram showing a correspondence between a flow of a subroutine of a dimension area recognition process of step 3 in FIG. 5 and a diagram provided for explaining each step thereof.
FIG. 12 is an explanatory diagram for explaining the size area recognition process.
FIG. 13 is a flowchart of a subroutine of a dimension auxiliary line extraction process in step 4 in FIG. 5;
FIG. 14 is a diagram showing an example of a building image and a size area in input image data of a construction drawing.
FIG. 15 is a diagram illustrating a horizontal black dot number measurement array in the dimension area of FIG. 9;
FIG. 16 is an enlarged view for explaining a process of recognizing a dimension auxiliary line from the black dot number measurement array.
FIG. 17 is a diagram showing image image data obtained by reading an actual architectural drawing, and black dot number measurement array data in the horizontal and vertical directions for the image data.
18 is a diagram illustrating an example in which a size area is determined using the black dot number measurement array data in the horizontal and vertical directions in FIG.
19 is a diagram in which, for each dimension area in FIG. 18, black dot number measurement array data in the horizontal or vertical direction is created based on image data inside the area.
FIG. 20 is a diagram showing the relationship between the arrangement of the number of black dots measured in the vertical direction in one dimension area and the threshold value for extracting a dimension auxiliary line.
FIG. 21 is an explanatory diagram of an example in which a numerical value is obtained by calculation.
FIG. 22 is a diagram showing a display example of recognized dimension values.
[Explanation of symbols]
1: Overall control unit (CPU) 2: Image reading unit
3: Communication control unit 4: Memory
5: Automatic skew correction unit
6: Dimension position recognition unit 7: Dimension list creation unit
8: Dimension numerical value recognition part 9: Display part
10: operation input unit 11: external storage device
12: Printing device 13: Bus
20: Building image 21: Dimension area

Claims (8)

Extension line to the dimension numerical recognizer, dimension line, and inputs image information of the drawing with dimensional information consisting of dimension numbers, using the dimensions numerical recognizer, black horizontal and vertical directions in the image of the drawing Or, measure the number of white dots, create horizontal and vertical dot count measurement array data, analyze the created dot count measurement array data in both directions, recognize the part having the characteristics of the dimension area as the dimension area, For the image information, create and analyze the number-of-dots measurement array data in the recognized dimension area, extract each dimension auxiliary line in the input image information, and extract the dimension line existing between the extracted dimension auxiliary lines. Searches, searches the dimension line on which side the character is located, and performs character recognition processing on the area between the dimension auxiliary lines in the vicinity of the dimension line determined to have the character. Do Dimensions numeric recognition method drawing and recognizes the size numeric Te. Extension line, dimension line, and an image information input means for inputting image information of the drawing with dimensional information consisting of size numeric, horizontal to measure the number of black or white dots horizontally and vertically in an image of the drawing And creating the dot number measurement array data in the vertical direction, analyzing the created dot number measurement array data in both directions, recognizing a portion having the characteristic of the dimension area as a dimension area, and recognizing the dimension area with respect to the image information. Means for extracting and analyzing each dimension-assisting line from the input image information by creating and analyzing the number-of-dots-measuring array data, and searching for a dimension line existing between the dimension- assisting lines extracted by the means. Means, a means for searching in which side of the dimension line the character is located, and an area between the dimension auxiliary lines near the dimension line on which the character is determined to be located by the means. Dimensions numerical recognizer drawings is characterized in that a means for recognizing the size numeric by performing character recognition processing for. 3. The apparatus for recognizing dimension values of a drawing according to claim 2, which collects data of a dimension line which can be searched, data of two auxiliary dimension lines corresponding to the dimension line, and dimension values recognized for the dimension line. A dimension list creating means for creating a number of dimension lists corresponding to the number of dimension lines. 4. The dimension numerical value recognition device of the drawing according to claim 3, wherein a dimension numerical value related to another dimension line in the vicinity is calculated from the dimension numerical value already recognized based on information of the dimension list created by the dimension list creating means. Dimension numerical value recognizing means provided with a calculating means. 5. The apparatus according to claim 2, wherein the image information input unit is an image reading unit that reads an image of the drawing and inputs the image image information. 6. 5. The apparatus according to claim 2, wherein the image information input unit is an image information receiving unit that receives and inputs image information of the drawing by communication. 6. 7. The dimensional numerical value recognition device according to claim 2, further comprising a display unit for displaying the recognized dimensional numerical value simultaneously with an image of the input image information. Recognition device. 8. The apparatus according to claim 7, further comprising a recognition result confirming means for confirming the recognized dimension value displayed on said display means by an external instruction. .

Images