JPH04260980A - Device for recognizing graphic - Google Patents

Abstract

PURPOSE:To correctly detect an objective graphic even at the time of inputting a drawing on which other elements such as characters are written on a graphic element with contact. CONSTITUTION:This graphic recognizing device is provided with a basic graphic detecting means 51 for detecting a basic graphic to be used for objective graphics in common, a linear graphic segmenting means 52 for segmenting a linear graphic from which the basic graphic is removed, a graphic feature variable defining means 8 for defining the graphic feature variable of a graphic element to be added to the basic graphic, a graphic element discriminating means 71 for calculating the graphic feature variable of the linear graphic segmented by the means 52, collating the calculated value with a graphic feature variable defined by the means 8 and discriminating the sort of the graphic element, and a graphic discriminating means 72 for discriminating the graphic based upon the detected basic graphic and the graphic element added to the basic element.

Description

[Detailed description of the invention]

0001

[Field of Industrial Application] This invention relates to a figure recognition device that detects a specific figure in a drawing and determines its type in order to automatically input information written on the drawing into a computer, etc. It is.

0002

2. Description of the Related Art FIG. 13 is a block diagram of a conventional figure recognition device, which is shown, for example, in the Information Processing Society of Japan's 37th National Conference Proceedings 1W-1 (page 1598). In the figure,
1 is an image input means for inputting a drawing as an image and obtains binary digital image data; 2 is a binary data storage means for storing the input binary image data; 3 is a binary data storage means 2 Input the image data stored in
Point sequence forming means for creating point sequence data indicating the center coordinates of lines forming a figure; 4 is a point sequence data storage means for storing the point sequence data created by the point sequence forming means 3; 5 is a point sequence data storage Figure detection means inputs the point sequence data stored in the means 4 and detects a specific target figure; 6 is a figure storage means that stores data of the target figure detected by the figure detection means 5; 7 is a figure memory This figure determining means inputs the figure data stored by the means 6 and determines the type of figure.

The conventional figure recognition device is constructed as described above. When a drawing as shown in FIG. 2 is input to the image input means 1, the image input means 1 converts it into binary digital image data. The converted data is stored in the converted data storage means 2. The point string forming means 3 thins the line having the width of the above-mentioned image data stored in the binarized data storage means 2 to form a line with a width of one pixel, thereby forming end points and branching points. Point sequence data is created for each line from feature point to feature point, and is stored in the point sequence data storage means 4. The figure detection means 5 detects lines forming a loop and lines having end points, and stores a collection of these lines in the figure storage means 6 as a target figure. The figure determining means 7 calculates figure feature quantities such as the number of loops and the number of end points for the target figure stored in the figure storage means 6, and determines the type of figure based on the feature quantities.

0004

[Problem to be Solved by the Invention] Since the conventional figure recognition device is configured as described above, when a line constituting a target figure is written in contact with a line constituting a character, it is difficult to detect the figure. Since the method detects the lines that make up the character as being included in the target figure, the figure determination means may incorrectly calculate the feature quantities such as the number of loops and end points, and therefore incorrectly determine the type of figure. There was a problem with this.

[0005] This invention was made to solve the above-mentioned problems, and it is not possible to correctly detect a figure and determine its type even if another element such as a character comes into contact with the target figure. The purpose is to obtain a figure recognition device that can.

[0006]

[Means for Solving the Problems] A figure recognition device according to a first aspect of the present invention defines a plurality of types of basic figures that are commonly used for a target figure among predetermined figure elements constituting the target figure. basic figure defining means for storing the basic figures in the point sequence data storage means; basic figure detecting means for detecting the basic figures based on the point sequence data stored in the point sequence data storage means; A line figure cutting means that cuts out a line figure based on an arbitrary combination of lines, and a figure that defines a discrimination tolerance value of figure features for figure elements added to that basic figure, which is determined for each basic figure. The feature definition means calculates the figure feature of the line figure cut out by the line figure cutting means, and compares this with the discrimination tolerance value of the figure feature defined in the figure feature definition means to determine the basic figure. A graphical element determining means for determining the type of a graphical element added to the object, and a graphical determining means for determining the type of the target graphic based on the detected basic graphic and the determination result of the type of the graphical element. .

[0007]Furthermore, the figure recognition device according to the second invention includes:
A basic figure detection means for detecting a basic figure that fits a predetermined rule; and a line figure cutting means for cutting out some line figures based on an arbitrary combination of lines from the detected basic figures. , a figure feature definition means for defining the figure feature of a basic figure; the figure feature of this basic figure; and a figure feature of several line figures cut out by the line figure cutting means, calculated and compared. By doing so,
The present invention is characterized in that it includes a figure determining means for specifying a figure.

[0008]

[Operation] The basic figure detecting means in the first invention detects a basic figure constituting a part of the target figure from point sequence data. The line figure stamp cutting means cuts out some line figures from the line figures remaining after removing the basic figure detected from the target figure, based on the combination of lines forming the line figure. The graphic element determination means determines, for each cut out line figure,
The graphic feature amount is calculated, and the type of the graphic element added to the basic graphic is determined by comparing it with the discrimination tolerance value of the graphic feature amount of the graphic element defined by the graphic feature amount definition means. Then, the basic figure and the graphic elements added to the basic figure are combined by the figure determining means to specify the figure.

Further, the basic figure detecting means in the second invention detects a basic figure that meets predetermined specifications as a basic figure, but at this point it has not yet been determined that it is a basic figure. Therefore, the line figure cutting means cuts out some basic figure candidates by arbitrarily combining the lines constituting the detected basic figures. Since the feature values of the basic figure are defined by the figure feature value definition means, the figure determination means selects the true basic figure from among these several basic figure candidates by comparing and matching these feature values. do.

0010

DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the first invention will be described below with reference to the drawings. FIG. 1 is an overall configuration diagram showing an embodiment of the present invention. In the figure, 1 to 4 are the same components as the conventional device, and 9 is a basic figure that defines and stores basic figures that are commonly used within the target figure. Defining means 51 is a basic figure detection means for detecting basic figures constituting the target figure from point sequence data; 61 is a basic figure storage means for storing detected basic figure data; 52 is a basic figure detected from the target figure. Line figure cutting means for cutting out line figures based on any combination of lines from line figures excluding figures; 62 is a line figure storage means for storing cut out line figures; 8 is added to basic figures; 71 calculates the graphic feature of the line figure stored in the line figure storage means 62, and calculates the figure feature of the line figure stored in the line figure storage means 62; A figure element determining means 72 determines the type of a figure element added to a basic figure by comparing it with the discrimination tolerance value of the figure feature defined in 8; It is a figure determining means that determines the type of target figure based on the determination result.

Next, the operation of the above embodiment will be explained. First, when a drawing as shown in FIG. 2 is input using the image input means 1, binary digital image data is created.
It is stored in the binarized data storage means 2. The point string forming means 3 thins the line having the width of the above-mentioned image data stored in the binarized data storage means 2 to form a line with a width of one pixel, thereby forming end points and branching points. Point sequence data is created for each line from feature point to feature point, and is stored in the point sequence data storage means 4.

The basic figure detecting means 51 detects a basic figure based on the point sequence data while referring to the basic figure defined by the basic figure defining means 9. FIG. 3 is a diagram showing an example of a basic figure and a figure to be recognized including the basic figure, and FIG. 4 is a diagram illustrating a method for detecting the basic figures (a), (b), and (c). Using these, the operation of the basic figure detection means 51 will be explained in detail.

First, lines having a connection relationship are sequentially traced in point sequence data to detect closed loops. Next, for each detected closed loop, the vertical and horizontal lengths of the circumscribed rectangle and the number of pixels in the sequence of points constituting the closed loop (this is defined as the loop length) are determined. The basic figures (b) and (c) are detected by finding the circumscribed rectangle whose vertical and horizontal lengths and loop length are within a predetermined range stored by the basic figure definition means 9. . Basic shapes (
a) is a rectangle whose vertical and horizontal lengths and loop lengths are within the predetermined range stored by the basic figure definition 9, and for any combination of the two, 2 It is detected by finding the distance d between two circumscribed rectangles that is less than or equal to a certain length. In the basic figure (a), a vertical line between two closed loops is also detected. The basic figure data detected in this way is stored in the basic figure storage means 61.

Next, based on the basic figure data, the line figure cutting means 52 cuts out a line figure based on an arbitrary combination of lines from the remaining line figure after removing the basic figures from the target figure. . FIG. 5 shows an example of a line figure cut out in this way. In the figure, (a) is the figure to be recognized;
(a) is a line figure that remains after removing the basic figure from the figure to be recognized, and (1) to (2) are line figures cut out from the line figure of (a) based on an arbitrary combination of lines. The cut out line figure is stored in the line figure storage means 62.

On the other hand, the figure feature definition means 8 determines the figure features, such as the number of feature points, the number of lines, and the length of each line, for each basic figure and the figure elements added to the basic figure. Tolerances are defined. FIG. 6 shows the graphic feature definition means 8
FIG. 3 is a diagram showing graphic elements for which discrimination tolerance values of graphic feature amounts are defined.

The graphic element determination means 71 calculates graphic feature quantities such as the number of features, the number of lines, and the length of each line for each line figure stored in the line figure storage means 62, and The figure feature quantity defined in the feature quantity definition means 8 is compared with the discrimination tolerance value, and the type of the figure element added to the basic figure is determined. FIG. 7 shows the result of determining the type of graphic element of the line figure cut out from the recognition target figure in FIG. 5 by the graphic element determining means 71. In the figure, an x mark indicates a failed match, and an ○ mark indicates a successful match. That is, since only the line figure ■ and the figure element (A) have been successfully matched, it is determined that the figure element added to the basic figure is (A).

Finally, the figure determining means 72 finalizes the type of figure to be recognized based on the result of the determination of the type of the basic figure detected above and the type of figure element added to the basic figure. As a result of the above, among the figures shown in recognition target (a) in FIG. 5, the one finally determined by the figure determination means is the predetermined figure, and the other parts can be determined to be characters. Become. In this example, since the remaining part has the shape C, it can be determined that this is the letter C. In particular, according to the first invention, the basic figure is first removed and other elements such as characters are added to the figure element in order to determine the figure element to be added to the basic figure from the remaining line figures. This makes it easier to distinguish between cases.

Next, a figure recognition device according to a second invention will be explained. In the above-mentioned embodiment of the first invention, a means for cutting out a line figure based on an arbitrary combination of lines from a line figure obtained by removing basic figures detected from the target figure is used as the line figure cutting means. However, a similar operation can be expected by using means for cutting out line figures from the detected basic figures based on any combination of lines that constitute the basic figure.

FIG. 8 is a diagram showing an embodiment of the second invention, and 1 to 4 are similar to FIG. 1. FIG. 9 is an input drawing in which the figure to be recognized is written, and FIG. 10 is a diagram showing the figure to be recognized. For each figure (A), (B), and (C),
The graphic feature definition means 8 defines a discrimination tolerance value for the graphic feature. Further, here, we consider a case where the rules for recognizing basic figures that are commonly used as recognition target figures are closed loops with a fixed size range.

The basic figure detection means 51 detects a closed loop having a fixed size range as a basic figure from among the line figures created for the drawing of FIG. Line figure cutting means 5
2 is the line figure that constitutes the detected closed loop.
Cut out a line figure based on an arbitrary combination of lines. However, at this time, since all the figures to be recognized are closed loops, the line figures to be cut out are limited to closed loops. FIG. 11 shows an example of a detected basic figure and a line figure cut out from it.

The figure determining means 72 calculates the figure feature amount for the cut out line figure, and calculates the figure feature quantity for each figure (A), (B), (C) defined in the figure feature quantity defining means 8. The type of figure is determined by comparing the figure feature amount with the discrimination tolerance value. FIG. 12 shows the result of determining the type of a line figure cut out from the basic figure shown in FIG. 11 by the figure determining means 72. That is, the type of figure is determined to be (A).

[0022] In the above embodiment, the basic figure detecting means used the rule "closed loop with a fixed size range" to detect the basic figures, but in addition to this, the following rules were used: It may be. "Closed loop with loop length within a certain range""Figure whose circumscribed rectangle area is within a certain range""
A figure whose circumscribing rectangle has a certain length or width, a figure with a certain number of endpoints or more, a figure with no endpoints, a figure with or without a branch point, and of course,
Rules or specifications other than these may be used. Furthermore, a combination of these rules and specifications may be used.

As described above, according to the second invention, by using means for cutting out a line figure based on an arbitrary combination of lines from among the detected basic figures as the line figure cutting means, basic figures can be cut out based on an arbitrary combination of lines. Even in drawings where other elements such as characters are in contact with shapes, the target shape can be detected correctly.
It has the effect of determining its type.

[0024]

[Effects of the Invention] As described above, according to the present invention, since the basic figure or the figure element added to the basic figure is determined first, other elements such as characters come into contact with the basic figure or the figure element. Even if you input a drawing written in

[Brief explanation of the drawing]

FIG. 1 is an overall configuration diagram showing a figure recognition device which is an embodiment of the first invention.

FIG. 2 is a diagram showing an example of a drawing to be recognized.

FIG. 3 is a diagram showing examples of basic figures and examples of recognition target figures corresponding to each basic figure.

FIG. 4 is an explanatory diagram of a basic figure detection method.

FIG. 5 is a diagram showing an example of a line figure cut out from a part of the recognition target figure excluding the basic figure.

FIG. 6 is a diagram illustrating an example of a graphic element for which a discrimination tolerance value of a graphic feature is defined.

FIG. 7 is a diagram showing the result of determining the type of graphic element for the cut out line figure.

FIG. 8 is an overall configuration diagram showing a figure recognition device that is an embodiment of the second invention.

FIG. 9 is a diagram showing an example of a drawing to be recognized.

FIG. 10 is a diagram showing an example of a figure to be recognized.

FIG. 11 is a diagram showing an example of a line figure cut out from a basic figure.

FIG. 12 is a diagram showing the result of determining the type of a cut out line figure.

FIG. 13 is a configuration diagram of a conventional figure recognition device.

[Explanation of symbols]

1 Image input means 2 Binarized data storage means 3. Point array means 4 Point sequence data storage means 51 Basic figure detection means 52 Line figure cutting means 61 Basic figure storage means 62 Line figure storage means 71 Graphic element determination means 72 Figure determination means 8 Graphic feature definition means 9 Basic figure definition means

Claims (2)

[Claims] Claim 1: A figure recognition device (a
) image input means for inputting an image and creating binary image data; (b) point sequence generating means for creating point sequence data of lines forming a figure based on the input image data; (c) recognition. (d) A basic figure definition means that defines and stores basic figures that are commonly used for target figures; basic figure detection means for detecting the basic figure detected by the basic figure detection means; (e) line figure cutting means for cutting out the remaining line figure excluding the basic figure detected by the basic figure detection means from the line figure; (f) basic figure (g) a figure feature definition means for defining and storing the figure feature of the figure element to be used; (g) a figure feature definition means for calculating the figure feature of the line figure cut out by the line figure cutting means; (h) determining a figure from the basic figure detected by the basic figure detection means and the figure element determined by the figure element judgment means; figure determination means. Claim 2: A figure recognition device (a) comprising the following elements:
) image input means for inputting an image and creating binary image data; (b) point sequence generating means for creating point sequence data of lines forming a figure based on the input image data; (c) points. basic figure detection means for detecting, from among line figures constituted by column data, those that meet a predetermined rule as basic figures commonly used in recognition target figures; (d) lines constituting the detected basic figures; (e) a figure feature defining means for defining and storing figure features of basic figures commonly used for recognition target figures; (f) ) Calculate the figure feature amount for the line figure cut out by the line figure cutter, and compare this with the discrimination tolerance value of the figure feature quantity of the basic figure determined by the figure feature value definition means to determine the type of figure. A figure determining means for determining.