JPH04158482A - Arrow head recognizing device - Google Patents

Abstract

PURPOSE:To recognize the running direction of the arrow head of a diagram in an image at high speed by providing a detecting means which detects a tip vector to form the tip of the arrow head, a control means which sets the flag of the arrow head on the tip vector, and a decision means which decides a direction to which the tip of the arrow head points. CONSTITUTION:When image data is inputted, it is converted to vector data consisting of a start point, an end point, an angle, and width and is stored in a vector storage means. The tip vector which forms the tip of the arrow head from another ordinary vector is detected from read out vector data by a vector detecting means. The control means performs control to set the flag of the tip vector of the arrow head on the tip vector, and the decision means which decides the direction to which the tip of the arrow head points, and a tip data storage means holds tip data consisting of a place and a direction representing the tip and the size of the tip. In such a way, it is possible to recognize the running direction of the arrow head of the diagram in the image at high speed.

Description

[Detailed Description of the Invention] [Industrial Application Field] The present invention converts input image data into vector data,
The present invention relates to an arrow recognition device that recognizes arrows in an input image based on the vector data and is suitable for, for example, graphic recognition devices such as digital printers, facsimile machines, digital printing machines, and digital copying machines.

[Conventional technology]

As a technology for recognizing images by processing image signals read by raster scanning, for example, Japanese Patent Application Laid-Open No. 54-15493
No. 5 discloses a method for recognizing a connecting line connecting two circles in a diagram, and JP-A-55-83972 discloses a method for distinguishing between different symbols in a bitmap image using a certain area. Japanese Unexamined Patent Publication No. 56-59374 discloses a device for extracting the joining point between lines in a bitmap image and the direction of the line at that point. Japanese Patent Publication No. 60-2468
Publication No. 1 discloses a drawing reading device that reads a line diagram, such as a circuit diagram, drawn on graph paper and compares each square of the graph paper with a "dictionary" to distinguish different symbols.

Furthermore, Japanese Patent Laid-Open No. 56-105580 discloses a figure recognition method that converts bitmap data into vector data through line thinning processing and then calculates the line length to recognize symbols. JP-A-57-150075 discloses a method for recognizing a target figure, JP-A-57-150075 discloses a device for recognizing a rectangular shape by examining the horizontal and vertical lines of a bitmap image, and JP-A-58-18776 discloses a method for recognizing a rectangular shape by first identifying the center of the figure. Discloses a technology that recognizes the shape of a figure by finding it, measuring the distance from the center to a point on the outer circumference of the figure in all directions, graphing the distance, that is, the radius r and angle, and calculating the first derivative of the graph. has been done.

Furthermore, JP-A-58-24974, JP-A-59-2
2175, JP-A-59-22178, and JP-A-61-877 first find the contour line of a bitmap image, examine density changes in eight directions at each point on the contour line, and then There is a method to recognize the shape of an image by graphing it against the distance from the starting point.
Japanese Unexamined Patent Publication No. 60-45887 discloses a device that recognizes shapes by specifying the region of the shape to be recognized and counting the number of pixels of a horizontal cutting line in a digital image.
-142486 publication finds the intersection of line vectors,
A drawing recognition device that recognizes, for example, circuit diagram symbols by extracting a small area including the intersection point and comparing it with a "dictionary" was developed in Japanese Patent Laid-Open No. 61
JP-A-74078 and JP-A-61-74079 disclose a shape separation device and a shape recognition device that use matrix operations to separate joining lines and symbols.
82183 discloses a pattern recognition method in which the shape of a bitmap image is compared with a set of shapes in a "dictionary" using an image division method, and JP-A-61-208171 discloses a pattern recognition method in which the shape of a bitmap image is compared with a set of shapes in a "dictionary". JP-A No. 62-133588 further describes a device that finds intersections and junctions, extracts images of these areas, and compares them with a "dictionary" to read drawings. An image recognition device for determining shape is disclosed.

[Problem to be solved by the invention]

One of the important image processes in a specific image processing apparatus is an arrow recognition process that recognizes the tip of an arrow in a vector image. For example, arrows are used to indicate the flow direction of control operations in the flowchart shown in FIG. 5, or the direction of current or polarity of voltage in the circuit diagram shown in FIG. An image processing system that attempts to extract such images must be able to detect and analyze arrows.

Previously developed arrow recognition methods were time consuming and unsuitable for use in vector image recognition for boat fishing. Most methods find out what type of symbol it is by comparing part of the image with a "dictionary". Not only is the "dictionary" comparison method time consuming and inflexible, but it also requires a large amount of memory, especially for bitmap "dictionaries."

The present invention has been made in view of the above circumstances, and by adopting other analysis methods, it is possible to recognize the arrow tip of a vector image, which not only eliminates the need for comparison with Dictionary J, but also eliminates the need for Dictionary J itself. The present invention aims to provide an arrow recognition device.

[Means to solve the problem]

In order to solve the above-mentioned problems, the present invention provides a first means for an arrow recognition device to include a vector storage means for storing vector data consisting of a starting point, an ending point, an angle, and a width, and a location indicating a tip, a direction, and a size of the tip. a tip data storage means for holding tip data consisting of; a detection means for detecting a tip vector forming the tip of an arrow from among other normal vectors; and control for setting a flag of an arrow tip vector on the tip vector. The apparatus includes a control means and a determining means for determining the direction in which the tip of the arrow points.

The second means is the same as the first means, further comprising recognition means for recognizing symbols in a vector image and judgment processing means for judging the vector image.

[Effect]

In the first means, when image data is input, it is converted into vector data consisting of a starting point, an end point, an angle, and a width, and is stored in a vector storage means. The read vector data is used by a detection means to detect a tip vector forming the tip of the arrow from among other normal vectors. The control means performs control to set a flag of the tip vector of the arrow in the tip vector. The determining means determines the direction in which the tip of the arrow faces. The tip data storage means holds tip data consisting of a location indicating a tip, a direction, and a size of the tip.

In the second means, the recognition means recognizes symbols in the vector image, and the judgment processing means judges the vector image.

〔Example〕

Hereinafter, one embodiment of the present invention will be described in detail with reference to the drawings.

FIG. 1 is a schematic block diagram of an image processing circuit of a digital copying machine as an embodiment of the present invention. In the figure, reference numeral 1 denotes a document reading device which optically reads a document, converts it into binary data, and stores it in a memory as image data. Reference numeral 2 denotes an image determining unit which determines whether the stored image data is character data or graphic image data. Reference numeral 3 denotes a vector conversion unit which reads image data determined to be a graphic image, extracts graphic image data, and converts it into vector data. Reference numeral 4 denotes a figure recognition unit which reads vector data, recognizes it as figure elements such as straight lines and circles, and stores the recognition results as figure element data. Reference numeral 5 denotes a drawing device which synthesizes graphic element data and character data and draws a drawing on recording paper.

The image data vector-converted by the vector converter 3 undergoes a lot of processing and is output, but before that, it is converted into the most compressed state. The vectors are then aligned with each other along the x and y axes.

FIG. 2 shows an example of an arrow image recognized by the figure recognition unit 4. In this example, three vectors are concentrated at the tips of the arrows, two of which are relatively short and a third, longer vector that bisects the angle between the two vectors. The two shorter vectors do not join to the other vectors at the start point (end point), but join to the other two vectors at the end point (start point). The present invention attempts to recognize the tip of an arrow in an image based on the properties of the above-described arrow vector.

FIG. 3 shows a flowchart of arrow recognition processing according to the embodiment. The above processing will be explained below according to this flowchart.

First, in step S-1, when a vector image is input, the image data is converted into vector data, and then the number of vectors connected at the end point of each vector is counted. Then, the junction points of all the vectors in the image are extracted and recorded in the buffer memory (S-2). The buffer memory stores twice the number of points as the number of vectors, and each point is attached with a counter NUM-JP and an index corresponding to the extracted vector. FIG. 4 shows the vector data of each point and the recording state of the vector in the buffer memory. Next, in order to speed up the search process for the location of the joining point, the points are arranged in ascending order of X coordinate using a high speed arrangement method. Furthermore, for each vector, count the number of vectors that join at the junction point. That is, for example, the number of points that fall within the limit distance of one fin at the junction is counted and stored in NUM-JP (S-3).

From the above fact, the NUM of the tip end point of all arrow vectors
- It can be seen that JP is 3. Furthermore, at the other end points of the two outer vectors at the tips of the arrows, NUM-JP=1
It can also be seen that (no junction vector). With this information, the number of vectors can be significantly reduced, leaving only those vectors that are likely to be arrow vectors, and the remaining vectors form a group with other vectors that connect to them.

That is, in step S-4, a vector is found that has two other vectors that are joined at one end and that is not joined to the other vectors at the other end, and the other points (vectors) are removed from the buffer memory. Single vectors (vectors with no opposing vectors) are grouped together with two other vectors joining at one end of the 0th order which are also removed (S-5
), the length of the central vector that bisects the angle formed by the point NUM-JP=3 where the outer vectors join is 10 m.
If it is larger than m, it can be seen that these vectors form a group of arrow vectors. This results in a pair of outer vectors and a group of unknown vectors that meet the above criteria.

Now check the next parameter, vector length.

The two outer vectors must be shorter than the central vector, but in this embodiment the length range of the outer vectors is set to 2 to 10 m, and vector pairs that do not satisfy this condition are removed. That is, in step S-6, it is checked that the length of the outer vector falls within the above range, and in step S-7, the direction of the tip of the arrow is found only for such a pair of vectors. Finally, since the direction of the central vector is the direction of the arrow vector, these data are stored in the buffer memory as arrow tip data (S-8).

〔Effect of the invention〕

As explained above, according to the present invention, the invention as set forth in claim 1 includes a tip data storage means for holding tip data consisting of a location indicating a tip, a direction, and a size of the tip; A detection means for detecting a tip vector forming the tip of an arrow from among the vectors, a control means for setting a flag of an arrow tip vector in the tip vector, and a determining means for determining the direction in which the tip of the arrow faces. Therefore, the flow direction of the arrow in the diagram in the image can be recognized at high speed.

Furthermore, the invention described in item 2 further includes a recognition means for recognizing symbols in a vector image and a judgment processing means for determining the vector image. It can be carried out.

[Brief explanation of drawings]

1 to 4 are diagrams relating to embodiments of the present invention, in which FIG. 1 is a schematic block diagram of an image processing circuit of a digital copying machine as an embodiment of the present invention, and FIG. 3 is a flowchart of arrow recognition processing; FIG. 4 is an explanatory diagram showing vector data of each point and the recording state of the vector in the buffer memory;
FIGS. 5 and 6 are a flowchart and a circuit diagram, respectively, showing examples of images to be subjected to arrow recognition processing. l... Original reading device, 2... Image determination unit, 3.
. . . vector conversion unit, 4 . . . figure recognition unit, 5 . . . drawing device. Bud 1 Figure 2 Figure 4 Figure 3

Claims (2)

[Claims] (1) A vector storage means for holding vector data consisting of a start point, an end point, an angle and a width, a tip data storage means for holding tip data consisting of a location indicating a tip, a direction and a size of the tip, and other normal vectors. Detecting means for detecting a tip vector forming the tip of an arrow from among; control means for controlling to set a flag of an arrow tip vector in the tip vector; determining means for determining the direction in which the tip of the arrow faces; An arrow recognition device with. (2) The arrow recognition device according to claim 1, further comprising recognition means for recognizing symbols in a vector image, and judgment processing means for judging the vector image.