JP2658136B2 - Character recognition method - Google Patents

Description

Description: TECHNICAL FIELD The present invention relates to a character recognition method in a character reading device.

(Prior Art) Various methods have been proposed as character recognition methods in conventional character reading devices. Stroke analysis and pattern matching methods are widely used for character recognition for alphanumeric characters and katakana. In addition, methods to analyze the line structure of patterns and background structures to absorb character deformation are used. There is a method of analysis.

However, in the above-described method, for example, in the case of the stroke analysis method, since the characteristics of each character are described in a dictionary including the deformation, the dictionary becomes enormous, and thus the processing time becomes long. There is a disadvantage that the size of the wear becomes large.

In the method of analyzing the background structure, a character is identified by focusing on the background portion of the character and extracting a characteristic such as a loop of a character line or a concave or convex shape. It has the disadvantage of being complicated.

In order to eliminate such a drawback, a technique in such a field has been conventionally described in Japanese Patent Application Laid-Open No. Sho 59-161784 (online character recognition large classification method). Hereinafter, the configuration will be described with reference to FIG.

A tablet 11 that generates data indicating the coordinates of a writing instrument when writing characters, and an online character recognition device that recognizes written characters based on data generated from the tablet, converts analog data from the tablet into digital data. Means 12 for temporarily storing digital data including the start point and the end point of the stroke and
(3) and (14), a means 16 for storing the result of performing the calculation 14 of the feature amount including the length of the line segment, the relative position, and the like from the data after the preprocessing, and data stored in advance or stored in advance. Means 18 for comparing the magnitude relationship between the data 17 which is the modified data and the data of the predetermined calculation result, and identifies the distribution position of the stroke line segment of the written character by writing the written character. Was aware of.

Then, the line length of all strokes described as the feature amount and the position where each segment representing the stroke line segment exists are used.

(Problems to be Solved by the Invention) However, in the conventional configuration shown in FIG.
For character recognition, the starting point and the ending point of the stroke must be stored, and there is a problem in further reducing the hardware scale and the processing time. For this reason, using the contour extraction method, the starting point may be any point on the contour, that is, it is not necessary to consider the stroke. Here, the method using the contour extraction method is not the object of the present invention. The character recognition ability in the case of using this method is insufficient when the average value of the position where each line segment exists is used as the feature amount.

SUMMARY OF THE INVENTION An object of the present invention is to provide a character recognition method in a character reading device that enhances character recognition by considering the inclination of a line segment when extracting a feature amount of a position where each line segment of a character exists. I do.

(Means for Solving the Problems) The present invention provides a character having a means for reading a character on a form and storing binarized character pattern data and a means for extracting a contour of the character pattern from the data. Means for determining the inclination of a line segment between x, y outline coordinates from the data obtained by extracting the outline of the character pattern, and for each of the determined inclinations, based on the x, y outline coordinates of each line segment. Means for calculating a characteristic amount indicating a distribution position which is a relative position from a predetermined reference point; and means for comparing a characteristic amount stored in advance with the characteristic amount of the calculation result, the input character pattern The character is recognized by identifying the distribution position of the line segment for each inclination of the line segment between the x and y outline coordinates.

(Operation) According to the present invention, since the character recognition method is configured as described above, the means for determining the inclination of the line segment is based on the data obtained by extracting the outline of the character pattern. Means for judging whether the inclination is upper right, lower right, horizontal or vertical, and calculating the characteristic amount is based on the x, y contour coordinates of each line segment for each inclination based on the line segment inclination. A feature amount indicating a distribution position that is a relative position from a point is calculated.

The means for comparing the previously stored feature amount with the feature amount of the predetermined calculation result includes, for all the recognition target characters, a difference in matching between the previously stored feature amount and the feature amount of the predetermined calculation result. As the matching distance, sorting is performed by the matching distance, and the character having the minimum matching distance is selected as the recognition result.

Therefore, the above problem can be eliminated, and a character recognition method in a character reading device with improved character recognition ability can be provided.

(Embodiment) FIG. 1 is a block diagram showing an embodiment of the present invention. In the figure, 1 is a pattern register for storing a binarized character pattern, 2 is an outline extraction unit for extracting the outline of the character pattern based on the contents of the pattern register 1, 3
Is an inclination determining unit that determines the inclination of a line segment from the x, y outline coordinates extracted by the outline extracting unit 2, ie, upper right, lower right, horizontal or vertical, and 4 is a character pattern for each inclination determined by the inclination determining unit 3. The characteristic amount calculating unit 5 for calculating the characteristic amount based on the relative position of the line segment is an identification unit for identifying a character pattern.

 Hereinafter, the operation of the present embodiment will be described.

The pattern register 1 reads the characters on the form,
The digitized character pattern is input by a character pattern input unit (not shown). Here, it is assumed that the character pattern shown in FIG. 3 is stored. The contour extraction unit 2 performs contour tracing from the contents of the pattern register 1 with the coordinates (9, 32) and (11, 24) as starting points, as shown in FIG. Since the contour extraction method is not the object of the present invention, the description is omitted, but the contour can be easily extracted. Note that the contour tracking start point may be any point.

Next, the inclination determining unit 3 extracts the x, y extracted by the contour extracting unit 2.
From the outline coordinates, it is determined whether the line segment is inclined, that is, whether the line is upward, downward, rightward, horizontal or vertical.

For right up the x _i> x _{i + 1} with y _i> y _{i + 1} or x _i <x _{i + 1} with y _i <y _{i + 1} for downhill x _i> x _{i + 1} with y _i < y _{i + 1} or x _i <x _{i + 1} and y _i > y _{i + 1 For} horizontal, x _i = x _{i + 1} and y ₁ ≠ y _{i + 1 For} vertical, y _i = y _{i + 1} and x By determining each condition of _i判別 xi _{+ 1} , the inclination of each line segment is determined.

FIG. 5 shows the x and y outline coordinates and inclination of the character pattern.
In the slope section of Fig. 5, "/" means upper right, "＼" means lower right,
"-" Indicates horizontal and "|" indicates vertical.

The feature amount calculation unit 4 calculates x,
A feature amount is calculated from the relative position of the line segment from the y-coordinate.

 The feature amount calculation will be described in detail below.

The position where each line segment exists is used as the feature value. The location where a certain line segment is located in the x and y directions is quantified for each of the x and y components, and the average value is calculated.

 First, consider the upper right line segment.

For the relative position of the x component on the x axis, Similarly, for the relative position of the y component on the y axis, Is represented by

 Here, Hx and Hy indicate the character width of the character pattern.

For the position of the x component on the y axis, And the position of the y component on the x axis is Is represented by

Similarly, for a line segment descending to the right, a relational expression equivalent to Q ₅ = Q ₁ for the position of the x component on the x axis, and a relational expression equivalent to Q ₆ = Q ₂ for the position of the y component on the y axis. The position of the x component on the y-axis is expressed by a relational expression equivalent to Q ₇ = Q ₃ .

The position of the y component on the x-axis is represented by a relational expression equivalent to Q ₈ = Q ₄ .

Similarly, for a horizontal line segment, a relational expression equivalent to Q ₉ = Q ₁ for the position of the x component on the x axis, and a relational expression equivalent to Q ₁₀ = Q ₃ for the position of the x component on the y axis. Is represented.

Similarly, for a vertical line segment, a relational expression equivalent to Q ₁₁ = Q ₂ for the position of the y component on the y axis, and a relational expression equivalent to Q ₁₂ = Q ₄ for the position of the y component on the x axis. Is represented by

The Q ₁ to Q ₁₂ are rectangular bottom left (FIG. 4 (1,1)) circumscribing a character pattern performs calculation by the coordinate system with the origin. Therefore, the position where the x and y components of each line segment exist is y
The feature amount decreases as the position on the axis moves downward and the position on the x axis moves to the left, and in the method of the present invention, all the weights related to the positions of all line segments are added, so that the position is closer to the origin. The change in the line segment in the portion appears as a small difference, and is influenced by the change in the line segment in the upper right portion on the rectangle circumscribing the character pattern. Therefore, the upper right corner of the rectangle circumscribing the character pattern (Fig. 4 (2
2, 32)), calculations are performed on the above-mentioned Q _{1 to} Q _{12 in} a coordinate system with the origin as Q _{13 to} Q ₂₄ .

Using the formula Q ₁ to Q ₂₄ described above, x shown in FIG. 5 performs a calculation by y coordinate, and inclination data. An operation is performed on the outer edge contour shown in FIG. 5 (a) and the inner edge contour shown in FIG. 5 (b), and the result is obtained as the sum of the outer edge and the inner edge contour.
Q ₁ ~Q ₂₄ is required. As described above, the above operation is performed on a character having a plurality of inner edges with respect to all the line segments.

The identification unit 5 stores the feature values of Q _{1 to} Q ₂₄ for each recognition target character. The identification unit 5 matches the characteristic amounts Q _{1 to} Q _{24 of} the input character pattern calculated by the characteristic amount calculation unit 4 with the characteristic amounts Q _{1 to} Q _{24 of the} character pattern stored in the identification unit 5. The difference in these matchings is defined as a matching distance, and this calculation is performed for all the identification target characters stored in the identification unit 5, and sorting based on the matching distance is performed.

According to the sorting result, the character having the minimum matching distance is selected as the recognition result.

(Effects of the Invention) As described in detail above, according to the present invention, a character is regarded as a figure, and the x, y contour coordinates of each line segment are separately determined by taking into account the inclination of the line segment between the x, y contour coordinates. Since a feature amount indicating a distribution position that is a relative position from a predetermined reference point is extracted based on the extracted characteristic amount, an effect of increasing the character recognition ability of the character reading device can be expected.

[Brief description of the drawings]

FIG. 1 is a block diagram of one embodiment according to the present invention, FIG. 2 is a block diagram of a conventional online character recognition large classification method, FIG. 3 is a character pattern diagram, FIG. The figure is a contour feature diagram showing coordinates and inclination. 1: pattern register, 2: contour extraction unit, 3: inclination determination unit, 4: feature value calculation unit, 5: identification unit.

Continuation of the front page (56) References JP-A-62-290985 (JP, A) JP-A-62-269286 (JP, A) IEICE Technical Report PRL82-29 IEICE Technical Report PRL82-79

Claims (1)

(57) [Claims] 1. An apparatus for recognizing a character, comprising: means for reading a character on a form and storing binarized character pattern data; and means for extracting an outline of the character pattern from the data. Means for determining the inclination of the line segment between the x, y outline coordinates from the data obtained by extracting the contour of the pattern; and for each of the determined inclinations, a relative to a predetermined reference point based on the x, y outline coordinates of each line segment. Means for calculating a characteristic amount indicating a distribution position as a position, and means for comparing a characteristic amount stored in advance with the characteristic amount of the calculation result, wherein the distribution position of a line segment of an input character pattern is provided. A character recognition method characterized by recognizing a character by identifying a line segment inclination between x and y contour coordinates.