JPH0433190B2 - - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION [Technical Field of the Invention] The present invention relates to an image signal binarization device used, for example, in CCR or facsimile.

[Technical Background of the Invention and Problems Therewith] Conventionally, OCR or facsimile systems are configured such that an image signal obtained by scanning an object to be read is converted into a binary signal and then processed. For this binarization process, a method using a fixed judgment threshold is normally used. That is, as shown in FIG. 7, for example, an image signal A obtained by scanning images P1 to P6 (L direction scanning) with a CCD or the like.
When sliced by threshold levels THu, THn, and THl, they are converted into binary signals Du, Dn, and Dl, respectively.

In such a method, as shown in Fig. 7, the thin line P2 is output as black in the binarization process using the threshold level THl, but in the case of a narrow white line P3 with white between the lines, the white between the lines is output. Not done. Also, the threshold
In the binarization process using THn, image P2 is missing,
The space between the narrow white lines P3 is output as white. Furthermore, if there is a difference in density between images like images P4 to P6, it is not possible to obtain the required binarized signal at a certain threshold level.

For this reason, various binarization methods have been considered depending on the level of the appearing image. For example, there is a binarization process in which a density generation histogram of an image is created and a valley V of the histogram as shown in FIG. 8 is set as a threshold level. However, this method has problems such as difficulty in detecting the valley V and inability to set an accurate threshold level.

[Object of the Invention] An object of the present invention is to obtain a binarized signal according to the density characteristics of an image by determining a threshold level for binarization processing as a value that is a function of the maximum value of the density of the image. An object of the present invention is to provide an image signal binarization device that can perform the following steps.

[Summary of the Invention] The present invention includes a predetermined point of interest (ij) in a multivalued image input signal expressed by a matrix (xij), and calculates the density average value and its deviation in a plurality of directions in the vicinity from the point of interest, respectively. It is equipped with calculation means for calculating. The smoothed data determining means determines the average value in the direction indicating the minimum value of the deviation calculated by the calculating means as the smoothed data of the point of interest (ij). The maximum concentration value determining means calculates the maximum average value from the concentration average values calculated by the calculation means, and calculates the maximum average value around the point of interest (ij) based on this maximum average value. Determine as a concentration value.
The binary data determining means is configured to determine the binary data based on the maximum density value determined by the maximum density value determining means and the smoothed data determined by the smoothed data determining means. There is.

Further, the present invention obtains shape codes from a plurality of directions determined centripetally with respect to the point of interest (ij), and calculates the degree of coincidence of the shape codes in each direction facing the point of interest (ij). It is equipped with a shape calculation means for calculation. When the calculation result of the shape calculation means exceeds a predetermined threshold and the point of interest (ij) is determined as a feature candidate point, the shape determination means determines the feature candidate point based on the maximum density value and the smoothed data. Determine it as a feature point. The binarized data correction means is configured to correct the binarized data determined by the binarized data determining means based on the feature points determined by the shape determining means.

[Embodiment of the Invention] An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing the configuration of a binarization processing device according to an embodiment. In Figure 1,
The average value calculation unit 10 is a circuit that calculates the density average value for a multivalued image input signal obtained by scanning a reading object. The deviation calculation unit 11 is a circuit that calculates the deviation from the multivalued image input signal and the density average value. The minimum deviation detection section 12 is a circuit that obtains the minimum value of the deviation calculated by the deviation calculation section 11. The smoothed data determination unit 13 is a circuit that determines smoothed data based on the average density value and the minimum deviation value from the minimum deviation detection unit 12. The maximum density detection section 14 is a circuit that detects the maximum density value from the density average value from the average value calculation section 10.

The binarization determination unit 15 is a circuit that determines binarized data based on the maximum density value from the maximum density value detection unit 14 and the smoothed data from the smoothed data determination unit 13. The binarization correction unit 16 is a circuit that operates based on the correction selection signal S and corrects the binarized data output from the binarization determination unit 15 based on the output from the shape determination unit 18. Shape calculation section 17
is a circuit that obtains shape codes from multiple directions determined centripetally with respect to a point of interest in a multivalued image input signal, and calculates the degree of coincidence of shape codes in each direction relative to the point of interest. be. Here, the shape code is a code indicating a change in image density that is set in response to a change in image density (see FIGS. 5 and 6).

When the calculation result of the shape calculation means exceeds a predetermined threshold and the point of interest is determined as a feature candidate point, the shape determination means determines the feature candidate point as a feature point based on the maximum density value and the smoothed data. This is the circuit that determines.

In the binarization processing apparatus having such a configuration, the operation of this embodiment will be explained. First, it is assumed that a multivalued image input signal obtained by scanning an object to be read is provided to the average value calculation section 10. Here, the multivalued image input signal is expressed as a matrix (xij),
A predetermined point of interest (ij) is set. Average value calculation section 1
0 calculates the density average value hl (l=0 to 7) in the vicinity of the point of interest (ij) in eight directions in the matrix (xij) as shown in FIG. 2a.
Here, the i direction is the main scanning direction of the multivalued image input signal, and j is the sub-scanning direction thereof. The neighborhood in eight directions centered on the eye point (ij) is expressed as y0 to y7 as shown in FIG. 2b. Further, the deviation calculation unit 11 calculates the deviation value bl(l-0
~7) Calculate. That is, the density average value hl and the deviation value bl are determined by the following equations (1) to (8).

h ₀ = (x _i-2,j +x _ij , +x _ij )/3 h ₀ = (x _i-2,j +x _ij , +x _ij )/3 b ₀ =k((x _i-2,j −h ₀ ) ² + (x _i-1,j −h ₀ ) ² + (x _ij −h
₀ ) ² ) ^1/2 ... (1) ... ... h ₇ = (x _i-2,j+2 +x _i-1,j+1 +x _ij /3 h ₇ = (x _i-2,j+2 +x _i-1,j+1 +x _ij /3 b ₇ =k((x _i-2,j+2 −h ₇ ) ² +(x _i-1,j+1 −h ₇ ) ² +(x _i
j −h ₇ ) ² ) ^1/2 ...(8) Here, in the above formulas (1) to (8), k is the deviation value bl
This is a constant for normalizing .

Next, the minimum deviation detection unit 12 detects the minimum value of the deviation value bl, and determines the direction of the minimum value. Thereby, the smoothed data determining unit 13 determines the concentration average value hl in the method determined by the minimum deviation detecting unit 12 (that is, in the direction of the minimum deviation value) from the calculation result of the average value calculating unit 10, and calculates it. The smoothed data Xij of the point of interest (ij) is determined. That is, the smoothed data Xij
is the concentration average value hl at the minimum value min of the deviation value bl
(l=0 to 7). On the other hand, maximum concentration detection section 1
4 detects the maximum value max of the density average value hl from the average value calculation unit 10 and sets it as the first maximum density value hij.
That is, hij=maxhl (l=0 to 7) (9). Next, the maximum density detection unit 14 calculates a second maximum density as shown in the following equation (10) from the first maximum density value hij in the area from i-m to i+m with respect to the point of interest (ij) as a constant m. Find the value Hij.

Hij=max hlj (l=i−m to i+m) (10) The maximum density detection unit 14 sets the maximum density value Hij shown in the above equation (10) as the maximum density value at the point of interest (ij).

The binarization determination unit 15 obtains binarized data Dij from the smoothed data Xij and the maximum density value Hij obtained as described above. Here, the binarized data Dij is the smoothed data Xij and the maximum density value Hij
is expressed as a function of That is, Dij=f(Xij, SLij, THmin) (11), where GLij is data that determines the threshold value of the point of interest (ij), and is f(Hij). Also,
THmin is the lowest level value of the slice. If the threshold value is determined to be half of the maximum density value Hij, that is, the midpoint between white and black, then equation (11) can be expressed as the following relationship.

If Xij≧SLij (1/2Hij), Dij=1 (however, Xij≧THmin) Also, if Xij≦SLij, Dij=0 becomes.

Through such an operation, the binarization determination unit 15
Binarized data Dij as shown in FIG. 3 will be output. That is, the image signal A shown in FIG.
From this, smoothed data Xij, maximum density values Hij and SLij shown in FIG. 5 are obtained. Threshold determination data
SLij will be automatically determined near the middle of the image, and the binary data Dij for the white and low density image P6 of the thin line P2 and narrow white line P3 will be "1", "0", and "1", respectively. Appropriate value. Next, 2
A case where correction processing is performed on the binarized data Dij obtained by the digitization determination section 15 will be described. This correction operation is started by a correction selection signal S supplied to the binarization correction section 16. First, the state of change in image density at the point of interest (ij) is detected based on the peripheral shape of the point of interest (ij). Here, the peripheral shape is the state of change in the peripheral density of the point of interest. In other words, the shape calculation unit 17 calculates a centripetal 8 centering on the point of interest (ij) from the neighboring points similar to that shown in FIG. 2a.
The directions are Z0a~Z3a, Z0b~ as shown in Figure 5.
Defined as Z3b. Furthermore, the shape calculation unit 17
From a pre-stored table as shown in Figure 6,
Find the shape code for each direction Zna, Znb (n=0 to 3). Here, for example, the shape code of Z0a is (Xi-2j) → (Xi-1j) → shown in Figure 2 a.
This is a code indicating density changes at three points in the direction of (Xij). Similarly, for example, the shape code of Z2b is
(Xij+2) → (Xij+1) → (Xij) shown in figure a
This is a code indicating density changes at three points in the direction of .
The table in FIG. 6 is a code in which the shapes of density changes in each direction toward (i, j) shown in FIG. 5 are classified into, for example, nine types. For example, shape No. 2 shows a state in which the density of the point of interest (the rightmost point among the three points) gradually increases from the outside (the leftmost point). On the contrary, for example, shape No. 5 shows a state in which the density of the point of interest gradually decreases from the outside. Further, for example, shape No. 9 shows a state in which the density at the central portion (middle point) is high and the density at the point of interest changes to be low. Next, the four opposing direction combinations Zna,
The degree of matching of shape codes is calculated for Znb (n=0 to 3). As a result of this calculation, when the number of matches is greater than or equal to a predetermined constant, a ridge point candidate is selected if the shape code is "1", and a trough point candidate is selected if the shape code is "2".

The shape determining unit 18 converts the ridge point candidates and valley point candidates into the smoothed data Xij calculated as described above.
and Sij are determined as ridge points and valley points, respectively. That is, as shown in Fig. 4, if the allowable deviation differences are ΔK and ΔM, respectively, then if the relational expression Δ=SLij−Xij≦ΔK holds true, then the point of interest (ij ) is determined as the ridge point. Furthermore, if a relational expression such as Δ=Xij−SLij≦ΔM (13) holds true, the point of interest (ij) is determined as the valley point.

Based on the output of the shape determining unit 18, the binarization correction unit 16 converts the binarized data into binary data if the point of interest (ij) is a ridge point and the binarized data Dij of the binarization determination unit 15 is “0”. Dij is corrected and a correction value D1ij which is "1" is output. Further, if the point of interest (ij) is the valley point and the binarized data Dij of the binarization determination unit 15 is "1",
A complementary value D1ij which is "0" is output. Other than that,
Output the binarized data Dij as is. With such a correction operation, even in the case of a white line Q1 surrounded by a high concentration area and an extremely thin line Q2 adjacent to a high concentration area as shown in FIG. 4, appropriate binary data D1ij can be obtained.
It becomes possible to obtain a binary signal D that is .

In this manner, appropriate binarized data can be obtained by setting a threshold value that is a function of the maximum density value around the point of interest (ij) for the multivalued image input signal. Therefore, even if the image has narrow white lines (for example, when there is a difference in density within characters) or a difference in density between images, it is possible to convert the image into binary data without losing the characteristics of the image.

In addition, by correcting the binarized data Dij based on the shape code determined by the peripheral shape of the point of interest (ij), in the case of a white line surrounded by a high-density area and an extremely thin line adjacent to a high-density area, However, it is possible to obtain appropriate binarized data. This allows conversion into a binary signal that can faithfully reproduce minute images.

[Effects of the Invention] As detailed above, according to the present invention, the threshold level for binarization processing is determined as a value that is a function of the maximum value of the density of the image, so that A valued signal can be obtained. Also,
By performing a correction operation based on the peripheral shape of the image, it is possible to obtain a binarized signal that can faithfully reproduce a minute image. Therefore, when the present invention is applied to OCR or facsimile, it is possible to improve the accuracy of image binarization, and as a result, the reading accuracy can be improved.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing the configuration of an embodiment of the present invention, FIGS. 2a and 2b are diagrams for explaining the binary data determination operation of the embodiment, and FIG.
4 and 4 are waveform diagrams for explaining the operation of the same embodiment, respectively. FIGS. 5 and 6 are diagrams for explaining the correction operation of binary data of the embodiment, respectively. FIG. 8 is a waveform diagram for explaining a conventional binarization method, and FIG. 8 is a diagram for explaining a conventional binarization method using a density generation histogram. 10... Average value calculation section, 11... Deviation calculation section,
12... Minimum deviation detection unit, 13... Smoothed data determination unit, 14... Maximum density detection unit, 15... Binarization determination unit, 16... Binarization correction unit, 17... Shape calculation unit, 18...Shape determining section.

Claims (1)

[Claims] 1. Including a predetermined point of interest (ij) in a multivalued image input signal expressed by a matrix (Xij), the average density value and its deviation in a plurality of directions in the vicinity of the point of interest are calculated, respectively. a calculation means; a smoothed data determination means for determining the average value in the direction indicating the minimum value of the deviation calculated by the calculation means as the smoothed data of the point of interest (ij); maximum density value determining means for determining a maximum average value from the density average values obtained and determining a maximum average value around the point of interest (ij) as the maximum density value of the point of interest (ij) based on this maximum average value; and binarized data determining means for determining binarized data based on the maximum density value determined by the maximum density value determining means and the smoothed data determined by the smoothed data determining means. An image signal binarization device comprising: 2. Calculating means for calculating density average values and deviations thereof in a plurality of directions in the vicinity of a predetermined point of interest (ij) in a multivalued image input signal expressed by a matrix (Xij), including a predetermined point of interest (ij); smoothed data determining means for determining the average value in the direction indicating the minimum value of the previous period deviation calculated by the means as the smoothed data of the point of interest (ij); and from the concentration average value calculated by the calculating means. maximum density value determining means for determining a maximum average value and determining the maximum average value around the point of interest (ij) as the maximum density value of the point of interest (ij) based on the maximum average value; Binarized data determining means for determining binarized data based on the maximum density value determined by the determining means and the smoothed data determined by the smoothed data determining means; and pre-prepared image density. The shape code is obtained from a plurality of directions determined centripetally with respect to the point of interest (ij) based on a table storing shape codes corresponding to changes in a shape calculation means for calculating the degree of coincidence of the shape codes in each direction; and a shape calculation means for calculating the matching degree of the shape code in each direction; a shape determining means for determining the feature point as a feature point based on the density value and the smoothed data; and a binary value determined by the binarized data determining means based on the feature point determined by the shape determining means. An image signal binarization device comprising: a binarization data correction means for correcting converted data.