JP2002015313A - Image data correcting device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To correct the luminance distribution of the image data of a document to a prescribed level. SOLUTION: The image data of the document 1 are read by a CCD(charge coupled device) sensor 11 and stored in an image memory 12. A frequency distribution generating section 13 generates the luminance frequency distribution of pixels based on the image data in the image memory 12 and stores it in a frequency distribution memory 14. A document density detecting section 15 detects a peak near the white level in the frequency distribution as the density of the ground color of the document. A luminance correcting section 16 determines a correction value based on the ratio between the luminance of the pixels in the image memory 12 and the density of the ground color in reference to a correction value table 17. The determined correction value is multiplied by the predetermined reference luminance to output corrected image data DATA.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image data correcting apparatus for correcting the brightness of image data obtained by reading a form.

[0002]

2. Description of the Related Art Conventionally, in an OCR (character reading device) or the like,
The form to be read is irradiated with light, the intensity of the reflected light is read by a CCD (Charge Coupled Device) sensor or the like, and the level of the read light is binarized by a predetermined threshold to perform processing such as character recognition. ing.

[0003]

However, the conventional OCR has the following problems. For example, when reading a form using a CCD sensor such as a digital camera, the intensity of light reflected from the form changes due to the influence of extraneous light and the like, and the level of light detected by the CCD sensor shifts as a whole. In some cases, binarization could not be performed correctly. In addition, there is a case where a shadow enters a part of a form and a reading error occurs partially.

An object of the present invention is to provide an image data correcting apparatus which solves the problems of the prior art and corrects the luminance distribution of image data obtained by reading a form to a predetermined level.

[0005]

According to a first aspect of the present invention, a form to be read is decomposed into pixels and optically read by an image data correcting apparatus. Image reading means for storing the luminance of the pixels as image data in an image memory; frequency distribution generating means for generating a frequency distribution (histogram) of the luminance of the image data; and ground density of the form based on the frequency distribution And a correction value for each pixel based on the ratio of the luminance of the pixel stored in the image memory to the density of the ground color of the form detected by the form density detection means. Brightness correction means for correcting the brightness of the image data by multiplying the value by a predetermined reference brightness.

According to the first aspect of the present invention, since the image data correcting device is configured as described above, the following operation is performed. A frequency distribution generating unit creates a luminance frequency distribution based on the image data of the form that has been decomposed into pixels and read by the image reading unit. In addition, the density of the ground color of the form is detected from the frequency distribution by the form density detecting means. A correction value for each pixel is obtained by the luminance correction unit based on the ratio of the luminance of each pixel to the density of the ground color, and the correction value is multiplied by the reference luminance to correct the image data.

According to a second aspect of the present invention, in the image data correcting apparatus, the form to be read is decomposed into pixels and optically read, and the luminance k of the pixel at each pixel coordinate (x, y) on the form is determined.
An image reading means for storing (x, y) as image data in an image memory; and dividing the image data into a plurality of rectangular image blocks each having m pixels vertically and n pixels horizontally, and A block image generating means for generating block image data whose luminance is a luminance P (X, Y) at the center coordinates (X, Y) of the image block; and a luminance k (x, y) of a pixel stored in the image memory. ) Is the luminance P1 (Xa, Ya), P2 (Xa, Yb), P2 of the center coordinates of the four image blocks surrounding the pixel in the block image data.
Using 3 (Xb, Ya), P4 (Xb, Yb) and a predetermined reference luminance M, the following equation is obtained: K (x, y) = k (x, y) +
M − ｛(Xb−x) (Yb−y) P1 + (Xb−x) (y−Y
a) P2 + (x-Xa) (Yb-y) P3 + (x-Xa) (y-Y
a) brightness correction means for calculating a corrected brightness K (x, y) by correcting according to P4） / {(Xb-Xa) (Yb-Ya)}.

According to the second aspect, the following operation is performed. The image data of the form read out by being decomposed into pixels by the image reading means is divided into rectangular image blocks of m × n pixels by the block image generating means, and the maximum luminance of the pixels in each image block is determined by the image block. Is considered to be the luminance at the center coordinates of. Further, the luminance correcting means corrects the luminance of each pixel of the image data based on a predetermined calculation formula in accordance with the luminance of the center coordinates of the four image blocks surrounding the pixel.

[0009]

(First Embodiment) FIG. 1 is a block diagram of an image data correction apparatus showing a first embodiment of the present invention. This image data correction device has image reading means (for example, a CCD sensor) 11 which decomposes an image of the form 1 to be read into pixels and optically reads the pixels. CC
The D sensor 11 converts the luminance of each pixel constituting the image of the form 1 into, for example, 256-gradation image data and outputs the image data. The output side of the CCD sensor 11 is connected to an image memory 12 for storing image data.

A frequency distribution generating means (for example, a frequency distribution generating unit) 13 is connected to the image memory 12. The frequency distribution generation unit 13 generates a frequency distribution of the luminance of the image data stored in the image memory 12, and a frequency distribution memory for storing the generated frequency distribution on the output side of the frequency distribution generation unit 13. 14 are connected. Form density detecting means (for example, a form density detecting unit) 15 is connected to the frequency distribution memory 14. Form density detector 15
Is for detecting the density of the ground color of the form 1 based on the frequency distribution stored in the frequency distribution memory 14. The form density detection unit 15 detects a tone that is close to the white level and has the highest frequency as the density of the ground color of the form 1.

A brightness correction means (for example, a brightness correction unit) 16 is connected to the form density detection unit 15. The brightness correction unit 16 further includes an image memory 12 and a correction value table 1.
7 is connected. The brightness correction unit 16 includes the image memory 1
2, a correction value for each pixel is obtained based on a ratio of the luminance of the pixel stored in the form 2 to the density of the ground color of the form detected by the form density detection unit 15, and the correction value is multiplied by a predetermined reference luminance. Then, the brightness of the image data is corrected.

That is, the brightness correction section 16 is provided in the image memory 12
Is calculated by calculating the ratio of the luminance of each pixel stored in the form and the density of the ground color of the form detected by the form density detection unit 15. Further, the brightness correction unit 16 obtains a correction value for each pixel with reference to the correction value table 17 using the normalized brightness as a variable, and corrects the brightness of the image data by multiplying the correction value by a predetermined reference brightness. I do. Then, the brightness correction unit 16
Output corrected image data DATA.

FIGS. 2A and 2B are explanatory diagrams showing examples of the correction value table 17 in FIG. 1. FIG. 2A shows a correction table for linear correction and FIG. 2B. Indicates a correction table when positive and negative gamma corrections are combined.

In the linear correction shown in FIG. 2A, the same correction value is output for the normalized luminance shown on the horizontal axis. In the gamma correction of FIG. 2B, a correction value calculated by a combination of positive and negative gamma functions is output for the normalized luminance shown on the horizontal axis.

FIGS. 3A and 3B are explanatory diagrams of the operation of FIG. Hereinafter, the operation of FIG. 1 will be described with reference to FIGS. 3 (a) and 3 (b). The image of the form 1 to be read is separated into pixels by the CCD sensor 11 and read. The read luminance of each pixel is converted into image data of 256 gradations from a black level (0) to a white level (255), and is sequentially stored in the image memory 12. When the reading of the form 1 by the CCD sensor 11 is completed, the frequency distribution generator 13 is activated.

The frequency distribution generator 13 includes an image memory 12
Are sequentially read out, and a frequency distribution of pixels for each luminance is generated.
Is stored in The frequency distribution of the pixels of the form 1 is shown in FIG.
As shown in FIG. 7, the peak has a substantially black level corresponding to the luminance of characters and the like and a peak relatively close to the white level corresponding to the density of the ground color. When the frequency distribution generation unit 13 completes the generation of the frequency distribution of the form 1, the form density detection unit 15
Is started.

In the form density detecting section 15, based on the frequency distribution stored in the frequency distribution memory 14, a level P (for example, P = 2) which is close to the white level and has the highest pixel frequency.
00) is detected as the density of the ground color of the form 1. When the form density detection unit 15 detects the density P of the ground color of the form 1, the brightness correction unit 16 is activated.

The brightness correction unit 16 controls the image memory 12
Are sequentially read out, and the following correction processing (1) to (3) is performed according to the value of the luminance k, and the corrected luminance K is output. You.

(1) In the case of k ≦ P First, the ratio of the luminance k of a pixel to the density P of the ground color of a form (= k / P)
P) is calculated as the normalized luminance. Further, the correction value table 17 is referred to using the normalized luminance as a variable, and a correction value TBL (k / P) for each pixel is obtained according to a predetermined correction method (for example, linear correction, gamma correction, or the like). Further, the correction value TBL (k / P) is multiplied by a predetermined reference luminance M (for example, M = 230). Then, the image data DAT in which the luminance K resulting from the multiplication is corrected
Output as A. That is, the corrected luminance K can be expressed as follows. K = TBL (k / P) × M

(2) In the case of P <k ≦ 255−M + P The luminance k of the pixel is shifted by (M−P). That is, the corrected luminance K can be expressed as follows. K = k + MP

(3) When k> 255−M + P In all cases, K = 255. The frequency distribution of the luminance K of the pixel after the correction by the correction processing of the luminance correction unit 16 is shown in FIG.
As shown in (b), the correction is performed so that the ground color density P matches the reference luminance M. Then, from the brightness correction unit 16,
The corrected luminance K is output as image data DATA.

As described above, the image data correcting apparatus according to the first embodiment detects the form density of the background color of the form 1 based on the frequency distribution of the luminance of the pixels of the form 1 read. It has a detection unit 15 and a luminance correction unit 16 that corrects the luminance of each pixel using the correction value table 17 so that the ground color density P is converted into the reference luminance M. Accordingly, there is an advantage that the luminance distribution of the image data can be corrected to a predetermined level regardless of the ground color of the form 1 or the reading state of the CCD sensor 11.

(Second Embodiment) FIG. 4 shows a second embodiment of the present invention.
FIG. 1 is a configuration diagram of an image data correction device according to an embodiment;
Elements common to those in FIG. 1 are denoted by common reference numerals. This image data correction device is a form 1 to be read.
Has a CCD sensor 11 which reads the image of (3) into, for example, 3000 × 2000 pixels. The CCD sensor 11 calculates the luminance of each pixel constituting the image of the form 1 by
For example, it is output as image data of 256 gradations. The output side of the CCD sensor 11 is connected to an image memory 12 for storing image data.

The image memory 12 is connected to a block image generating means (for example, an image dividing unit) 18. The image dividing unit 18 converts the image data stored in the image memory 12 into m (for example, 100) pixels vertically and n (for example, 10 pixels) wide.
0) It is divided into 30 × 20 rectangular image blocks composed of pixels. The image dividing unit 18 calculates the maximum luminance of the pixel in each divided image block by the luminance P (X, Y) at the center coordinates (X, Y) of the image block.
Is generated. A block memory 19 for storing the generated block image data is connected to the output side of the image dividing unit 18.

The block memory 19 is connected to a brightness correction means (for example, a brightness correction unit) 20, and the brightness correction unit 20 is further connected to the image memory 12. The brightness correction unit 20 calculates the brightness k (x, y) of the pixel at each pixel coordinate (x, y) stored in the image memory 12 at the center of four image blocks surrounding the pixel in the block image data. Using the coordinates luminance P1, P2, P3, P4,
This is corrected by a calculation method based on the ratio of distances.

That is, the luminance correction unit 20 determines a predetermined reference luminance M representing a correction position (ie, luminance) on the histogram of the form ground color, and sets the center coordinates of the four pixel blocks to P1.
(Xa, Ya), P2 (Xa, Yb), P3 (Xb, Ya), P4
As (Xb, Yb), the corrected luminance K according to the following equation (1):
(X, y) is calculated. K (x, y) = k (x, y) + M − ｛(Xb−x) (Yb−y) P1 + (Xb−x) (y−Ya) P2 + (x−Xa) (Yb−y) P3 + ( x−Xa) (y−Ya) P4｝ / {(Xb−Xa) (Yb−Ya)} (1) Then, the luminance K (x,
The image data DATA of y) is output.

FIGS. 5A to 5C are explanatory diagrams of the operation of FIG. Hereinafter, the operation of FIG. 4 will be described with reference to FIGS. 5 (a) to 5 (c). The image of the form 1 to be read is separated into pixels by the CCD sensor 11 and read. The read luminance of each pixel is converted into image data of 256 gradations from a black level (0) to a white level (255), and is sequentially stored in the image memory 12. When the reading of the form 1 by the CCD sensor 11 is completed, the image dividing unit 18 is activated.

The image dividing unit 18 divides the image data stored in the image memory 12 into a grid of 30 × 20 rectangular image blocks by dividing the image data into vertical and horizontal lines every 100 pixels in the vertical and horizontal directions. Is done. FIG. 5A schematically illustrates the image data divided by the image dividing unit 18 in a simplified manner. FIG. 5A shows image data in which the center is darkened by shadow (the luminance is reduced).

Further, in the image dividing section 18, the maximum luminance of the pixels in each divided image block is defined as the luminance P (X, Y) of the central coordinates (X, Y) of the image block. Is generated. The generated block image data is stored in the block memory 19. FIG.
(B) schematically shows the block image data stored in the block memory 19. In FIG. 5B, since the luminance of the central image block is low due to the influence of the shadow, the luminance of this image block is lower than the peripheral image blocks. When the block image data is generated by the image division unit 18, the luminance correction unit 20 is activated.

The brightness correction unit 20 controls the image memory 12
The luminance k (x, y) at each pixel coordinate (x, y) in the block is sequentially read out, and correction processing for the luminance k (x, y) is performed based on the block image data in the block memory 19. . That is, in the brightness correction unit 20, the center coordinates (Xa, Ya), (Xa, Yb), (Xb, Yb) of the image block corresponding to the pixel coordinates (x, y) read from the image memory 12.
Ya) and (Xb, Yb) are calculated. As shown in FIG. 5C, the X coordinates Xa and Xb are the X coordinate values of the vertical lines on both sides of the correction target pixel among the vertical lines dividing the image data. Similarly, the Y coordinates Ya and Yb are the Y coordinate values of the upper and lower horizontal lines of the correction target pixel among the horizontal lines dividing the image data.

Next, the brightness P1 (Xa, Ya), P2 (Xa, Yb), P3 of each image block at these center coordinates
(Xb, Ya) and P4 (Xb, Yb) are read from the block memory 19. Then, the luminance k (x,
y) is corrected by the equation (1), and the luminance K (x,
y) is calculated. The calculated brightness K (x, y) is sequentially output as corrected image data DATA.

When the pixel to be corrected is a pixel at the periphery of the document 1, the center coordinates of the four image blocks corresponding to the pixel cannot be obtained. In such a case, the processing can be performed on the assumption that there is an image block having the same luminance. However, the luminance may be output as the image data DATA without performing the correction processing.

As described above, the image data correction apparatus according to the second embodiment divides the read image data of the form 1 into rectangular image blocks composed of a plurality of pixels, and sets the maximum luminance as the central coordinate. An image division unit 18 that generates block image data having a luminance of, and a luminance correction unit 20 that uses the block image data to correct image data by a calculation method based on a distance ratio. As a result, the pixels of the image block having no shadow are hardly corrected. on the other hand,
The darkened portion is affected by the luminance of the surrounding image blocks, and is corrected to a luminance close to the ground color of a form without shadow.
Therefore, there is an advantage that the luminance distribution of the read image data can be corrected to a predetermined level regardless of the reading state of the CCD sensor 11.

Note that the present invention is not limited to the above embodiment, and various modifications are possible. For example, there are the following modifications (a) to (e). (A) The gradation of the image data is not limited to 256. 1
The same can be applied to arbitrary gradations such as 6, 64, 128, and 512.

(B) The correction in the correction table 17 in FIG. 1 is not limited to linear correction or gamma correction.

(C) Although FIG. 1 uses the correction table 17 in which a conversion table for correction is stored in advance, the calculation may be performed using a correction function without using the correction table 17. For example, in the case of linear correction, the correction table 17 is unnecessary.

(D) In the description of the operation of FIG. 1, it has been described that the brightness correction unit 16 performs the brightness level correction process for each pixel stored in the image memory 12.
The correction values for the luminance levels 0 to 255 stored in the image memory 12 may be calculated in advance, and the luminance levels may be replaced with the correction values. This makes it possible to shorten the processing time in the case of bitmap image processing using a lookup table.

(E) The size of the image block to be divided by the image dividing unit 18 in FIG. 2 is not limited to 100 × 100 pixels. An appropriate value can be used according to the actual use environment.

[0039]

As described above in detail, according to the first aspect, the form density detecting means for detecting the density of the ground color of the form based on the frequency distribution of the luminance of the pixels of the form, Brightness correction means for correcting the brightness of each pixel using a correction value so that the density of the pixel is converted to the reference brightness. This makes it possible to correct the luminance distribution of the read image data to a predetermined level regardless of the background color of the form or the reading state of the image reading unit.

According to the second aspect, the image data of the form is divided into rectangular image blocks each including a plurality of pixels,
Block image generation means for generating block image data having the maximum luminance as the luminance of the center coordinates, and luminance correction means for correcting image data by a calculation method based on a distance ratio using the block image data.

Further, a value detected from the histogram of the block can be used as the predetermined reference luminance M. In this case, when the shadow portion becomes large, the form ground color detected from the histogram becomes the shadow color, and the form ground color portion is uniformly corrected to a dark color. Therefore, by correcting the image processed in the second invention by the first invention, it is possible to correct the form ground color at a predetermined level even if the shadow range is widened. Therefore, the distribution of the luminance of the read image data can be corrected to a predetermined level regardless of the reading state of the image reading means.

[Brief description of the drawings]

FIG. 1 is a configuration diagram of an image data correction device according to a first embodiment of the present invention.

FIG. 2 is an explanatory diagram showing an example of a correction value table 17 in FIG.

FIG. 3 is an explanatory diagram of the operation of FIG. 1;

FIG. 4 is a configuration diagram of an image data correction device according to a second embodiment of the present invention.

FIG. 5 is an explanatory diagram of the operation in FIG. 4;

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Form 11 CCD sensor 12 Image memory 13 Frequency distribution generation part 14 Frequency distribution memory 15 Form density detection part 16, 20 Brightness correction part 17 Correction value table 18 Image division part 19 Block memory

Claims (2)

[Claims] An image reading unit that decomposes a form to be read into pixels and optically reads the pixels and stores the luminance of each pixel as image data in an image memory; and a frequency of generating a frequency distribution of the luminance of the image data. Distribution generation means; form density detection means for detecting the density of the ground color of the form based on the frequency distribution; luminance of the pixels stored in the image memory; and the form background detected by the form density detection means. Brightness correction means for obtaining a correction value for each pixel based on a color density ratio, and multiplying the correction value by a predetermined reference brightness to correct the brightness of the image data. Image data correction device. 2. A form to be read is decomposed into pixels and optically read, and a luminance k (x, y) of a pixel at each pixel coordinate (x, y) on the form is stored in an image memory as image data. An image reading unit that divides the image data into a plurality of rectangular image blocks each including m pixels vertically and n pixels horizontally, and calculates the maximum luminance of the pixels in each image block as the center coordinates (X, Y) of the image block. A block image generating means for generating block image data having a luminance P (X, Y) of the pixel luminance k (x, y) of a pixel stored in the image memory
Is defined as 4 surrounding the pixel in the block image data.
Luminance P1 (Xa, Ya), P at the center coordinates of the image blocks
2 (Xa, Yb), P3 (Xb, Ya), P4 (Xb, Yb) and a predetermined reference luminance M, the following equation: K (x, y) = k (x, y) + M− ｛(Xb−x) (Yb−
y) P1 + (Xb-x) (y-Ya) P2 + (x-Xa) (Yb
−y) P3 + (x−Xa) (y−Ya) P4｝ / ｛(Xb−Xa)
(Yb−Ya)｝, and a brightness correction unit that calculates a corrected brightness K (x, y).