JP2021072484A - Image processing apparatus, image processing method, and image processing program - Google Patents

Abstract

To provide a binarization processing technology that improves achievement of both discrimination of a low-density image and reduction of image noise.SOLUTION: An image processing apparatus comprises: a histogram analysis unit that calculates, for input image data with a discriminant analysis method, a first average gradation value that is an average gradation value of a first class, and a second average gradation value that is an average gradation value of a second class on a side including a relatively large amount of background images; an operation display unit that receives a user input for adjusting a threshold between the first average gradation value and the second average gradation value; and a binarization processing unit that adjusts the threshold according to the user input that is input to the operation display unit and executes binarization processing by using the adjusted threshold. The operation display unit adjusts the threshold according to the operation and displays an image after the binarization processing in real time.SELECTED DRAWING: Figure 1

Description

The present invention relates to an image processing apparatus, an image processing method and an image processing program, and more particularly to a binarization processing technique.

When a document containing background noise is read and the scanned image is binarized, there is a problem that unnecessary background noise remains. To solve such a problem, for example, Patent Document 1 obtains a moving average of frequencies for each density in a density histogram of an input image, and obtains a binarized slice level based on the density value for the maximum frequency of the result. We are proposing a technology for binarization. However, since the threshold value is set by a simple method on the assumption that the histogram after taking the moving average has clear bimodality, the threshold is set when there is no clear bimodality. There is a problem that it cannot be done. On the other hand, in Patent Document 2, a "cell" of n × n pixels is acquired, a measurement area of m × m pixels (n <m) is set around the cell, and a local area with respect to the cell is obtained from a luminance histogram in the measurement area. We are proposing a technique for obtaining a target threshold value and binarizing a cell using a local threshold value within a preset limit value range. The reason why the value is within the preset limit value is to suppress the extraction of noise components.

Japanese Unexamined Patent Publication No. 7-262348 Japanese Unexamined Patent Publication No. 2001-245148

However, according to the findings of the inventor of the present application, when the density distribution of the background is wide, clear bimodality is often not recognized, and Patent Document 1 corresponds to such binarization of images. There is a problem that it cannot be done. On the other hand, according to the analysis of the inventor of the present application, the generation of the noise component fluctuates according to the density of the background. Therefore, with the preset fixed limit value, the noise component is extracted and the thin figures and characters disappear. There is a problem that we cannot escape from the trade-off problem.

The present invention has been made in view of such a situation, and an object of the present invention is to provide a binarization processing technique for improving both discrimination of a low-density image and suppression of image noise.

The image processing apparatus of the present invention is a side that contains a relatively large amount of a first average gradation value, which is an average gradation value of the first class, and a background image in a discrimination analysis method for input image data. The threshold value is adjusted between the histogram analysis unit that calculates the second average gradation value, which is the average gradation value of the second class, and the first average gradation value and the second average gradation value. The operation display unit that accepts the user input for the operation, and the binarization that adjusts the threshold value according to the user input input to the operation display unit and executes the binarization process using the adjusted threshold value. The operation display unit includes a processing unit, and the operation display unit displays the image after the binarization processing in real time according to the operation of the threshold value.

The image forming method of the present invention is a side that contains a relatively large amount of a first average gradation value, which is an average gradation value of the first class, and a background image in a discrimination analysis method for input image data. The threshold value is adjusted between the histogram analysis step of calculating the second average gradation value, which is the average gradation value of the second class, and the first average gradation value and the second average gradation value. The operation display process that accepts the user input for the operation and the binarization that adjusts the threshold value according to the user input input in the operation display process and executes the binarization process using the adjusted threshold value. The operation display step includes a processing step, and displays the image after the binarization process in real time according to the operation of the threshold value.

The image processing program of the present invention is a side that contains a relatively large amount of a first average gradation value, which is an average gradation value of the first class, and a background image in a discrimination analysis method for input image data. Histogram analysis unit that calculates the second average gradation value, which is the average gradation value of the second class, adjusts the threshold value between the first average gradation value and the second average gradation value. An operation display unit that accepts user input for the purpose, and a binarization process that adjusts the threshold value according to the user input input to the operation display unit and executes a binarization process using the adjusted threshold value. The image processing device is made to function as a unit, and the operation display unit displays the image after the binarization processing in real time according to the operation of the threshold value.

According to the present invention, it is possible to provide a binarization processing technique for improving both discrimination of a low-density image and suppression of image noise.

It is a schematic block diagram which shows the whole structure of the image forming apparatus 10 which concerns on 1st Embodiment of this invention. It is a block diagram which shows the functional structure of the image forming apparatus 10 which concerns on 1st Embodiment. It is explanatory drawing which shows the scanned image and the luminance histogram of the scanned image. It is explanatory drawing which shows the binarization process which concerns on a comparative example, and the threshold THc for the binarization process of a comparative example. It is a flowchart which shows the content of the binarization processing procedure which concerns on 1st Embodiment. It is explanatory drawing which shows the content of the low-pass filter processing which concerns on 1st Embodiment. It is a flowchart which shows the content of the page threshold value setting process which concerns on 1st Embodiment. It is explanatory drawing which shows the content of the page threshold value setting process which concerns on 1st Embodiment. It is explanatory drawing which shows the content of the threshold value setting process for skin noise determination which concerns on 1st Embodiment and comparative example. It is explanatory drawing which shows the content of the background noise removal processing which concerns on 1st Embodiment and comparative example. It is explanatory drawing which shows the content of the background noise removal processing and binarization processing which concerns on 1st Embodiment. It is a flowchart which shows the content of the binarization process which concerns on 1st Embodiment. It is explanatory drawing which shows the state of selection of the local region of interest which concerns on 1st Embodiment. It is a graph which shows the threshold value THS for switching which concerns on 1st Embodiment. It is explanatory drawing which shows the content of the binarization process which concerns on 1st Embodiment. It is a flowchart which shows the content of the threshold value adjustment process for binarization which concerns on 2nd Embodiment. It is explanatory drawing which shows the operation display screen which concerns on 2nd Embodiment. It is explanatory drawing which shows the content of the filter processing which concerns on the modification.

Hereinafter, embodiments for carrying out the present invention (hereinafter, referred to as “embodiments”) will be described in the following order with reference to the drawings.
A. First Embodiment:
B. Second embodiment:
C. Modification example:

A. First Embodiment:
FIG. 1 is a schematic configuration diagram showing the overall configuration of the image forming apparatus 10 according to the first embodiment of the present invention. FIG. 2 is a block diagram showing a functional configuration of the image forming apparatus 10 according to the first embodiment. The image forming apparatus 10 includes an image reading unit 100, a control unit 210, an image forming unit 220, an operation display unit 230, a storage unit 240, and a fax processing unit 250. The image reading unit 100 has an automatic document feeder (ADF) 160 and a platen (contact glass) 150, and reads an image (original image) from the document to generate an image data ID which is digital data.

The image forming unit 220 forms an image on a print medium (not shown) based on the image data ID and discharges the image. The image forming unit 220 includes a color conversion processing unit 221, a halftone processing unit 222, and an image output unit 223. The color conversion processing unit 221 color-converts the image data ID, which is RGB data, into CMYK image data. The halftone processing unit 222 executes halftone processing to generate halftone data of CMYK image data. The image output unit 223 forms an image based on the halftone data. The operation display unit 230 receives user operation input from a display (not shown) that functions as a touch panel and various buttons and switches (not shown).

The control unit 210 includes main storage means such as RAM and ROM, and control means such as MPU (Micro Processing Unit) and CPU (Central Processing Unit). Further, the control unit 210 has controller functions related to interfaces such as various I / O, USB (universal serial bus), bus, and other hardware, and controls the entire image forming apparatus 10.

The storage unit 240 is a storage device including a hard disk drive, a flash memory, or the like which is a non-temporary recording medium, and is a control program (including an image processing program) for processing executed by the control unit 210 and the binarization processing unit 140. And memorize data.

As shown in FIG. 2, the image reading unit 100 includes a light source driver 111 and a light source 112. The light source 112 has a plurality of LEDs (not shown) that irradiate the document D with light. The light source driver 111 is an LED driver that drives a plurality of LEDs arranged in the main scanning direction, and controls on / off drive of the light source 112. As a result, the light source 112 can irradiate the document surface of the document D with the irradiation light L1 by pulse width modulation (PWM) with a variable drive duty.

The irradiation light L1 is emitted at an angle of 45 degrees (inclined direction) with respect to the direction perpendicular to the surface of the document D. The document D reflects reflected light including diffusely reflected light L2 and specularly reflected light. The light receiving element 122 receives the diffuse reflected light L2.

Further, as shown in FIG. 1, the image reading unit 100 further connects the first reflector 113, the first carriage 114, the second reflector 115, and the third reflection between the document D and the image sensor 121. It includes a mirror 116, a second carriage 117, and a condenser lens 118. The first reflecting mirror 113 reflects the diffuse reflected light L2 from the document D in the direction of the second reflecting mirror 115. The second reflecting mirror 115 reflects the diffuse reflected light L2 in the direction of the third reflecting mirror 116. The third reflecting mirror 116 reflects the diffuse reflected light L2 in the direction of the condenser lens 118. The condenser lens 118 forms an image of diffuse reflected light L2 on each light receiving surface (not shown) of a plurality of light receiving elements 122 included in the image sensor 121.

The image sensor 121 is three CCD line sensors (not shown) that detect each of the three colors R, G, and B using a color filter (not shown) of each color component of R, G, and B. .. The image sensor 121 scans the document (secondary scan) with three CCD line sensors extending in the main scanning direction, and acquires an image on the document as a combination of voltage values corresponding to R, G, and B. In this way, the image sensor 121 can perform photoelectric conversion processing and output R, G, and B analog electric signals for each pixel in the main scanning direction.

The first carriage 114 mounts the light source 112 and the first reflecting mirror 113, and reciprocates in the sub-scanning direction. The second carriage 117 mounts the second reflecting mirror 115 and the third reflecting mirror 116, and reciprocates in the sub-scanning direction. The first carriage 114 and the second carriage 117 are controlled by a control unit 210 that functions as a scanning control unit. As a result, the light source 112 can scan the document in the sub-scanning direction, so that the image sensor 121 can output an analog electric signal according to the two-dimensional image on the document.

When the automatic document feeder (ADF) 160 is used, the first carriage 114 and the second carriage 117 are fixed at preset sub-scanning positions, and the sub-scanning direction is achieved by the automatic feeding of the document D. Is scanned. In addition, some ADF160 read not only one side but also both sides simultaneously or sequentially.

The ADF 160 includes a paper feed roller 161 and a document reading slit 162. The paper feed roller 161 automatically feeds the original, and the original is read through the original reading slit 162. In this case, since the first carriage 114 is fixed at a preset sub-scanning position, the light source 112 mounted on the first carriage 114 is also fixed at a predetermined position.

As shown in FIG. 2, the image reading unit 100 further includes a signal processing unit 123, a shading correction unit 124, a shading correction table 124a, a gamma conversion unit 125, a binarization processing unit 140, and an AGC processing. A unit 130 and a white reference plate 132 (see FIG. 1) are provided. The binarization processing unit 140 has a filter processing unit 141 and a threshold value setting unit 142.

The signal processing unit 123 is a variable gain amplifier having an A / D conversion function. The signal processing unit 123 is set by the AGC processing unit 130, amplifies the analog electric signal with the gain stored in the storage unit 240, and A / D-converts the amplified analog electric signal into digital data.

In the present embodiment, the AGC processing unit 130 is a gain adjusting unit that uses the black reference signal and the white reference signal to set the optimum gain and offset value for each of the plurality of light receiving elements 122. The black reference signal is an analog electric signal of the light receiving element 122 when the light source 112 is off. The white reference signal is an analog electric signal of the light receiving element 122 when the white reference plate 132 is irradiated instead of the document D.

The AGC processing unit 130 sets an offset value so that each RGB gradation value of the image data ID when the black reference signal is A / D converted by the signal processing unit 123 becomes the minimum value “0”. The AGC processing unit 130 gains using this offset value so that each RGB gradation value of the image data ID when the white reference signal is A / D converted by the signal processing unit 123 becomes the maximum value “255”. To set. As a result, the dynamic range from the minimum value "0" to the maximum value "255" can be effectively used.

The shading correction unit 124 executes shading correction on the digital data to generate an image data ID. The shading correction is caused by the non-uniformity of the amount of light in the length direction of the light source 112, the peripheral dimming due to the cosine fourth power rule of the lens, and the uneven sensitivity of the plurality of light receiving elements 122 arranged in the main scanning direction. It is a correction for suppressing. The gamma conversion unit 125 performs gamma conversion based on the characteristics of the image reading unit 100. As a result, the image reading unit 100 can generate an image data ID having each RGB gradation value.

The binarization processing unit 140 uses the calculation formula of the luminance value L (luminance value L≈0.3R + 0.6G + 0.1B) to calculate the luminance value L using each RGB gradation value of the image data ID. To generate monochrome image data MD0. The binarization processing unit 140 further executes binarization processing on the monochrome image data MD0 to obtain binary data BD in which each pixel is represented by one bit. The FAX processing unit 250 can execute the facsimile transmission processing using the binary data BD having a small data size.

In this way, the image reading unit 100 reads the image on the document D to generate an image data ID, and generates binary data BD as needed. The image data ID is RGB image data representing the image on the document D with each RGB gradation value (0 to 255).

FIG. 3 is an explanatory diagram showing a scanned image and a luminance histogram of the scanned image. FIG. 3A shows the original image D0. The original image D0 is an image having relatively low brightness of the background and poor visibility. The original image D0 is an image represented by an image data ID generated by reading the image reading unit 100.

FIG. 3B shows the luminance histogram H0 of the monochrome image data MD0. The monochrome image data MD0 is a histogram of the brightness value L of the image data ID representing the original image D0. The horizontal axis of the luminance histogram is the luminance gradation value (0 (black) to 255 (white)), and the vertical axis is the number of pixels (frequency). The luminance histogram H0 includes a line drawing pixel group which is a pixel group which constitutes a line drawing image such as black character text and a ruled line, and a background pixel group which is a pixel group which constitutes a background image.

FIG. 4 is an explanatory diagram showing the binarization process according to the comparative example and the binarization processing threshold THc of the comparative example. The binarization processing threshold THc is set using a discriminant analysis method (Otsu's method) as a comparative example. The discriminant analysis method is a method in which the luminance histogram is divided into two classes according to a provisional threshold value, the shape of the histogram is examined from the variance value in each class and the variance value between classes, and the threshold value that seems to be located most in the valley is adopted. is there. The processing content of the discriminant analysis method will be described later.

FIG. 4A shows a binarized image Dc as a processing result of the binarization process according to the comparative example. The binarized image Dc is an image represented by the binarized data BD after the binarization process. In the binarization data BD, the binarization processing unit 140 sets the luminance gradation value of the line drawing pixel group of the monochrome image data MD0 as the input image data to "0 (black)", and the binarization processing of the background pixel group is performed. Image data generated by setting the luminance gradation value of a pixel whose luminance gradation value is lower than the threshold THc to "0" and setting the luminance gradation value of another pixel to "1 (white)". is there.

FIG. 4B shows the binarization processing threshold value THc according to the comparative example. The binarization processing threshold THc not only discriminates the text image of black characters as the pattern area, but also discriminates the image area composed of pixels having low brightness in the background image as the pattern area. Since the brightness of the background image determined to be the pattern area is changed to "0 (black)" by the binarization processing unit 140, the binarized image Dc is remarkably grainy by the binarization processing. The image is deteriorated (rough) (see FIG. 4 (a)).

FIG. 5 is a flowchart showing the contents of the binarization processing procedure according to the first embodiment. The binarization treatment according to the first embodiment can remarkably suppress the deterioration of graininess caused by the above-mentioned background image.

In step S100, the filter processing unit 141 of the binarization processing unit 140 executes the low-pass filter processing. In the low-pass filter processing, the binarization processing unit 140 executes a smoothing process on, for example, 300 dpi monochrome image data MD0 (also referred to as input image data) using a Gaussian filter having 5 × 5 pixels. Thereby, the low-pass filter processing can smooth the noise of the background image and generate the monochrome image data MD1. The background noise is an example of background noise.

FIG. 6 is an explanatory diagram showing the contents of the low-pass filter processing according to the first embodiment. FIG. 6A shows a luminance histogram H0 of the monochrome image data MD0 before the low-pass filter processing. FIG. 6B shows the luminance histogram H1 of the monochrome image data MD1 after the low-pass filter processing. As can be seen from the luminance histogram H1, the gradation value distributions of the discrete background pixel groups are grouped into a single mountain.

The low-pass filter processing smoothes the high-frequency component of the monochrome image data MD0 (the gradation region of the background where the pixel value fluctuates sharply (noisy and jagged luminance component)), thereby setting the threshold value for background noise determination (step S300). ) To make it possible to set an appropriate threshold.

In step S200, the threshold value setting unit 142 of the binarization processing unit 140 sets the page threshold value THP based on the luminance histogram H1 after the low-pass filter processing. In the page threshold setting process, the binarization processing unit 140 sets the page threshold using the discriminant analysis method (Otsu's method). The page threshold THP is a binarization threshold applicable to the entire surface of the image.

FIG. 7 is a flowchart showing the contents of the page threshold value setting process (step S200) according to the first embodiment. FIG. 8 is an explanatory diagram showing the contents of the page threshold value setting process according to the first embodiment. In step S210, the binarization processing unit 140 functions as a histogram analysis unit, and uses a provisional threshold value to provisionally change the luminance histogram H1 into class 1 (also referred to as a first class) and class 2 (second class). It is divided into two classes (also called classes) (see FIG. 8A). The second class is a class that contains a relatively large amount of background images.

In step S220, the binarization processing unit 140 executes the intra-class variance calculation process. In the intra-class variance calculation process, the binarization processing unit 140 calculates the intra-class variance using the calculation formula F1. In step S230, the binarization processing unit 140 executes the inter-class variance calculation process. In the inter-class variance calculation process, the binarization processing unit 140 calculates the inter-class variance using the calculation formula F2. In step S240, the binarization processing unit 140 executes the total variance calculation process. In the total variance calculation process, the binarization processing unit 140 calculates the total variance using the calculation formula F3. The total variance can be used as an evaluation value for the provisional threshold.

The binarization processing unit 140 repeatedly executes the processes of steps S210 to S240 with all the gradation values of the luminance gradation values (step S250). In step S260, the binarization processing unit 140 sets the page threshold value THP to the gradation value having the maximum total variance.

In step S300, the binarization processing unit 140 functions as a background noise determination threshold value setting unit, and sets a background noise determination threshold value THB, which is a background noise determination threshold value. In addition, this process (step S300) may be skipped when the background is black. The background noise determination threshold THB is also referred to as a background noise determination threshold.

FIG. 9 is an explanatory diagram showing the contents of the threshold value setting process for determining background noise according to the first embodiment and the comparative example. FIG. 10 is an explanatory diagram showing the contents of the background noise removal processing according to the first embodiment and the comparative example. FIG. 9A shows a method of setting the background noise determination threshold THB according to the first embodiment. FIG. 9B is an explanatory diagram showing the content of the threshold value setting process for determining background noise according to the comparative example. FIG. 10A is an explanatory diagram showing the contents of the background noise removal processing according to the first embodiment. FIG. 10B is an explanatory diagram showing the contents of the background noise removal processing according to the comparative example.

In this example, the binarization processing unit 140 has a luminance gradation value that is a ratio (for example, 10%) of the number of pixels (frequency) in a predetermined range of the number of peak pixels, which is the number of pixels of the peak value PB of the distribution of the background image. Is searched from the side of the background peak gradation value, which is the brightness gradation value of the peak value PB, to the side of the lower brightness gradation value (the side where the density becomes darker).

In the threshold value THB for determining background noise (FIG. 9 (b)) according to the comparative example, the gradation value distribution of the background pixel group is discrete (jagged), so that the binarization processing unit 140 determines the background noise. It can be seen that it is not possible to set a threshold value for determining background noise that can be effectively eliminated (see FIG. 10B). On the other hand, in the background noise determination threshold THB (FIG. 9A) according to the first embodiment, the gradation value distribution of the background pixel group is organized into a single mountain, so that the binarization processing unit The 140 can smoothly set an appropriate threshold value for determining the background noise and effectively eliminate the background noise (FIG. 10A).

As a result, the binarization processing unit 140 can set the searched threshold value as the background noise determination threshold value THB. In the luminance histogram H1, as described above, the high-frequency component (the gradation region of the background where the pixel value fluctuates drastically (the noisy and jagged brightness component)) is smoothed, so that the binarization processing unit 140 is used for the background. It is possible to smoothly set the background noise determination threshold THB so that the residue does not become excessive. The proportion in the predetermined range is preferably 5% to 20%, more preferably 5% to 15%, and most preferably in the vicinity of 10%.

In step S400, the binarization processing unit 140 compares the page threshold value THP with the background noise determination threshold value THB, and if the page threshold value THP is larger than the background noise determination threshold value THB, the process proceeds to step S500. If the page threshold THP is equal to or less than the background noise determination threshold THB, the process proceeds to step S600.

In step S500, the binarization processing unit 140 replaces the value of the background noise determination threshold value THB with the value of the page threshold value THP and resets it. As a result, when the threshold THB for determining the background noise is set to be excessively small, the binarization processing unit 140 excessively erases the background noise by the background noise removal processing and deletes the text image or the like to be left. You can prevent what happened.

In step S600, the binarization processing unit 140 functions as a background noise reduction processing unit and executes background noise removal processing (also referred to as background noise reduction processing). In the background noise removal processing, the binarization processing unit 140 uses the pixel value of a pixel having a higher brightness gradation value (thin density) than the background noise determination threshold THB as the brightness gradation value of the background noise determination threshold THB. Set.

As a result, the binarization processing unit 140 can generate the monochrome image data MD2 having the luminance histogram H2. In the luminance histogram H2, the luminance gradation value distribution of the background image is smoothed by concentrating on the background noise determination threshold THB, and the contrast becomes low. Therefore, in the binarization process (step S700) described later, noise (particularly edges) It is possible to suppress erroneous discrimination from the pattern image.

FIG. 11 is an explanatory diagram showing the contents of the background noise removal process and the binarization process according to the first embodiment. In this example, unlike the binarization process (step S700) described later, the binarization processing unit 140 assumes a case where the threshold value of the binarization process is fixed to the page threshold THP. FIG. 11A shows a monochrome image D1 after the background noise removal processing. In the monochrome image D1, the background image is processed so that the brightness of the pixels having a remarkably low brightness is high, while the brightness of the pixels having a remarkably high brightness is low, so that the graininess of the monotone is improved (fine). ) Have a background image.

FIG. 11B shows a binary image D2 after the binarization process according to the first embodiment. The binary image D2 is an appropriate image without deteriorating the graininess because the pixels in the background region, which are erroneously determined to be the pixels in the pattern region, are remarkably reduced by the setting of the page threshold value THP according to the first embodiment. It has become. Such reduction of erroneous discrimination is realized by reducing the graininess by the background noise removing treatment and reducing the local contrast.

As described above, the image forming apparatus 10 according to the first embodiment executes the low-pass filter processing as the preprocessing before setting the threshold value for the binarization processing. As a result, the binarization processing unit 140 can reduce the noise of the background image and reduce the dispersion of the luminance gradation value. The noise removal of the background image can reduce the deterioration of graininess due to the binarization process. To reduce the dispersion of the brightness gradation value, the width of the distribution of the background image is narrowed around the average value of the brightness gradation value of the background image, and the change of the gradation value of the distribution is smoothed to smooth the change of the gradation value of the distribution, which is the threshold value THB for determining the background noise. Can be facilitated.

FIG. 12 is a flowchart showing the contents of the binarization process (step S700) according to the first embodiment. In step S710, the binarization processing unit 140 functions as a local area selection unit of interest, and a plurality of pixels constituting the monochrome image data MD2 (also referred to as input image data) are (M × N) pixels (M and N). Is divided into a plurality of local regions composed of, for example, an integer of 3 or more), and the divided plurality of local regions are sequentially selected as the local regions of interest. The local region of interest is, for example, an region having a reference size of 5 × 5 pixels. The reference size is set according to, for example, the resolution of the image to be processed.

FIG. 13 is an explanatory diagram showing a state of selection of a local region of interest according to the first embodiment. FIG. 14 is a graph showing the switching threshold THS according to the first embodiment. In this example, two local regions LR1 and LR2 are shown. When the local region LR1 is selected as the local region of interest, since the text image of black characters is in the reference range, the minimum luminance value is close to 0, and the maximum luminance value is the luminance value of the background, that is, the background noise determination. It becomes the brightness value in the vicinity of the threshold value THB. On the other hand, when the local region LR2 is selected, since the thin text image is in the reference range, the minimum luminance value becomes the luminance value of the thin text image, and becomes the luminance value in the vicinity of the background noise determination threshold THB. The maximum brightness value is the brightness value of the background.

In step S720, the binarization processing unit 140 executes the maximum luminance value acquisition process. In the maximum luminance value acquisition process, the binarization processing unit 140 acquires the maximum luminance value in the local region of interest. Specifically, the binarization processing unit 140 acquires the maximum brightness value of the background in each local region regardless of whether the local region of interest is the local region LR1 or the local region LR2. In this example, it is assumed that the binarization processing unit 140 has acquired the local maximum luminance value L_Max (luminance value 170) in the local region LR2 (see FIG. 14A). The maximum brightness value is the maximum gradation value of the brightness, and may be the maximum gradation value which is the density gradation value on the lowest density side.

In step S730, the binarization processing unit 140 functions as a switching threshold setting unit and executes the switching threshold setting process. In the switching threshold setting process, the binarization processing unit 140 reads a preset binarization threshold switching threshold table (also referred to as a threshold switching table) T from the storage unit 240 and sets the switching threshold THS. Make it possible. In this example, it is assumed that the binarization processing unit 140 has acquired "30" as the switching threshold THS based on the local maximum luminance value L_Max (luminance value 170).

The threshold value switching table T is a table obtained by discretizing the switching threshold value THS defined by the calculation formula F4. As for the switching threshold THS, the lower the brightness of the background area (the background image in this example), the more the contrast generated in the local area may be caused not by the pattern area but by the noise of the image in the background area. It is set based on the inventor's knowledge that the property is high. The inventor of the present application has found in experiments and simulations that it is preferable to change the switching threshold value THS according to the maximum gradation value. Specifically, it has been found that it is preferable to set the switching threshold value THS so as to increase as the maximum gradation value decreases (as the density increases), and in particular, set so as to change linearly.

In step S740, the binarization processing unit 140 executes the local contrast calculation process. In the local contrast calculation process, the binarization processing unit 140 determines the difference between the maximum luminance value (170 in this example) and the minimum luminance value (120 in this example) among the 25 pixels of 5 × 5 in the local region. Is calculated as the local contrast LC (see formula F5). In this example, it is assumed that the binarization processing unit 140 has acquired "50" (= 170-120) as the local contrast LC. The minimum brightness value is the minimum gradation value of the brightness, and may be the minimum gradation value which is the gradation value on the darkest side.

In step S750, the binarization processing unit 140 advances the process to step S760 when the local contrast LC is larger than the switching threshold THS, and performs the process when the local contrast LC is equal to or less than the switching threshold THS. Proceed to step S770. As a result, the binarization processing unit 140 can suppress erroneous determination that noise in the background region is the contrast in the pattern region and omission of characters.

In step S760, the binarization processing unit 140 sets the local threshold value THL (see calculation formula F6) as the binarization processing threshold value used for the binarization processing of the local region LR2. In this example, in the calculation formula F6, the coefficient α is, for example, a numerical value of 0.1 or more. In step S770, the binarization processing unit 140 sets the page threshold THP as the binarization processing threshold used for the binarization processing of the local region LR2. The processing of steps S710 to S770 is executed for all local regions (step S780). The local threshold value may be set within a range between the maximum gradation value and the minimum gradation value.

FIG. 15 is an explanatory diagram showing the content of the binarization process according to the first embodiment. FIG. 15A shows a manuscript image D0a showing a thin text image. The original image D0a has the same background image as the original image D0 (see FIG. 3A), but is shown with the background removed for the sake of clarity. FIG. 15B shows the image Dca after the binarization processing according to the comparative example. In this example, in the image Dca, the thin text image is erroneously determined as the background image and disappears by the binarization process. FIG. 15B shows the image D2 after the binarization processing according to the first embodiment. In this example, in the image D2, the thin text image is discriminated from the image in the pattern region and is clearly reproduced by the binarization process.

As described above, the image forming apparatus 10 according to the first embodiment adjusts the switching threshold value THS according to the luminance gradation value according to the maximum brightness value in the local region, and locally based on the switching threshold value THS. The binarization process is executed by appropriately switching between the threshold value THL and the page threshold value THP. This makes it possible to improve both discrimination of low-density images (thin text, etc.) and suppression of image noise. On the other hand, since the image forming apparatus 10 reduces the contrast of the background noise by the background noise removal processing, it is possible to suppress erroneous determination that the noise in the background region is the contrast of the low-density image.

B. Second embodiment:
FIG. 16 is a flowchart showing the contents of the binarization threshold adjustment process (step S800) according to the second embodiment. In the binarization process according to the second embodiment, after the binarization process according to the first embodiment, the binarization threshold value is adjusted according to the user's request, and the binarization process can be executed again. It is configured as follows. The binarization process according to the second embodiment is the first embodiment in that the binarization threshold adjustment process (step S800) is added to the binarization process of the first embodiment at the end of the process. Different from the form.

FIG. 17 is an explanatory diagram showing an operation display screen according to the second embodiment. The binarization threshold adjustment process (step S800) is activated as an interactive fine adjustment process mode in response to a predetermined user input to the operation display unit 230 after the binarization process. The operation display unit 230 has a user interface screen 231 and a start button 232. The user interface screen 231 has an interactive fine adjustment processing mode, and has a selection icon 233, a release icon 234, an OK icon 235, a density decrease icon 237d, and a density increase icon 237u.

In step S810, the operation display unit 230 accepts user input for area selection. The user can specify the selection area SR by sliding a finger on the user interface screen 231 in a state where the selection icon 233 is touched and inverted. When the selection area is selected again, the designation of the selection area SR can be canceled by touching the release icon 234. When the OK icon 235 is touched in this state, the operation display unit 230 displays a character input pop-up screen (not shown).

In step S820, the operation display unit 230 accepts user input on a pop-up screen (not shown) for character input. When the user touches the OK icon (not shown) on the pop-up screen with or without entering characters, the process proceeds to step S830.

In step S830, the OCR processing unit 211 of the control unit 210 executes the OCR accuracy calculation process. In the OCR accuracy calculation process, the OCR processing unit 211 recognizes the input characters, quantifies the OCR accuracy (recognition accuracy), and calculates the integrated value of the recognition accuracy of each character. _{The OCR processing unit 211 has a threshold value between the class 1 average luminance value M 1} (see FIG. 8) and the class 2 average luminance value M ₂ set at the time of the threshold value TH 1 and the page threshold value according to the first embodiment. The OCR accuracy is calculated for each threshold value while changing the above (step S840). The OCR processing unit 211 is also called a character recognition processing unit. The average luminance value M ₁ is also called the first average gradation value. The average luminance value M ₂ is also called a second average gradation value.

In step S850, the OCR processing unit 211 of the control unit 210 sets the maximum accuracy threshold. The highest accuracy threshold is the threshold at which the integrated value of the recognition accuracy of each input character is the highest. The binarization processing unit 140 executes the binarization processing of the selected area SR using the highest accuracy threshold value, and displays the binarized image after the binarization processing on the user interface screen 231 in real time. Note that, for example, at the user's choice, the target for which the binarization process is performed using the highest accuracy threshold value may be the entire page.

In step S860, the operation display unit 230 accepts user input for fine adjustment processing. In the fine adjustment process, touching the density decrease icon 237d enables fine adjustment to increase the threshold value, and touching the density increase icon 237u enables fine adjustment to decrease the threshold value.

As described above, when the image forming apparatus 10 according to the second embodiment is not satisfied with the result of the automatic processing in the first embodiment, the average brightness value M ₁ and the class 1 of the class 1 are used in a specific area or the entire page. The threshold value with the highest OCR accuracy can be automatically changed between the average luminance value of _{2 and M 2,} and the characters disappeared in the binarization process of the automatic process can be reproduced in the interactive fine adjustment process mode. ..

As a result, the image forming apparatus 10 can easily deal with, for example, an abnormal image (all white or all black), and can realize a user-favorable binarization process. The density decrease icon 237d and the density increase icon 237u are in the range of all gradation values or between the average brightness value M ₁ and the average brightness value M _{2 even when the processes of steps S810 to S850 are not executed.} It is preferable to make it available.

C. Modification example:
The present invention can be implemented not only in the above embodiment but also in the following modifications.

Modification 1: In the above embodiment, the filter used in the low-pass filter processing is a Gaussian filter, but the filter is not limited thereto, and a moving average filter may be used, for example. Further, if it has a property of removing noise from a background image (for example, a background image), it is possible to remove noise such as a DOG (Defense of Gaussian) filter (also referred to as a Gaussian difference filter) and enhance a line image. Bandpass filters are also available.

FIG. 18 is an explanatory diagram showing the contents of the filter processing according to the modified example. FIG. 18A is the same as FIG. 9A, and shows the histogram H1 of the monochrome image data MD1 after the Gaussian filter processing. FIG. 18B shows a histogram H1a of monochrome image data MD1a after DOG filtering. In the histogram H1a, light text is emphasized. As a result, in the threshold setting of the binarization process, it is possible to set an appropriate threshold value that enhances the persistence of the thin text.

Modification 2: In the above embodiment, the luminance gradation value and the luminance histogram are used, but for example, the density gradation value and the density histogram may be used. The density is, for example, the density gradation value of the K color material when printing is performed using the K color material.

Modification 3: In the above embodiment, the present invention is applied to an image forming apparatus, but the present invention is not necessarily limited to the image forming apparatus, and an electron functioning as an image processing apparatus such as an image reading apparatus or a mobile terminal. Applicable to equipment.

10 Image forming device 210 Control unit 220 Image forming unit 230 Operation display unit 240 Storage unit 100 Image reading unit 111 Light source driver 112 Light source 121 Image sensor 122 Light receiving element 123 Signal processing unit 124 Shading correction unit 130 AGC processing unit 140 Binarization processing Unit 141 Filter processing unit 142 Threshold setting unit 150 Document stand 160 Automatic document feeder 162 Document scanning slit

Claims (7)

The first average gradation value, which is the average gradation value of the first class in the discriminant analysis method for the input image data, and the average gradation value of the second class, which is the side containing a relatively large amount of background images. A histogram analysis unit that calculates the second average gradation value, which is
An operation display unit that accepts user input for adjusting a threshold value between the first average gradation value and the second average gradation value, and an operation display unit.
A binarization processing unit that adjusts the threshold value according to a user input input to the operation display unit and executes a binarization process using the adjusted threshold value.
With
The operation display unit is an image processing device that displays the image after the binarization processing in real time according to the operation of the threshold value. The image processing apparatus according to claim 1, further
It is provided with a character recognition processing unit that recognizes characters included in the input image data, calculates the recognition accuracy which is the certainty of the recognition, and calculates the integrated value of the recognition accuracy of each character.
The binarization processing unit sequentially selects the threshold value between the first average gradation value and the second average gradation value.
The character recognition processing unit calculates the integrated value for each of the selected threshold values.
The binarization processing unit is an image processing device that executes binarization processing using a threshold value having the largest integrated value. The image processing apparatus according to claim 1 or 2, further
A filter processing unit that executes filter processing that suppresses background noise in the input image data,
The gradation value at which the number of pixels of the background noise of the filtered input image data is the peak number of peak pixels is defined as the background peak gradation value, and the density becomes darker from the side of the background peak gradation value. On the value side, there is a background noise determination threshold setting unit that searches for a gradation value that is the number of pixels in a predetermined range of the peak number of pixels and sets a background noise determination threshold.
A background noise reduction processing unit that reduces background noise by setting all the gradation values of pixels having a gradation value on the side where the density is lower than the background noise determination threshold value as the background noise determination threshold value.
With
The input image data is an image processing device that is image data in which the background noise is reduced. The image processing apparatus according to claim 3.
The filter processing unit is an image processing device that suppresses the background noise by using a Gaussian filter. The image processing apparatus according to claim 3.
The filter processing unit is an image processing device that executes the filter processing using a Gaussian difference filter. The first average gradation value, which is the average gradation value of the first class in the discriminant analysis method for the input image data, and the average gradation value of the second class, which is the side containing a relatively large amount of background images. A histogram analysis step for calculating the second average gradation value, which is
An operation display process for accepting user input for adjusting a threshold value between the first average gradation value and the second average gradation value, and
A binarization process step in which the threshold value is adjusted according to the user input input in the operation display step and the binarization process is executed using the adjusted threshold value.
With
The operation display step is an image processing method for displaying an image after the binarization process in real time according to the operation of the threshold value. The first average gradation value, which is the average gradation value of the first class in the discriminant analysis method for the input image data, and the average gradation value of the second class, which is the side containing a relatively large amount of background images. Histogram analysis unit that calculates the second average gradation value
An operation display unit that accepts a user input for adjusting a threshold value between the first average gradation value and the second average gradation value, and the operation display unit according to the user input input to the operation display unit. The image processing device is made to function as a binarization processing unit that adjusts the threshold value and executes the binarization processing using the adjusted threshold value.
The operation display unit is an image processing program that displays the image after the binarization processing in real time according to the operation of the threshold value.

Images