JPS62152093A - Character picture binary-coding device - Google Patents

Abstract

PURPOSE:To attain the stable binary-coding by recognizing the contrast level of a background part and a character part white referencing the contrast of a center picture element and plural peripheral picture elements so as to recognize the change in the contrast level of the center picture element with respect to the average value. CONSTITUTION:The contrast of plural peripheral picture elements at a position parted from a noticed center picture element by a prescribed distance, that is, an output of a memory 13 of a 2-dimension part is referenced, the maximum contrast and the minimum contrast of the center element are recognized and the result is set to a maximum value calculation circuit 141 and a minimum value calculation circuit 142. The mean value between the calculated maximum and minimum values is calculated by a means value calculation circuit 143 and an absolute value difference calculation circuit 144 calculates the absolute difference between the means value and the contrast of the noticed center picture element. A comparison circuit 145 subtracts a prescribed threshold value alphafrom the result and binary-coding is applied depending on the presence of the remaining value.

Description

[Detailed Description of the Invention] [Industrial Application Field] The present invention relates to a sensor (image input sensor) that scans a character image area to be read in an optical character reading device.
Regarding the image signal obtained from the character image used for binarization, the signal representing the ground part of the recording medium on which characters are recorded is "0", the signal representing the character pattern part is 1", etc. This relates to a binarization device.

[Conventional technology]

FIG. 4 is a circuit diagram showing a conventional example of a character image binarization device. In the figure, 1 is an image input sensor, 2 is a comparator,
3 is a resistor, 4 is a capacitor, 5 is a variable constant voltage source, and 6 is a resistor.

FIG. 4A is a waveform diagram of each part signal in FIG. 4,
FIG. 4B is an explanatory diagram showing an example of an image to be read. In FIG. 4B, 7 indicates a recording card, 8 indicates a bar code, and S indicates a scanning direction.

The circuit operation for binarizing an input image signal will be described with reference to FIGS. 4, 4A, and 4B.

That is, in FIG. 4, the image input sensor 1
The raw image input signal (a) obtained when scanning the barcode 8 on the recording card 7 along the S direction as shown in Figure B is input to the (+) input side of the comparator 101, and on the other hand, the By passing the raw signal (a) through a low-pass filter composed of a resistor 3 and a capacitor 4, harmonic components are removed to create a reference signal (b) used as a comparison standard, which is then passed through a comparator. Insert it into the (-) input side of 101. (
-) A constant voltage is applied in advance to the input side from a variable constant voltage source 5 via a resistor 6.

In this way, the line image signal (a) obtained by scanning the barcode 8 will be on the (-) input side of the comparator 2.
As mentioned above, the harmonic components are removed and the signal is smooth, so by comparing the levels of the signals (A) and (B) in the comparator 2, the binarized signal (C) is converted to the barcode 8.
is obtained as the read output of

By the way, in the conventional binarization device as explained above,
An image consisting of multiple parallel line segments, such as a barcode,
This is effective when the image input sensor scans from a direction perpendicular to that, but if the scanning direction of the image input sensor is parallel to the line segment that makes up the barcode, the length of that line segment is effective. Depending on the situation, binarization may or may not be possible.

As an extreme example, in the case of a straight line extending in the same direction as the scanning direction of the image input sensor, it cannot be binarized. When the object to be read is not a line segment like a barcode but a character, the line segments that make up the character include components parallel to the sensor scanning direction, components perpendicular to the sensor scanning direction,
Nine diagonal components are mixed, and if a conventional binarization device such as the one shown in FIG. 4 attempts to binarize this, its operation will become unstable.

[Problem that the invention seeks to solve]

Therefore, in the present invention, the object to be read is not an image consisting of line segments arranged parallel to one direction like a bar code, but like a general character, the line segments that make up the image vary in the scanning direction of the sensor. For image patterns that are made up of line segments that form a certain angle, the image signal obtained from the sensor can be converted into a stable binarization operation between the pattern part and the ground part. The problem that needs to be solved is to make it possible, regardless of the situation. Therefore, an object of the present invention is to provide a character image binarization device that makes the above possible.

[Means and effects for solving the problem] In order to achieve the above object, the present invention utilizes a two-dimensional local memory. This two-dimensional local memory pixelizes and quantizes a two-dimensional image signal obtained by imaging with a two-dimensional imaging device such as a television camera, and stores it two-dimensionally in the memory. It is possible to retrieve pixel data in any desired local area of the memory (the inventor has filed a patent application for a convenient two-dimensional local memory in which the possible local area can be changed freely). 1986-
223697).

Therefore, in the present invention, as a local area in the two-dimensional local memory, we consider a local area that is larger than the width of the line constituting the target character pattern, and read out the central pixel and its surrounding pixels in the area as representative surface elements. Then, check the grayscale values of each of these representative surface elements, obtain the maximum and minimum values from them, calculate the intermediate value between the maximum and minimum values, and calculate the grayscale value of the center pixel and this intermediate value. The purpose is to determine whether the center pixel is "0" or "1" depending on whether the difference (absolute value) with the value is greater than or equal to a predetermined value, and to perform binarization.

In other words, in the local area assumed in the present invention, if the central pixel is a pixel on a line segment forming a character pattern, the surrounding pixels will necessarily include pixels corresponding to the background, that is, the ground. thinking.

〔Example〕

The present invention will now be described in detail with reference to the drawings.

FIG. 5 is an explanatory diagram showing an example of a character image to be binarized by the binarization apparatus according to the present invention, and also showing the waveform of an image signal obtained by scanning the image.

That is, the image signal to be converted into 2 (Ii!) by the binarization device according to the present invention is an image signal obtained by scanning general characters (alphabet, hiragana, etc.) as shown in FIG. be.

For example, the waveform of an image signal obtained by optically scanning a line x1 along the main scanning direction is like Sx, and the image signal obtained by optically scanning a line y along the sub-scanning direction. The waveform of the signal is similar to Sy, but unlike the image signal obtained by scanning a code bar as shown in Figure 4A, the DC level on the line segments that make up a character varies depending on the character position. It will be recognized that the value fluctuates greatly, and as described above, it is difficult to perform binarization using a conventional binarization device.

FIG. 1 is a block diagram showing the overall configuration of an optical character reader (OCR) incorporating a binarization device according to the present invention.

In the figure, 11 is a sensor (image input sensor) that optically scans a character image written on a recording medium such as paper and outputs an image signal, and specifically, it is an image reading unit of a television camera or a fax machine. It can be thought of as equivalent to

12 is an A/D converter that quantizes the image signal from the sensor 11 and outputs it as a digital signal of multiple bits (for example, 6 bits, 64 gradations); 13 is the aforementioned two-dimensional local memory; and 14 is a binarization unit. , 15 is a character recognition unit.

As mentioned above, the two-dimensional local memory 13 is explained in detail in the specification of Japanese Patent Application No. 60-223697. This will be explained with reference to the figures.

FIG. 2 is an explanatory diagram showing an example of a possible local area in the two-dimensional local memory 13 and a pixel arrangement representative of the area.

In other words, a partial character image area of (M dots) x (N dots) is designated as a local area, and the central pixel within it is
(represented by a black circle) and surrounding pixels that can be selected arbitrarily, and (represented by a white circle) are considered to be representative surface elements representing the local area, and the quantized values of these pixels are simultaneously calculated. The two-dimensional local memory allows for reading and reference. Therefore, if you shift the center pixel one dot at a time along the scanning direction on the scanning screen, the local area centered on the center pixel will also move in the same way, so any pixel on the entire screen will be shifted one dot at a time along the scanning direction. When a pixel is used, surrounding pixels can be considered, and the quantized value of each pixel at that time can be known.

FIG. 3 is a block diagram showing details of the binarization section 14 (an embodiment of the present invention) in FIG. 1.

In the figure, 141 is a maximum value calculation circuit, 142 is a minimum value calculation circuit, 143 is an average value calculation circuit, 144 is an absolute difference calculation circuit, and 145 is a comparison circuit.

Returning to FIG. 1, the overall circuit operation of the optical character reading device will be briefly described. An image signal obtained by scanning a character image by the image input sensor 11 is quantized for each pixel by the A/D converter 12, and input to and stored in the two-dimensional local memory 13. Next, from the two-dimensional local memory 13, the quantized values (shading values of pixels on the recording medium) of the central pixel as a representative surface pixel representing the local area and its surrounding pixels are read out, and the binarization unit At step 14, the central pixel is binarized and the result is sent to the character recognition section 15. The character recognition unit 15 performs character recognition of the target image scanned by the sensor 11 from the binarized dot (pixel) pattern obtained as described above.

Next, the Sonoji operation of the binarization section 14 as an embodiment of the present invention will be described with reference to FIG.

As already explained, the binarization section 14 has a configuration as shown in FIG. 3. The maximum value calculation circuit 141 simultaneously refers to the output of the two-dimensional local memory 13, that is, the grayscale values of the center pixel of interest and a plurality of surrounding pixels located a predetermined distance away from the pixel, and calculates the maximum grayscale value among them. know. The minimum value calculation circuit 142 similarly knows the minimum gray value. When the target image is a character written in black on a white background such as paper, the maximum value calculation circuit 141 uses the gray scale value of the paper color near the center pixel of interest as the maximum value, and the minimum value calculation circuit 14
2, the shading value of the character color (black) is calculated and set as the minimum value.

The average value calculation circuit 143 calculates an intermediate value between the maximum value and the minimum value calculated as described above, that is, an average value.

The absolute difference calculation circuit 144 calculates the absolute difference between the average value from the average value calculation circuit 143 and the shading value of the center pixel of interest (the opposite of the shading values of the background and character colors, that is, the opposite of black characters on a white background or white characters on a black background). If not, calculate the simple difference).

Next, the comparison circuit 145 uses the output from the absolute difference calculation circuit 144 to take S/N into consideration and prevents slight variations in the shading value in the background (ground part) from being mistakenly recognized as text. A predetermined threshold value α is subtracted from the value α, and binarization is performed depending on the presence or absence of the remaining value.

As described above, stable binarization that can effectively distinguish the character part from the ground part can be performed without being confused by gradual changes in gradation values that may occur in the ground part.

By the way, the binarization force formula according to the present invention can be expressed as follows.

The center pixel of interest is po, the surrounding pixels are p++ pz...
Set to pH. p0 to p are pixels representing the local area AL.

Letting the maximum density value in the local area AL be pIIIIIIX, pH1llX=l, 1. X(po, pl, pz...p
g) If the minimum gray value in the local area AL is pl, then p
, in = 1Ii11(po + pr + p
g...pg) pmax and p. , 7, p.

Then, pm = (pmmx ” pm=n) /
If p is the gradation difference between 2p i and the center pixel of interest p0, then pd = I po - pg 1 If the binarized output at the center pixel of interest p0 is pb, and the setting input (threshold value) is α, then p , becomes as follows.

〔Effect of the invention〕

According to this invention, the background part 1 in the local area is determined by referring to the gray scale values of the center pixel in the local area having a width sufficiently larger than the width of the line segment constituting the character, and the shading values of a plurality of surrounding pixels.
Since the gray level of the text area is known, the degree of change in the gray level of the center pixel relative to the average value is known, and binarization is performed based on this, it is possible to detect variations in the gray level of the background area in the image and the gray level of the text area. This method has the advantage of being able to perform stable binarization that can distinguish between text and background even when there are level fluctuations.

[Brief explanation of drawings]

Fig. 1 is a block diagram showing the overall configuration of an optical character reading device (OCR) incorporating the binarization device according to the present invention, and Fig. 2 shows possible local areas in a two-dimensional local memory and pixels representing the areas. FIG. 3 is a block diagram showing details of the two-dimensional local memory 13 in FIG. 1, FIG. 4 is a circuit diagram showing a conventional example of a character image binarization device, and FIG. 4A is an explanatory diagram showing an example of the arrangement. A waveform diagram showing the waveforms of the input signal and output signal (binarized output), FIG. 4B is an explanatory diagram showing an example of an image to be read, and FIG. An explanatory diagram showing an example of a character image considered as a target for value conversion and the waveform of an image signal obtained by scanning the image,
It is. Explanation of symbols 1... Image input sensor, -2... Comparator, 3...
Resistor, 4... Capacitor, 5... Variable constant voltage source, 6
... Resistor, 7... Recording card, 8... Barcode, 11... Image input sensor, 12... A/D converter, 13... Two-dimensional local memory, 14... 2 (a conversion unit, 15... Character recognition unit, 141... Maximum value calculation circuit, 142... Minimum value calculation circuit, 143... Average value calculation circuit, 144... Absolute difference calculation circuit, 145...Comparison circuit, Agent Patent attorney Akio Namiki Agent Patent attorney Kiyoshi Matsuzaki Figure 1 Figure 2 B: J'J Figure 4B Figure 5 Main pursuit direction (X)

Claims (1)

[Claims] 1) A character image input sensor that decomposes a target character image area into pixels, scans in the main scanning direction and sub-scanning direction, and detects and outputs a character image signal for each pixel; an A/D (analog/digital) converter that inputs the character image signal, quantizes it, and outputs it; and an A/D (analog/digital) converter that receives the quantized signal from the converter and places it on the character image area.
With the pixel of interest as the center pixel, quantized signals for the center pixel and multiple surrounding pixels in a two-dimensional local area selected to have a predetermined size are sequentially output for each pixel of interest in synchronization with the scanning. a two-dimensional local memory to select the maximum value and minimum value from among the quantized signals for the center pixel and peripheral pixels for each local area, and calculate the average value thereof;
and an arithmetic means for calculating the absolute difference between the average value and the quantized signal of the center pixel, and comparing the absolute difference with a certain set value and determining whether the center pixel is to be binarized based on the magnitude relationship. A character image binarization device comprising: binarization means.