JP2637498B2 - Image signal processing device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION [Summary] The present invention relates to an image signal processing apparatus which reads out predetermined information from a manuscript consisting of characters, background and color character entry frames, and a format. Image information conversion means for reading an original as three color image signals and converting them into information of saturation, luminance, and hue; and saturation information obtained by the conversion. And an achromatic / chromatic color determining means for determining whether the achromatic color is a chromatic color by comparing the achromatic color with a predetermined threshold, and comparing the luminance information obtained by the conversion with the predetermined threshold to determine whether the achromatic portion is a background or a character. And a background / character judging means for outputting in accordance with the output of the achromatic / chromatic color judging means, and comparing the hue information obtained by the conversion with a plurality of predetermined thresholds to determine a chromatic color portion. Multi-valued data according to the output of the achromatic / chromatic color determining means And a color determining means for outputting.

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image signal processing apparatus for reading predetermined information from a document including characters, background and color character entry frames, and a format.

[Prior Art] In a banking business or the like, a character reading OCR (Optical Char-
acter Reader) is used. This type of character reading OCR has also been used for reading handwritten characters due to improvements in pattern recognition technology. In this type of apparatus, a character entry frame of a target form (hereinafter referred to as a manuscript) is printed in a dropout color. The dropout color is a color that can be clearly distinguished by the human eye but has a hue and darkness that the OCR sensor cannot distinguish from the background color. If such a dropout color is used for the character entry frame, the character entry frame disappears from the image data read by the OCR, so that the character entry frame and the characters can be separated.

FIG. 5 is a diagram showing a configuration example of a conventional OCR reading unit. In manuscript 1, characters (A, B,
C, D) has been written. In the example shown in the figure, the character information is read line by line in the main scanning direction while moving the original 1 in the sub-scanning direction. One line of the image on the original 1 is condensed by the condensing lens 2, and after removing the dropout color by the filter 3, the CCD image sensor 4
Is input to The CCD image sensor 4 converts the input light into an electric signal and outputs the electric signal. After the electric signal is amplified to a predetermined level by the following amplifier 5, it is converted into digital data by an A / D converter (not shown), and character recognition processing or the like is performed on the digital data.

[Problem to be Solved by the Invention] In the conventional method, it is necessary to select the characteristics of the dropout color and the filter 3 according to the writing implement (pencil or ballpoint pen), and replace the filter 3 according to the color of the dropout color. There was a problem that had to be done. Alternatively, in order to cope with a wide range of dropout colors, it is necessary to reduce the density, and there has been a problem that character entry frames and notes written in the dropout colors become invisible. For example, FIG. 6 shows the relationship between the dropout color and the characteristics of the filter when blue and black ballpoint pens are used as writing utensils.

In FIG. 6, the horizontal axis is the light wavelength, and the vertical axis is the light transmittance versus OC.
R indicates the relative reflectance of paper. f1 is the dropout color (orange), f2 is the ballpoint pen ink (blue),
f3 indicates the relative reflectance of the ballpoint pen ink (black). In order to distinguish between the dropout color and the blue and black of the ballpoint pen from among the reflectances having such characteristics, it is necessary to use a band-pass filter having the characteristic shown in f4 where the three characteristics are different. is there. Within the characteristics of the filter f4, the three reflectance characteristics (especially f1 and f2, f3) are significantly different, so that the dropout color and the ballpoint pen black and blue can be distinguished.

Further, as a disadvantage of the conventional method, the character entry frame 1a is removed from the image data at the time of reading as a dropout color, so that character positioning, character lump (for example, katakana tsu, tsu, n There is a problem that characters cannot be used as information for detecting characters if they can be detected as a lump). For example, by recognizing whether or not the character “S” is in the character entry box, it is possible to recognize for the first time whether or not it is one character.

The present invention has been made in view of such a problem, and an object of the present invention is to provide an image signal processing device capable of reading character information and other information separately.

[Means for Solving the Problems] FIG. 1 is a principle block diagram of the present invention. In the figure, reference numeral 10 denotes an original 11 read as a three-color image signal,
Image information conversion means for converting into luminance and hue information; and achromatic / chromatic color determination means 12 for comparing the saturation information obtained by the conversion with a predetermined threshold to determine whether the color is achromatic or chromatic. , 13 compares the luminance information obtained by the conversion with a predetermined threshold value to determine whether the achromatic portion is a background or a character, and outputs the background / character to be output according to the output of the achromatic / chromatic color determining means 12. The character determination means 14 compares the hue information obtained by the conversion with a plurality of predetermined thresholds and determines the chromaticity portion as the achromatic / chromatic color determination means.
This is a color determination unit that outputs as multi-valued data in accordance with the output of 12. Character information (output 1) is output from the background / character determination unit 13, and character entry frame information (output 2) is output from the color determination unit 14.

[Operation] In the present invention, a document 11 such as a slip is read by the image information conversion means 10 as image signals of three colors, and saturation, hue and luminance conversion are performed. Hereinafter, hue is H (Hue) and saturation is S (Saturatio)
n), and the luminance is represented by V (Value). After performing HSV conversion by the image information converting means 10 and comparing the saturation with the predetermined threshold Ts by the achromatic / chromatic color determining means 12 to divide the image into achromatic and chromatic colors, receiving the luminance information of the achromatic color Background / character determination means
13, the character information is extracted by comparing it with the threshold value Tv according to the output of the achromatic / chromatic color determining means 12. Then, in response to color information of chromatic color by the color determination unit 14, as compared to the multiple thresholds T _H and a binary or multivalue image predetermined in accordance with the output of the achromatic / chromatic color determination unit 12 And output character entry frame information.

FIG. 2 is a diagram showing the distribution of colors in HSV display colors.
After the conversion, the area where the character / background and the character entry frame are located is shown in the HSV coordinate system. That is, since the characters and the background are achromatic, they enter the region of the inner cylinder 16 in the HSV coordinates, and the color character entry frame becomes chromatic, so they enter the region of the outer hollow cylinder 17 in the HSV coordinates. become. The present invention makes use of this property after the HSV conversion, first applies a threshold value with the saturation S, and separates an achromatic character / background from a chromatic character entry frame.

Then, a threshold is applied to the luminance V from the separated achromatic color to distinguish the character from the background. On the other hand, for the chromatic color, a threshold value for dividing the hue H is determined in advance for the representative colors used in the slip as shown in FIG. Identify. Thus, according to the present invention, character information and other information can be read separately. In FIG. 3, the colors are red (of Red), yellow (of Yellow), green (of Green), cyan (of Cyan), blue (of Blue) and magenta (of Magenta). T1 to T5 indicating colors and boundaries between the colors indicate threshold values. The hue H changes in the direction indicated by → in the figure.

[Example] Hereinafter, an example of the present invention will be described in detail with reference to the drawings.

FIG. 4 is a configuration block diagram showing one embodiment of the present invention. On the manuscript 11, there is a character entry frame 11a and characters entered therein. The image processing unit includes an image reading unit 20 and a color identification unit 30. In the image reading unit 20, the original 11
The information read from the lens L1, L2, L3 and the filters F1, F
2. Image signals for three colors are read in line units by using three optical systems including F2 and image sensors CCD1, CCD2, and CCD3. The read signals are the following amplifiers A1, A2, A3, respectively.
After being amplified to a predetermined level, the data is converted into digital data by A / D converters A1, A2 and A3. And the signal line l1
Output from ~ l3.

The color identification unit 30 receives the signals for these three colors,
The converter 31 separates the signals into H, S, and V signals and outputs the signals. Among these signals, the S signal is compared by a comparison circuit 32 with a threshold value Ts for separating achromatic and chromatic colors. The comparison circuit 32 includes, for example, S
If <Ts, it is regarded as an achromatic color and outputs “0”. If S ≧ Ts, it is regarded as a chromatic color and outputs “1”.

On the other hand, the V signal and the H signal are input to the comparison circuits 33 and 34, respectively. The threshold value Tv input to the comparison circuit 33 is for distinguishing the luminance of a character and a background from among achromatic colors, and the threshold value T _H input to the comparison circuit 14 is for distinguishing colors. . Threshold T _H, as will be inferred from FIG. 3, it is not necessary character entry box to distinguish if one color. One threshold is used for two colors, and two thresholds are used for three colors. The threshold and the number n of the thresholds are determined in advance according to the number of colors used for the slip, such as five thresholds for six colors.

The comparison circuit 33 compares the input V signal information with a threshold value Tv, and if the V signal <Tv, outputs the signal as "1" as a character.
If signal ≧ Tv, “0” is output as the background. Further, this output signal is supplied to a multiplexer controlled by a comparison circuit 32.
The achromatic portion is output as it is by 35, but the chromatic character entry frame portion is forcibly selected and output as "0" input to the other side of the multiplexer 35. Therefore, the character entry frame portion is removed in the same manner as read using the dropout color.
Is provided to a subsequent character recognition unit (not shown).

The comparison circuit 34 compares the input H signal information with a plurality of predetermined thresholds T _H as described above, and converts the H signal into n values and outputs the signal. For example, when six colors are distinguished as shown in FIG. 3, each color is represented by six values as compared with threshold values T1 to T5. Next, the chromatic portion of this output signal is output as it is by the multiplexer 36 controlled by the comparison circuit 32, but “0” input to the other end of the multiplexer 36 is output in the achromatic character entry frame portion. Forced selection,
It is output as a signal having a total of seven values. The output of the multiplexer 36 is a character entry frame reference section (not shown) at the subsequent stage.
Given to.

In the above description, the case where five threshold values are used to multi-value the hue information H is taken as an example. However, the present invention is not limited to this, and it is possible to use a threshold value less than or greater than that. It can be multi-valued.

[Effects of the Invention] As described above in detail, according to the present invention, the character / background and the character entry frame are separated by comparing each color component obtained by performing the HSV conversion on the read image information with a predetermined threshold value. And an image signal processing device capable of reading out the data.

[Brief description of the drawings]

FIG. 1 is a block diagram showing the principle of the present invention, FIG. 2 is a diagram showing a color distribution in the HSV color system, FIG. 3 is a diagram showing a relationship between a hue distribution and a threshold for dividing the hue, and FIG. FIG. 5 is a block diagram showing a configuration of an embodiment of the present invention, FIG. 5 is a diagram showing a configuration example of a conventional OCR reading unit, and FIG. 6 is a diagram showing characteristics of a filter which can use a ballpoint pen. In FIG. 1, reference numeral 10 denotes image information conversion means, 11 denotes an original, 12 denotes achromatic / chromatic color judgment means, 13 denotes background / character judgment means, and 14 denotes color judgment means.

 ────────────────────────────────────────────────── ─── Continuation of the front page (56) References JP-A-56-2073 (JP, A) JP-A-53-106521 (JP, A) JP-A-62-172468 (JP, A)

Claims (1)

(57) [Claims] An image information conversion means (10) for reading an original (11) as image signals of three colors and converting the same into respective information of saturation, luminance and hue; Achromatic / chromatic color judging means for judging whether an achromatic color or a chromatic color by comparing with a threshold of (12)
And comparing the luminance information obtained by the conversion with a predetermined threshold value to determine whether the achromatic portion is a background or a character, and outputs the background according to the output of the achromatic / chromatic color determination means (12). Comparing the hue information obtained by the conversion with a plurality of predetermined thresholds, and converting the chromatic portion into multi-valued data according to the output of the achromatic / chromatic color determining means (12). An image signal processing apparatus comprising: a color determination unit (14) for outputting as coded data.