JPH0432979A - Image processor - Google Patents

Abstract

PURPOSE:To use a color pen which is put on the market and to decrease errors in color discrimination by providing a function which detects the color characteristics of a color pen and selects a color pen having the detected color characteristics. CONSTITUTION:This image processor is provided with an image input part 1 which scans a color mark and/or a document and a drawing entered into a form and outputs a color image signal and a color characteristic decision part 3. Then the color characteristic decision part 3 detects the color characteristics of the color mark according to the image signal, decides the similarity between the detected color characteristics, and selects only a color pen having nonsimilar color characteristics. Consequently, the color pen which is put on the market can be used and errors in color discrimination are decreased.

Description

[Detailed Description of the Invention] [Industrial Field of Application] The present invention provides documents, drawings, and/or drawings created using color pens.
The present invention also relates to an image processing apparatus that performs image processing on a drawing of a document to which additional marks have been added using a color pen, and particularly to an image processing apparatus that has a function of selecting usable color pens.

[Prior art]

Conventionally, as a technology in this type of field, the journal of the Institute of Electronics and Communication Engineers
April 1985 Vol, J68-D No. 4 No. 8
``Automatic recognition of multicolor drawings using real-time color coding techniques'' disclosed on pages 29-836. In this technology, as a method to obtain color-coded images for recognizing multicolor diagrams, the distribution of gray values of each pixel input divided into limited spectral bands and the distribution of the ratio of these values are used as indicators. Color identification was performed using

Furthermore, in order to improve the identification accuracy for the shading and color unevenness of the described colors, the parameters used in the method have been expanded and modified through numerous experiments.

[Problem to be solved by the invention]

However, there are many types of color pens available to Document 2 drawing creators, including colored pencils, color ballpoint pens, color felt-tip pens, color marker pens, and color fluorescent pens, and even color pens that display the same color may have different color characteristics depending on the color pen manufacturer. In addition, even if the same color pen is used, the occurrence of shading and color unevenness often differs depending on the type of color pen and/or writing conditions. Therefore, if the user of the device uses a color pen freely selected based only on the color name presented in the device specifications, there is a problem that errors in color identification may occur.

Therefore, there is a problem in that the user is forced to use a color pen recommended by the device provider.

The present invention has been made in view of the above-mentioned problems, eliminates the above-mentioned problems, enables the use of commercially available color pens without being limited to the color pens recommended by the device provider, and makes it possible to avoid errors in color identification. It is an object of the present invention to provide an image processing device with excellent processing ability that can reduce the amount of image processing.

[Means to solve the problem]

In order to solve the above-mentioned problems, the present invention provides an image processing apparatus that performs image processing on a drawing of a document created using a color pen and/or a drawing of a document created with a postscript mark using a color pen. Color marks and/or documents as mentioned above.

An image input unit that scans a drawing and outputs a color image signal; and an image input unit that detects the color characteristics of color marks based on the color image signal, determines the degree of similarity between the detected color characteristics, and determines the similarity between similar marks. The present invention is characterized in that it is provided with a color characteristic determination section that issues a warning when the color characteristic is detected.

[Effect]

In the present invention, as described above, the image processing device is provided with an image input section having the above functions and a color characteristic determination section, so that the color characteristic determination section detects the color characteristics of the color mark based on the color image signal. Since the degree of similarity between the detected color characteristics is determined and only color pens with dissimilar color characteristics are selected, the use is not limited to color pens recommended by the device provider, and commercially available color pens can also be used. At the same time, it becomes possible to reduce errors in color identification.

〔Example〕

Hereinafter, one embodiment of the present invention will be described based on the drawings.

FIG. 1 is a block diagram showing the configuration of an image processing apparatus according to an embodiment of the present invention. As shown in the figure, this image processing apparatus has a configuration including an image input section 1, a mode switching section 2, a color characteristic determination learning section 3, and an image processing section 4.

The image input unit 1 scans the color characteristic learning paper, document 2 drawing, and/or document 2 drawing with additional marks as shown in FIG. 3, with the main scanning in the horizontal direction (XX) and the sub scanning direction (YY). , color image signals, such as R (red), G (green), B
(Blue) multilevel signal is output to the mode switching section 2.

The mode switching unit 2 switches between a color characteristic determination learning mode and an original reading mode using a switch (not shown) or the like. When the mode switching unit 2 is in the color characteristic determination learning mode, it outputs the output of the image input unit 1 to the color characteristic determination learning unit 3, and also outputs a determination activation signal. Furthermore, when the mode switching section 2 is in the document reading mode, it outputs the output of the image input section 1 to the image processing section 4 and outputs an image processing activation signal.

The color characteristic judgment learning section 3 starts processing in response to the judgment activation signal from the mode switching section 2, and determines the color characteristic based on the color image signal obtained by scanning the color learning paper as shown in FIG. It detects, stores, and determines the degree of similarity between the detected color characteristics and issues a warning for similar marks.

In addition, when all the similarity judgments on the color characteristic learning paper have been completed and there are no similar marks, the color characteristic judgment learning section 3 uses the stored color characteristic for image processing. Register as.

If similar marks exist, display the number of the similar marks (for example, the sequence number of the marks on the color characteristics study paper) on the printer, CRT, etc., and delete one of the similar marks. and register the other.

Note that the stored color characteristics may be displayed in a format such as the chromaticity diagram shown in FIG. 2, and the color characteristics to be registered or deleted may be determined.

The image processing unit 4 starts operating in response to an image processing activation signal from the mode switching unit 2, and processes the document 9 drawing image on the original based on the color characteristics registered in the color characteristic determination learning unit 3. Perform image processing according to the purpose of use.

FIG. 2 is an explanatory diagram of a chromaticity diagram used for color characteristic determination and registration by the color characteristic determination learning section 3, and schematically shows the color range of the original and/or the color characteristic learning paper. Furthermore, the second
The chromaticity diagram in the figure is a schematic diagram created by a known method, in which the RGB multilevel signal is converted to the xyz system using coordinate conversion formula (1), and X = 2. .7689R+1.7517G +1.13
02BY = R+ 4.5907 G +0.
0601 BZ= 0.0565G+5.5
943B (1) Based on the obtained x, y, z, calculate the color coordinates x, y using formula (2), x=X/(X+Y+Z) V=Y/(X+Y+Z) (2 ) Using orthogonal coordinates based on the determined chromaticity coordinates x and y. The x and y represent hue and saturation, and Y represents lightness.

The above-mentioned conversion from RGB system to XYZ system (based on equation (1)) and calculation to obtain x and y for hue and saturation (based on equation (2)) require R, G, and B multi-level signals to be input, respectively. death,
Using a ROM that outputs X, Y, Z, and
By inputting and converting using a ROM that outputs X and 7 in integer format, calculation time is unnecessary and processing speed can be increased.

FIG. 3 is a diagram showing an example of a color characteristic study paper, and the same figure (
Figure a) is an example of a color characteristics study sheet that has pre-filled spaces for filling in marks, and (b) is an example of a color characteristics study sheet that does not have the spaces but can be filled in under predetermined conditions. Examples of study forms for filling in marks for learning color characteristics are shown below.

In FIG. 3(a), mgl, mg2. mg3,...
...... is a rectangular entry frame with a size of (ΔXX, Δyy), and the origin of the study paper (0°0) has the apex of the entry frame at a predetermined distance (xx+-yy+). ,yyx
It is assumed that black has been printed in advance at a pitch of .

Note that the color, shape, number, and positional relationship of the entry frames are as specified in the third section.
The present invention is not limited to that shown in Figure (a).

An example of the entry conditions in FIG. 3(b) is as follows.

- Use paper with similar characteristics to the original from which the image will be extracted.

■Learning marks should be written at a distance so that they do not touch each other.

Note that the same desired color as the mark used for image extraction of the manuscript should be written on the study paper prior to reading.

The mark g1 written on the color characteristics learning sheet in Figure 3 is red, g
3 is blue, g4 is yellow, g5 is yellow-green, and g6 is purple.

FIG. 2 schematically shows the position of the mark on the chromaticity diagram.

Next, the operation of the color characteristic determination learning section 3 will be explained using FIGS. 2 and 3. Here, the type of color characteristics learning sheet to be used (study sheet shown in Figure 3 (a) or (b)) and the color, shape, positional relationship and rules of the entry frames of the color characteristics learning sheet are determined in advance by color characteristics judgment. It is assumed that this is set in the learning section 3. Further, the color characteristics to be learned may be learned using any known color characteristics, but in the present invention, learning is performed using the chromaticity diagram shown in FIG. 2, and the chromaticity coordinates x, y
It is assumed that a chromaticity diagram is constructed using a two-dimensional memory (color map) whose addresses are integer values X% and y% obtained by multiplying by 100, for example.

In the following description, to avoid confusion with X, Y, and Z representing color characteristics, the coordinate system of the paper plane will be expressed as Xx1 for the main scanning or horizontal direction, and YY for the sub-scanning or vertical direction.

The coordinates on the paper and the coordinates during scanning usually do not match, but to simplify the explanation, we will use the upper left corner of the paper as the scanning start point (origin (0,0)) and the lower right corner as the scanning end point. (
Assume that scanning is performed using a coordinate system of X mad m F ' □).

When the color characteristics learning sheet shown in FIG. 3(a) is scanned, and the scanning point is within the entry frame (input frame determination) and the color characteristics of the scanning point is a chromatic color, the color characteristic study sheet shown in FIG. The RGB multi-level signal input from the image input unit 1 is converted into chromaticity coordinates X and F using the above equations (1) and (2).
Furthermore, X% is converted into an integer.

When the output of the color map whose address is y% is "0", the color characteristic number i is saved.

If the output of the color map whose addresses are X% and y% is not l''OJ, the color characteristic number i is superimposed on the color map and saved, and an alarm is output.

Note that after learning the color characteristics of all marks, the color map may be referred to, it may be determined whether two or more color characteristic numbers on the color map exist, and a warning may be output.

Here, it is assumed that the color map is initialized to "rO" prior to learning.

In the above explanation, the fact that the color map output is not "O" means that the mark that has already been learned and the mark that is currently being learned share the same color map area, that is, they are similar; It means that two or more marks are indistinguishable.

In FIG. 2, it is determined that the yellow-green mark g5 indicated by the diagonally upward line to the left and the yellow mark g4 indicated by the diagonally upward line to the right are similar, and among the pens that have written mark g4 or mark g5. , outputs a warning to make one of the two unusable.

Note that the determination as to whether the color is a chromatic color or not is performed using a known method, for example, R
, G, and B have different multilevel signal levels. Further, the color characteristic number i is obtained from the coordinate values of the scanning point.

In the case of the color characteristic learning sheet shown in FIG. 3(b), the process of determining the entry frame is deleted, and the process can be performed in the same manner as described above. However, the color characteristic number i has a color other than white in the previous sub-scanning line, for example, a chromatic color, and on the current sub-scanning line,
This can be achieved by configuring to add a +1 coefficient when there is no chromatic color other than white, for example.

In the above explanation, the degree of similarity was determined using a chromaticity diagram, but the degree of similarity may also be determined using the frequency distribution of R, G, and B signal levels as shown in FIG. .

Next, a method for determining similarity and selecting color pens using a frequency distribution as shown in FIG. 4 will be described.

As in the previous explanation, the color characteristics study paper shown in Fig. 3(a) is scanned with main scanning in the horizontal direction (XX) and sub-scanning in the vertical direction (YY), and if the scanning point is within the enlarged frame i. (filling frame determination), if the color characteristics of the scanning point are chromatic, the RGB input from the image input unit 1 via the mode switching unit 2
The multilevel signal of the system (St+rxx,yv>tSa
l<xx, vr> + S *+.

X, YY) ) for R, G, and B independently for each signal level is totaled for each entry frame (color characteristic) i, and a frequency distribution table is created. FIG. 4 is a frequency distribution diagram that simulates the frequency distribution table so that it can be visually confirmed.

When the scanning of the color characteristic learning sheet is completed, the average value S□+SGITSII and the standard deviation σ□ are calculated for each entry frame i.

σ63. Find σ□ and calculate the signal level distribution range S11+±N, σlI, SGI±N, σClll5 for each R, G, and B.
Calculate II N, σ, . However, although it is normally desirable to set N to 3, it may be determined based on the allowable value of noise appearing in the mark image and/or document 1 drawing image separated and extracted by the processing of the image processing unit 4.

Next, the similarity of the colors of the marks in the entry frames is determined based on whether there is a common area in the R, G, and B distribution ranges of the entry frames.

If there is no common area in either R, G, or B, the color of the mark in the enlarged frame i is not similar to any mark other than the mark in the entry frame i, so the color marker used to enter the mark in the corresponding entry frame i is shall be available for use.

When R, G, and B all have a common area, the color of the mark in the entry frame i and the color of the mark in the entry frame j that has the common area are similar to each other, so it is not necessary to write in the corresponding entry frame. Only one color pen can be used among the selected color pens.

In Figure 4, the mark in frame 2 and the mark in frame 3 have a common area indicated by diagonal lines upward to the left for R, G, and B, so a color pen cannot be used in either frame and a warning is issued. Output.

In the method described above, the distribution of R, G, and B signal levels is determined independently to determine the similarity of color marks, but the output R of the scanning point
, G, and B signals may be expressed as vectors, and the similarity may be determined based on the distribution characteristics of RGB in a three-dimensional space.

Note that the above-described determination of the similarity of marks is not limited to the above-described method.

Further, the output of the alarm and the designation of usable pens in the above description are realized by using a lamp, a printer, a CRT, a keyboard and a mouse, a tablet, etc.

Furthermore, the aforementioned chromaticity diagram, distribution diagram, etc. may be displayed on a CRT or printer.

〔Effect of the invention〕

As explained above, according to the present invention, an image processing apparatus that performs image processing on a document 2 drawing created using a color pen and/or a document 2 drawing on which a postscript mark is applied using a color pen; By adding a function that detects the color characteristics of the color pen in question and selects only the color pens that have the detected color characteristics, you are not limited to the color pens recommended by the device provider, and can also use commercially available color pens. In addition, since errors in color identification can be reduced, it is possible to provide an image processing device with excellent processing performance from the standpoint of the device user.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing the configuration of the image processing device of the present invention, FIG. 2 is an explanatory diagram of color characteristics using a chromaticity diagram, and FIG. 3 is a diagram showing an example of a color characteristics learning sheet. 4(a) is a diagram showing a study paper with a frame for writing in, FIG. 4(b) is a diagram showing a study paper without a frame for writing in, and FIG. 4 is an explanatory diagram of the signal level distribution of the mark portion. In the figure, 1: image input unit, 2: mode switching unit, 3: color characteristic determination learning unit, 4: image processing unit. Figure 1 Figure 2 Level 45 of the 7-7 stem Now □Barouro Figure 4'l! PrA1 Study 7FI Ne's Shocking 1 Yuan 4 Mouth 3rd
figure

Claims (1)

[Scope of Claims] An image processing device that performs image processing on documents and drawings created using color pens and/or documents and drawings with addendum marks added using color pens; colored marks and/or documents,
an image input unit that scans a drawing and outputs a color image signal; and an image input unit that detects the color characteristics of the color mark based on the color image signal, determines the degree of similarity between the detected color characteristics, and identifies similar marks. An image processing device characterized by comprising: a color characteristic determination unit that issues a warning against the color characteristic determination unit.