JPH03225477A - Image processor - Google Patents

Abstract

PURPOSE:To perform desired image processing on a desired area by applying the image processing to a document drawing image according to a processing function corresponding to a classified color. CONSTITUTION:A mode switching part 2 is set at a learning mode, and a color command sheet in which the processing function corresponding to the color of a color pen is defined is read prior to the reading of an original, and after the color characteristic of the color pen described on the color command sheet is learned, learned color characteristic and the processing function are registered as a pair. Next, the mode switching part 2 is switched to an original reading mode, and a color mark described additionally on the original is separated from a document/drawing, and is extracted, and the color mark is classified by every color, and an image processing part 4 performs the image processing on a document/drawing image according to the processing function corresponding to the classified color. Thereby, it is possible to perform the desired image processing on the desired area.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to an image processing device, and particularly to an image processing device that reads a document/drawing in which a color mark of a different color has been added, and processes the image processing device according to the color of the color mark. The present invention relates to an image processing device that performs correspondingly defined processing on documents/drawings.

[Prior Art] Conventionally, the following is a method of reading a document with additional marks added using a pen of a different color from that of the document/drawing (hereinafter referred to as a blade pen) and performing different processing on the marked area and other areas. There are three known methods.

(1) The first method is the method disclosed in Japanese Patent Application Laid-Open No. 58-114280, in which markings are applied in different colors to the parts of the input drawing where the reading resolution is desired to be increased, depending on the accuracy of the resolution. However, this is a method of reading at a resolution different from that used when reading the roughened area where the marking part is detected.

(2) The second method is a method disclosed in Japanese Unexamined Patent Publication No. 58-60876, in which image information on a document having an area filled with a specific color and the area are read, and an image within the area is read. This is a method of performing processing on information that is different from image processing performed on image information outside the area.

(3) The third method is to display an image of the entire document scanned without adding marks on a CRT, specify the area using a mouse or tablet, and then perform different processing for each area. This is a method of applying

[Problems to be Solved by the Invention] However, the above-mentioned method (1) is limited to one type of processing, and therefore has the problem that the field of application is limited and lacks versatility.

In addition, method (2) not only specifies the color of the mark, but also requires setting the processing mode manually from the console panel. There is a risk that the processing function will be misunderstood.

Furthermore, when the number of processing functions increases, there is a problem that the machine operation becomes complicated.

Although method (3) is highly versatile, it is not possible to perform real-time processing, and it is necessary to specify the area in addition to setting the processing functions. The problem is that it requires a number of operations.

The present invention has been made to solve the above-mentioned three problems, and provides a human-friendly image processing device that is highly versatile, has excellent operability, and can be implemented with simple processing and configuration. The purpose is to

[Means for Solving the Problems] The image processing device of the present invention includes an image input section that outputs image information corresponding to the color and/or shading of an image on a document, and a learning mode using the image information as an input signal. a mode switching section for switching between the document reading mode and a predetermined color command paper set to define a processing function to be applied to an image of one document/drawing when the mode switching section is set to the learning mode; a color command setting section that reads area information as color characteristics and registers it together with a code corresponding to the processing function; and when the mode switching section is set to document reading mode, output from the image input section. Image processing that separates and extracts image information into a document/drawing image and a mark image, and performs processing corresponding to the color characteristics registered in the color command setting section on the separated and extracted document/drawing image. It has a section.

[Function] In the present invention, the mode switching section is set to learning mode, and a color command sheet that defines processing functions corresponding to the color of the color pen is read prior to reading the document, and the color pen written on the color command sheet is read. After learning the color characteristics of , the learned color characteristics and the processing function are registered as a pair.

Next, the mode switching section is switched to document reading mode, the color marks added on the document and the document/drawing are separated and extracted, the color marks are classified by color, and the document is read according to the processing function corresponding to the classified color. / Operates to perform image processing on drawing images.

[Example] An example of the present invention will be described in detail below based on the drawings.

FIG. 1 is a block diagram showing one embodiment of the present invention. The image processing apparatus according to the present invention includes an image input section 1 that inputs image information from a document or color command paper and outputs it to the next stage, a mode switching section 2 that receives the output of the image input section 1 as input, and a mode switching section 2 that inputs image information from a document or color command paper and outputs it to the next stage. It consists of a color command setting section 3 that receives the output from the section 2 and sets color commands, an image processing section 4 that performs various image processing, and a result storage section 5 that stores the processing results of the image processing section 4. ing.

The image input unit 1 receives color information corresponding to the shading and color of marks written on paper (not shown) or documents/drawings, such as a density multilevel signal or a multilevel signal of the three primary colors of red, green, and blue. Output.

The mode switching unit 2 is switched to a learning mode or a document reading remote mode by a switch (not shown) or the like.

Here, if the mode switching section 2 is set to the learning mode, the image information from the image input section 1 is output to the color command setting section 3, and the color command setting section 3
Outputs a setting start signal to start processing. In addition, when the mode switching section 2 is set to the document reading mode, the image output from the image input section 1 is output to the image processing section 4, and image processing is activated to start the processing of the image processing section 4. Output a signal.

The color command setting unit 3 starts operation by setting activation (No. 8), selects only the color information of a predetermined area of the input paper, recognizes the color information as a color characteristic, and selects the color information defined in the predetermined area. It is registered along with the code corresponding to the processing function to be applied to the image of the document/drawing.The color characteristics registered here may be the density multilevel signal mentioned above, red (R), green (G), etc. , blue (B).Also, the signal is not limited to these, and can be converted into other known color characteristics and registered.

In addition, in the following examples, the known coordinate transformation formula (1
) to convert to the XYZ system, and x, y, found from
Calculate x and y using equation (2) based on z, and obtain the obtained X and y.

Register Y as a color characteristic.

Here, x, y, and z are called tristimulus values as defined by JIS.

Further, x and y represent hue and saturation, and Y represents lightness.

The conversion formula (1) from the RGB system to the XYZ system and the calculation formula (2) for calculating x and y representing hue and saturation are as follows.
RO that inputs R, G, and B and outputs XY and Z.
Conversion is possible by using M, inputting XYZ, and using a ROM that outputs x and y in integer format.
This configuration eliminates the need for calculation time,
It becomes possible to speed up the processing.

Next, an example of color characteristic registration will be explained. x converted into an integer,
Construct a chromaticity diagram as shown in Figure 3(a) using a two-dimensional memory whose address is y, and set one point in the two-dimensional memory determined by the obtained integer x and y to "1". By doing so, color characteristics corresponding to hue and saturation are registered.

Note that the initial value of the two-dimensional memory mentioned above is 110 I+. Furthermore, the brightness Y is registered by updating its minimum and maximum values for each scanning point (pixel).

In addition, the processing function to be applied to the image of the document/drawing defined in a predetermined area may be determined based on the document/drawing to be processed, and the coat corresponding to the processing function may be determined based on the processing function. Any type of material may be used as long as it can be attached. For example, the numbers may be assigned in ascending order starting from the integer 1 in order of the positional coordinates of the areas set on the color command paper.

The image processing section 4 starts operating in response to an image processing start signal, and processes the color characteristics calculated from the color information output from the image input section 1 via the mode switching section 2 and the colors registered in the color command setting section 3. Image information is separated and extracted into one document/drawing image and a mark image based on the characteristics, and processing corresponding to the color characteristics that match the color of this mark is applied to the document/drawing image, and the results are Store it in the storage unit 5.

FIG. 2 is an explanatory diagram of color command paper used in the present invention. This color command paper has a name f+(x=1.
2.3,...) and f.

and a pair of frames mz+(i=1.2.3, . . . ) representing color command entry areas. Usually f1. mzl is printed or written in black.

It is assumed that the color, shape, number of fl and m21, and the correspondence between the position of the frame m21 and the processing function are defined in advance within the apparatus. Furthermore, the correspondence relationships between the colors, shapes, and numbers of fi, mz+, the positions of frames m and 1, and processing functions are not limited to those shown in FIG.

In FIG. 2, the frame m21 is yy2.
The upper left corner point of the first frame is at the position xx, and hereafter Fd
dXX, dyy+ repeatedly set at a distance of y yz
It is a rectangular area with a size of .

Prior to reading, the inside of this rectangular area is painted with a color pen of a desired color.

Note that if the inside of the rectangular area is not painted with a color pen, the process corresponding to this rectangular area is not used. If the background of the paper is white, whether or not the inside of the rectangular area is painted with a color pen is determined by the image input section l.
The output signal I,G.

The determination can be made based on whether there is a difference in the signal level of B and whether it is equal to or greater than a predetermined value.

Also, by defining that the color command entry area is white, the original document/drawing is an achromatic color of black, gray, or white, and the color command to be added is a chromatic color, the restriction on the color type of the color pen to be used is removed. can do.

As is clear from the explanation given in Figure 2, the color command paper in Figure 2 defines only the marks to be added, so it does not contain the characters, figures, photographs, etc. that appear in manual documents/drawings. was designed assuming that it is achromatic colors such as black and gray, and that the background is white.

FIG. 3 is an explanatory diagram of the color characteristics when the color information output from the image input section 1 is converted into the XYZ system, and the background part is white and the text, figures, and photographs are black or gray in the document/drawing. This is a simulated representation of the color characteristics of a document with red marks added.

Note that Y, x, and y shown in the figure are based on the above-mentioned formula (1) and (2).
) was calculated using the formula. It can be seen that even if the written write-once marks have many variations in shading and cannot be distinguished from documents/drawings based on the brightness Y alone, they can be distinguished on the chromaticity diagram in which y is represented on the vertical axis and X is represented on the horizontal axis.

FIG. 4 is a block diagram showing the detailed configuration of the color command setting section 3. As shown in FIG. As shown in FIG. 4, the color command setting section 3 includes a format setting section 31, a color characteristic learning section 32, and a color command registration section 33. The format setting section 31 sets the color command witness area m2. of the color command paper shown in FIG. The position and area information on the paper and the processing function corresponding to the information are set in advance. The format setting section 31 then outputs the position and area information to the color characteristic learning section 32 and color command registration section 33, and each processing function 451 (1=1.2...n) of the image processing section 45, which will be described later. Information for operating the color command register 33 is output to the color command registration section 33.

The color characteristic learning section 32 adjusts the image input section 1 manually via the mode switching section 2 based on the position and area information input from the formant setting section 31 and the position information of the scanning point of the image input section 1. The color information is learned and outputted to the color command registration unit 33 as color characteristics.

Note that the above-mentioned color characteristics are obtained as follows. RGB multi-value data, which is color information from the image input unit 1 input via the mode switching unit 2, is converted into Y, x, y using the above-mentioned equations (1) and (2), Regarding Y corresponding to brightness, the maximum value Yl+maX and minimum value yl+al□ within the area are determined for each color command specified area.

Next, regarding x-y, for example, the integer value X% (=xX100) converted into a 100th fraction (%), y% (=yxlOO
) and (y%) on a two-dimensional memory (color map) with an address where the maximum value of the
, y%) and stores the number 1 (1, 2, . . . n) assigned to each color command designated area.

This color map and YlmIn, Yl, . . . x are output to the color command registration unit 33 as color characteristics.

The color command registration unit 33 determines that the color characteristics output from the color characteristic learning unit 32 are registered in the image processing unit based on the position information of the scanning point of the image processing unit 1 and the device and area information constituted by the format setting unit 31. 45 is to be activated, and the color characteristics and an image processing code for activating the corresponding function of the image processing section are registered as a color command.

FIG. 5 is a block diagram showing the detailed configuration of the image processing section 4 shown in FIG. 1. In the figure, 41 is an image classification section,
Information 33S1 regarding the color characteristics Rta of the RGB multi-valued image 2S input from the image input unit 1 via the mode switching unit 2 to the color command registration unit 33
The signal is separated into a mark image signal and a document image signal based on the image signal.

For mark images, the order code corresponding to the registered color characteristics (for example, if the registered color characteristics are three colors, 1.2.
3) and output it as a mark image signal, and for one document/drawing image, the background part and mark part are LL Q 11
, characters, graphics, and photographs are set to '1', and two-color image data is output as a document image signal.

Next, the processing for obtaining the mark image signal and document image signal mentioned above will be explained. It is assumed here that the background of the document is white, the characters, figures, and photographs are achromatic black, and the marks are chromatic.

First, the RGB multi-value data of the image input unit 1 input via the mode switching unit 2 is calculated using the above-mentioned equations (1) and (2).
Convert to Y, x, y using the formula. Then converted Y
, x, y, and the color characteristics registered in the color command registration section 33, a one-document image signal and a mark image signal are output.

The document image signal is set to l]-TI when Y, x, and y satisfy the following condition 1, and it is set to it O+1 when not.

(Condition 1) As shown in Figure 3(b), Y is a character,
The value (number) of a point on the color map whose address is an integer value (XX, y%) obtained by converting x and y into 100 parts within the brightness range of the figure is O.

In addition, Y, x, and y of the mark image signal are as follows.

When condition 2 is satisfied, the number that satisfies that condition is 11 i I+
If not satisfied, set II O11.

(Condition 2) Integer values (XX, y
%) is the value (number) of the point on the color map whose address is
is a numerical value 1 other than O, and Y is a lightness range Y corresponding to the color of said l+++In and Y.

In between.

The mark image storage unit 42 is configured so that the main scanning direction of the image input unit 1 is
The mark image signal is a two-dimensional button memory whose Y axis is the axis and the sub-scanning direction, and the above-mentioned mark image signal is placed at the positions where the main scanning point XX and the sub-scanning point YY of the image input section 1 are the X address and the Y address, respectively. Save as a color label.

The document image storage section 43 is a two-dimensional binary pattern memory having the same coordinate system as the mark image storage section 42, and stores the main scanning point XX and sub-scanning point YY of the image input section 1 at an X address, respectively.
The document image signals described above are sequentially stored at the positions designated as the Y address.

The document image classification extraction unit 44 simultaneously scans the mark image storage unit 42 and the document image storage unit 43, and extracts document images within the area sandwiched between the same label numbers on the main scanning line 2 of the mark image storage unit 42. At the same time, it outputs an activation signal for activating the processing function of the image processing section 45 corresponding to the label number.

The image processing section 45 performs processing on the document image output from the document image classification and extraction section 44 based on the actuation signal, and stores the processing result in the processing result storage section 5 shown in FIG.

Next, the operations of the color command setting section 3 and the image processing section 4 will be explained in detail with reference to FIGS. 2 to 9.

First, the processing steps of the color command setting section 3 and the image processing section 41 will be explained. In addition, in the following explanation, the coordinate system of the paper plane in the figure will be referred to as
, Y, and Z, the main scanning direction or horizontal direction is expressed as XX, and the sub-scanning direction is expressed as YY.

FIG. 6 is a section showing the processing process of an embodiment of the present invention.
In the figure, step STI, 2 indicates the scanning order of the image input unit 1, and indicates that the paper is sequentially scanned with the horizontal direction XX of the paper as the main scanning direction and the vertical direction YY of the paper as the sub-scanning direction. In the following explanation, the upper left end of the paper is taken as the scanning start point [additional points (Cl, O)), and the lower right end is taken as the scanning end point (x).

6, 3'a++d), and it is assumed that the mark image storage section 42 and the document image storage section 43 are configured with the same coordinate system and operate synchronously.

In step ST3, if the mode switching section 2 is set to the learning mode, the color command setting section 3 sets the color characteristics and/or background corresponding to the color and shading of the mark to be added to the document by the process of step 5TIO111. Document 1 The color characteristics corresponding to the colors and shading of the drawing are registered.

First, in step 5TIO, it is determined whether the scanning point is within the color command registration area by comparing the coordinate data indicating the color command registration area set in advance in the color command setting section 3 with the coordinates of the scanning point. do.

In the example shown in FIG. 2, it is determined that the scanning point is within the color command registration area when the coordinate values XX, YY satisfy the following equation (3).

yy2+β+dyyz *(i-1)≦YY≦yy2+
dyy□〜β Here, β is the allowable setting value for the scanner and paper,
A constant determined based on the color characteristic mark writing conditions, etc., and i each indicate a color command setting area number.

In step 11, the RGB color information of the image input unit 1 input via the study paper/manuscript identification unit 2 is input as described above (1).
Convert to the XYZ system using the formula, convert the x and y obtained using the formula (2) into integers, and use the Y, x, and y to convert the first
The color characteristics being learned are updated as described in the explanation of the figure. In step ST3, if the mode switching section 2 is set to the original or manuscript reading mode, the operation of the image classification section 41 is started. In step 5T12, if the color characteristics of the scanning point are within the range of color characteristics registered in the color command setting section 3, that is, the RGB color information of the image input section 1 input via the mode switching section 2 is The value of Y representing brightness corresponds to the color command setting area number i, and the registered brightness range Y 1m1n + Y 1m, R is shown in FIG. 3(b).
When the brightness of the mark is within the brightness range shown in (2), x = y obtained using equation (2) is converted into an integer, and the contents of the two-dimensional memory corresponding to the chromaticity diagram with x and y as addresses are i. At some point, for example, if it is determined that the mark is located within the diagonally upward-left diagonal line shown in FIG. 3(a), the mark image storage unit 42
A color label number 11i indicating a mark image corresponding to the color characteristics of the fifth color command is written in the document image storage unit 43, and an OIT indicating the background is written in the document image storage unit 43 (step S T 13).

If the document drawing requires an image with color information, the color information corresponding to the background registered in the color command setting section 3 can be written into the document image storage section 43, and the mark image can be used as a label image. The color information or the corresponding color code may be registered in a mark table (not shown) provided separately from the mark image storage section 42 by using a binary image format. Note that the mark table contains data that includes a pair of any one point of the mark images to be connected, for example, the coordinates of the scanning point where the mark image is first detected, or the circumscribing frame of the mark images to be connected, and the color code described above. It is preferable to write it.

Next, in step 5T12, if the color characteristics of the scanning point are within the document/drawing condition range, "0" indicating the background is written in the mark image storage section 42, and "0" indicating the document/drawing is written in the document image storage section 43. Write 1″ (step S T
14).

Note that when an image with color information is required for a document drawing, the color information output from the image input section 1 is written directly into the document image storage section 43.As for mark images, the background usually has no meaning. The explanation in step 5T14 is followed, and the mark table mentioned above is not updated.

Next, in step 5T12, if the color characteristics of the scanning point are within the background condition range, or are not within the mark condition range and are not within the document or drawing condition range, the mark image storage unit 42 and document image storage unit 43 are stored. Both write "0" representing the background (step 5T15). If an image requiring color information is required, the same processing as described above is performed.

FIG. 7 shows the manuscript paper on which color marks according to the present invention have been added, and FIGS. 8(a) and (b) show the colors set using the manuscript paper shown in FIG. 7 using the color command paper shown in FIG. 2. This figure shows mark images and document drawing images that have been classified and extracted based on command registration information. The label images of these separated and extracted mark parts are stored in the mark image storage unit 4.
2, document drawing images are stored in the document image storage section 43, respectively.
Stored as a value image.

Next, using FIGS. 9 and 10, document image separation unit 4
4 and the processing process of the image processing section 45 will be explained. Step 5T21 indicates that all color commands registered in the color command setting section 3 are processed. In steps 5T23 and 24, the mark image storage section 42 and document image storage section 43 are simultaneously and sequentially scanned in the horizontal direction Xx as the main scanning direction and the vertical direction YY as the sub-scanning direction in the same procedure as the image input section 1 scans the paper. Indicates scanning. In step 5T25, the document image within the mark image area of the color set in step 5T21 is extracted, and the image processing unit 45
The document image in the above-mentioned mark image area is input to the image processing section 45 which outputs the image, executes the processing function set in step 5T21, and stores the result in the result storage section 5.

Next, the operation of step 5T25 will be explained with reference to FIG. Note that here, the color (label) number set in step 5T21 is 2. It is assumed that the processing function set in step 5T22 is character recognition.

The labels output from the mark image storage unit 42 are 110 II indicating the background up to the sub-scanning YYI line, so the image processing unit 45 is not activated. However, the label 2 indicating the character recognition processing function is output to the sub-scanning YY2 line. Since there is a pixel indicating , an activation signal for character recognition processing is output to the image processing section 45.

Next, in the sub-scanning line YY3, the document image in the area sandwiched between the two mark images connected to the mark image of the label 2 in the previous scanning line YY2 is extracted and processed by the image processing unit 45.
Send to.

Similar document image extraction processing continues up to sub-scanning row YYn-1. In row YYn, label 2 of previous scanning row YYn-1
Since there is no mark image connected to the image, the one-image processing section 45 is instructed to terminate the character recognition function.

Equations (4) and (5), which are detailed in the official gazette and shown in the first order, are
It can be determined using the formula.

X BYi-1≦XνYi...
(4) X WYi-1≧XBYi
-(5) Here, XBYi-1 and XYi-1 are the change point pair from label 0 to label 2 and from label 2 to label O in the previous scan row Yi-1 of scan row Yi, respectively. Indicates the X coordinate, and XBYi and XνYi are each scanning row Y
The X coordinates of the change point pair of i from label O to label 2 and from label 2 to label O are shown.

FIG. 11 is a diagram showing another processing process of the image processing unit 45, and unlike the processing described above, the processing functions of the image processing unit 45 are operated in parallel to speed up the processing and This is intended to simplify the method. In the process of FIG. 11, the image classification section 41 and the document image classification and extraction section 44 of FIG. 5 are performed simultaneously, so the mark image storage section 42 and the document image storage section 43 can be omitted. It is. In FIG. 11, step (
1) and (2) are 1 image processing unit 1 as in FIG. 6 described above.
The operation is shown below. Steps 5T31, 32, and 33 indicate processing for outputting a document drawing image to be subjected to image processing. Steps 5T34 to 38 are processes for switching the image processing function for document drawing images, and the color characteristic number is 0.
When is selected, image processing functions for colors other than color characteristic number 0 are stopped. The processing in steps 5T31 to 38 is performed based on the color characteristics of the scanning point and the color characteristics registered in the color command setting section 3. When executing step 5T33, it is necessary to register background image data for the document and drawing images in the color command setting section 3 in advance. Further, in order to execute the process of step 5T35, the process for the document image outside the marked area is registered in the command setting section 3 in advance.

The process in step 5T35 can be omitted.5Note that in this process, RGB multi-value data is output as a document drawing image, so multi-value image processing such as binarization and dither image creation is also possible. It can be set as an image processing function. Furthermore, as described in the explanation using FIG. 6, binarization processing can be included in steps 5T31, 32, and 33.

Furthermore, it is also possible to perform a plurality of image processes on an image within the same area by setting a plurality of processes for the same color number or by surrounding the same area with a plurality of color marks.

It goes without saying that the above-described processing can also be applied to the processing shown in FIGS. 6 and 9.

FIG. 12 shows an example of a sheet of paper used to learn the color characteristics of a document drawing to be subjected to image processing. The purpose of learning the color characteristics of documents and drawings is to be able to deal with documents and drawings in which the background in a document or drawing is not white and the characters, figures, photographs, etc. have color characteristics other than black. .

In order to learn the paper as shown in FIG. 12, the learning mode of the mode switching unit 2 is divided into a color command learning mode and a document image characteristic learning mode, and the color command is set corresponding to the document image characteristic learning mode. For example, the following functions are added to section 3.

A frequency distribution is determined for each color characteristic within an arbitrary learning area of the input paper, and the color characteristics are set in descending order of frequency. For example, if the background, text, figure, and photo each have a color, the background, text, figure, and photo each have the top two types with dissimilar color characteristics, taking advantage of the fact that the document drawing has more area in the background. When the 6 characters, figures, and photographs with color characteristics have multiple colors, the first color is used as the background, and the top n types are used as the background.

Furthermore, by setting a threshold value based on the area of the learning area, it becomes possible to learn and register the color characteristics of documents and drawings without being limited by the number of colors in one character, figure, or photograph.

By using the above color characteristics, an image processing device having the following characteristics can be realized.

(2) When performing image processing such as binarization and dither image creation on document drawings, it is possible to select the best parameters and obtain high-quality image processing results.

■ When learning and setting the color characteristics of the color pen used for color commands, it is possible to add detailed conditions regarding the color of the original and the color pen, so the color command and document image can be separated accurately, resulting in high quality. It is possible to obtain accurate image processing results.

■ It is now possible to deal with documents including photos with shading, drawings, color documents, multimedia documents such as single drawings, and poor quality paper such as newspapers, etc. Restrictions can be removed. Furthermore, image processing for color commands added on a color transparent cover can also be applied to document drawings inside the cover.

Although the shape of the color command added to the manuscript is a closed loop shape in the above-described embodiment, it is not limited to this, and color commands other than the closed loop shape as shown in FIG. 13 may also be used. I can do it. Here, in FIG. 13(f), a rectangular area whose sides are the horizontal line and the vertical line is the target area of the color command.

Further, in FIG. 13 (1), the area between vertical lines or between the vertical line and the edge of the paper is set as the target area of the color command.

Furthermore, in FIG. 13(C), a rectangular area with diagonal lines between square brackets is set as the target area of the color command.

These area extractions can be realized using known area extraction methods.

In addition, the image processing functions and area shapes defined on the color command paper are not limited to those described above. Amikake, coloring, inversion, mirror image.

It is possible to target a large number of processes such as output processing such as color conversion, recognition processing such as character recognition, figure recognition, and vectorization, correction processing such as γ correction, MTF correction, and shading correction.

Figures 14) to (a) each show an example of color command paper.

It is also possible to remove the image input section 1 described above and to directly input image data from a storage device such as a magnetic disk.

[Effects of the Invention] As described above in detail based on the embodiments, in the present invention, a color command paper having a processing function defined corresponding to the color of a color pen is read, and the color command is Learns the color characteristics of the color pen written on the paper, registers the learned color characteristics and the processing function described above as a pair, and separates the color mark added on the document from the document drawing based on the color characteristics. At the same time as extraction, the color marks are classified by color and image processing is applied to the document drawing image according to the processing function corresponding to the classified color, so the desired image processing can be applied to the desired area. It can be applied.

Moreover, it is possible to realize an image processing device with high versatility and excellent operability, which is not limited to the types of paper, the types of documents and drawings to be printed, and the types of color pens, with simple processing and configuration.

Furthermore, by limiting the functions of this device and implementing it in an 0CR1 document reading device, editing device, FAX, electronic blackboard, etc., a device with high versatility and excellent operability can be obtained.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing one embodiment of the present invention. Fig. 2 is an explanatory diagram of the color command paper used in the present invention, Fig. 3 is an explanatory diagram of color characteristics, Fig. 4 is a detailed block diagram of the color command setting section, and Fig. 5 is an illustration of the image processing section of the present invention. FIG. 6 is a block diagram showing the detailed configuration, FIG. 6 is a diagram showing the processing process of an embodiment of the present invention, FIG. 7 is a diagram showing manuscript paper on which color marks used in the present invention are added, and FIG. Figure 7 is a diagram showing the mark image and document drawing image separated and extracted from the manuscript paper, Figure 9 is a diagram showing the processing process of the document image classification extraction unit and the image processing unit, and Figure 10 is the document image classification extraction. Figure 11 is a diagram showing other processing steps of the image processing unit of the present invention, Figure 12 is a sheet for learning the color characteristics of characters, figures, photographs and backgrounds, Figure 13 is an additional page. FIG. 14 is a diagram showing an example of a color command sheet. - Color command setting unit, 4... Image processing unit, 5-... Result storage unit.

Claims (1)

[Claims] An image in which a document containing an image consisting of a document/drawing and a mark of a different color is read, and a process corresponding to the color of the mark is applied to the image of the document/drawing. The processing device includes: an image input unit that outputs image information according to the color and/or shading of an image on a document; a mode switching unit that uses the image information as an input signal to switch between a learning mode and a document reading mode; and the mode When the switching unit is set to the learning mode, information in a predetermined area of the color command paper set to define a processing function to be applied to an image of a document/drawing is read as a color characteristic and the processing function is read. a color command setting section which is registered along with a code corresponding to the color command setting section, and when the mode switching section is set to the document reading mode, the image information output from the image input section is input to the image of the document/drawing and the image of the mark. and an image processing unit that performs processing corresponding to the color characteristics separated and extracted and registered in the color command setting unit on the separated and extracted image of the document/drawing. Processing equipment.