JPH07175927A - Image processor - Google Patents

Abstract

PURPOSE:To efficiently perform the registration of a document by discriminating the classification of an object image from the information such as the location/ length, etc., of the ruled line extracted from the object image and enabling a document classification work without manual aid. CONSTITUTION:The image signal of a picture element under consideration in a processing object image is binarized in a binarization means, a black run length is calculated from this binarized image signal in a run length coding means 3, a short run is eliminated from this encoded run length code in a run elimination means 4, the area of connected runs is investigated based on the image signal where this short run is eliminated, a rectangle circumscribed about this area is extracted by a labeling/circumscribed rectangle extraction means 5, a ruled line area is decided by a ruled line area decision means 6 by the size of this extracted rectangle and the kind of an image is discriminated from this decided ruled area by an image decision means 7.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus for subjecting a plurality of document images used in a general office to determining what kind of image a processing target image can be classified.

[0002]

2. Description of the Related Art Generally, in registering a document in an electronic filing apparatus, a file structure is hierarchically constructed not only to register a document with a title but also to enable a quick search. In other words, documents are classified and registered in boxes such as cabinets and binders in the same concept as conventional paper document files.

When the amount of documents to be registered is small, it does not take much time to manually perform this document classification work, but in the case of registering a large number of documents, the document classification work is considerably complicated.

Further, in registering documents in a fixed format such as a form, the boxes into which those documents are classified are predetermined, and it is inefficient to manually perform this document classification work.

However, a method for automatically performing this document classification work has not been established, and the current electronic filing apparatus has no choice but to rely on humans for the document classification work for any document.

[0006]

In an image processing apparatus such as an electronic filing apparatus that needs to identify and determine the type of a document, a method for automatically performing the document classification work is not installed, and the document classification work is not performed. Relies on manpower. Therefore, document registration is cumbersome and time consuming,
It was inefficient work.

According to the present invention, ruled line information is extracted from a document image in an image processing apparatus for identifying and determining the type of image. The purpose is to identify and determine the type of document image based on these pieces of information.

[0008]

An image processing apparatus according to the present invention is a binarizing unit for binarizing an image signal of a pixel of interest in an image to be processed, and the image signal binarized by the binarizing unit is blackened. A run length encoding means for calculating a run length,
A run removing means for removing a short run from the run length code encoded by the run length encoding means, and an area of the run to be connected are examined based on the image signal from which the short run is removed by the run removing means, and A circumscribing rectangle extracting means for determining a rectangle circumscribing the area, a ruled line determining means for determining a ruled line area based on the size of the rectangle extracted by the circumscribing rectangle extracting means, and an image type from the ruled line area determined by the ruled line determining means It is composed of image determination means for determining.

The image processing apparatus of the present invention is a binarizing means for binarizing the image signal of the pixel of interest in the image to be processed.
A run length encoding means for calculating a black run length from the image signal binarized by the binarizing means, a run removing means for removing a short run from the run length code encoded by the run length encoding means, Based on the image signal from which short runs have been removed by the run removal means, the area of the connected runs is examined, and the circumscribed rectangle extraction means for determining the rectangle circumscribing this area, the size of the rectangle extracted by this circumscribed rectangle extraction means Ruled line determining means for determining a ruled line area by means of, and image determining means for determining the type of image based on the degree of similarity between the position / length of the ruled line determined by the ruled line determining means and the position / length of the ruled line of the document registered in advance. It consists of

[0010]

According to the present invention, the image signal of the pixel of interest in the image to be processed is binarized, the black run length is calculated from this binarized image signal, and the short run is removed from this encoded run length code. , Based on the image signal from which this short run has been removed, the area of the connected run is examined, the rectangle circumscribing this area is extracted, and the ruled line area is determined by the size of this extracted rectangle. The image type is discriminated from the ruled line area.

According to the present invention, the image signal of the pixel of interest in the image to be processed is binarized, the black run length is calculated from this binarized image signal, and the short run is removed from this encoded run length code. , Based on the image signal from which this short run has been removed, the area of the connected run is examined, the rectangle circumscribing this area is extracted, and the ruled line area is determined by the size of this extracted rectangle. The type of image is discriminated from the ruled line area based on the degree of similarity between the position and length of the ruled line and the position and length of the ruled line of the document registered in advance.

[0012]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram of an image processing apparatus for determining the document type of the present invention. In FIG. 1, 1 is an input image signal, 2 is a binarizing means for binarizing the input signal,
Reference numeral 21 is a binarized image signal, 3 is run length encoding means,
31 is a run length signal, 4 is a run removal means, 41 is an image signal after run removal, 5 is a labeling / circumscribing rectangle extraction means, 51 is a rectangular signal, 7 is a ruled line area determination means, 61 is a ruled line area signal, and 7 is Image determination means, 8 is a determination signal.
The document type determination method of the present invention will be described in detail below.

An input image signal 1 read by an input device such as a scanner is binarized by a binarizing means 2 which has a binarization threshold Th.
Is binarized and binarized image signal 21
(0 or 1) is output. The rungless encoding means 3 converts the image from the binarized image information 21 into run information.
Ruled line area information 61 is extracted based on this run information. First, the run removing means 4 removes short runs in the main scanning direction and in the sub-scanning direction, respectively.

Next, the labeling / circumscribing rectangle extraction means 5 integrates (labels) the connected runs based on the image signal output from the run removal means 4 into one area, and then adds them to the respective labeled areas. Find the circumscribing rectangle. The ruled line area determination means 6 outputs ruled line area information 61 according to the size of the rectangle. The image determination means 7 determines the type of image based on the ruled line area information 61.

Next, an embodiment of an image processing apparatus equipped with the document type determination processing of the present invention will be described. FIG. 1 is a schematic configuration diagram of an image processing apparatus according to this embodiment.
This image processing apparatus reads and inputs a general document original with a reading device such as an image scanner, inputs as 8-bit digital data per pixel, and determines and outputs the original type. Hereinafter, this embodiment will be described in detail.

In FIG. 1, reference numeral 1 is an input image signal. The input image signal 1 (f) is compared with a predetermined threshold Th by the binarizing means 2 to be binarized, and a binarized image signal 21 (g) is output. The binarization unit 2 is composed of a threshold memory that stores the threshold Th and a comparator that compares the input image signal 1 (f) with the threshold Th. If the input image signal 1 is smaller than the binarization threshold Th, "0" is output as the binarized image signal 21 (g), and if it is larger, "1" is output. The comparison process is shown in equation (1).

G = 0: f <Th g = 1: f ≧ Th (1) FIG. 2 shows the configuration of the binarizing means 2. The binarization means 2 is composed of an 8-bit comparator. 8-bit input pixel signal 1
Is compared with a preset 8-bit threshold Th, and (1)
The binarized image signal 21 is output under the condition shown in the equation.

Next, the run length encoding means 3 creates run information from the binarized image signal 21. FIG. 3 is a diagram for explaining the run information extraction method, which will be described in detail below. FIG. 3A shows an original image. FIG. 3B is a bitmap representation of the original image. Each square corresponds to a pixel, the shaded area is a black (1) pixel, and the others are white (0).
Represents a pixel. In FIG. 3B, the first black pixel is at the coordinate (2,1) and is further connected to the coordinate (4.1) in the right direction.

Further, the pixel at the coordinate (1,6) is the pixel at the coordinate (5,5).
It is connected up to 6). In this way, the connection state of the pixels is replaced with information (run) in which the pixels connected in the right direction are collected as shown in FIG. 3C. Further, these runs are output as information on the start point and length of the run. For example, the first run has a starting point (2,1) and a length of 3, and the second run has a starting point (1,2) and a length of 1 ... In this way, the run length encoding means 3 outputs the start point and length of the run from the binarized image signal 21 as run information.

FIG. 4 shows the configuration of the run length encoding means 3. First, the binarized image signal 21 causes the first pixel to be stored in the latch 300 at the first clock. Then, at the second clock, the AND gate 310 outputs "1" when the first pixel is white and the second pixel is black, and outputs "0" otherwise. That is, the output 311 of the AND gate 310
(Run start signal) is a signal indicating the start of a black run.

On the other hand, the AND gate 320 outputs "1" when the first pixel is black and the second pixel is white, and outputs "0" otherwise. That is, the output 321 of the AND gate 320
(Run end signal) is a signal indicating the end of a black run. The counter 330 is reset by the above-mentioned run start signal 311, and is counted by the image clock 22 (CLK). The output signal 331 of the counter 330 is stored in the latch 360 by the run end signal 321 described above. That is, the run length is stored in the latch 360.

Next, the counter 331 displays the image clock 2
2 (CLK) and vertical image clock 23 (VCLK)
Is input, and the current image position (X coordinate, Y coordinate) is counted. Run start X coordinate 341 and Y coordinate 34
2 is stored in the latch 370 and the latch 380 by the run start signal 311 described above. Selector 3
90 is the X coordinate, Y coordinate, and run length of the run start stored in the latches 370, 380, and 360, and the X coordinate, Y coordinate,
Select and output in order of run length. Select signal 35
1 is output from the counter 350 from the timing of the run end signal 321.

Based on the run information calculated by the above procedure, the run removing means 4, the labeling / circumscribing rectangle extracting means 5, and the ruled line area determining means 6 output ruled line area information 61. Hereinafter, the method of calculating the ruled line area information 61 will be described in detail.

First, the run removing means 4 removes a short run or a long run independently from the run information obtained by the run length encoding means 3. This procedure will be described in detail. FIG. 5A shows a run obtained by the run length encoding means 3. First, in removing short runs, only those with short run lengths are removed. FIG. 5B is an example in which the run length 1 is removed, and the second to sixth runs are removed. In other words, this processing is to remove a run that satisfies L <Ths (2) where L is the run length and Ths is the run length threshold for short runs.

More specifically, FIG. 6A shows a document image, which is an example of a document composed of ruled lines and characters. When short run removal processing is performed on (a) of FIG. 6, it becomes as shown in (b) of FIG. As can be seen from this figure, the vertical ruled lines and part of the characters are removed in this process. In this run removal process, short runs are removed while long runs are removed in parallel. This processing is to remove a run that satisfies L <Th1 (3) when the run length threshold of a long run is Th1.

FIG. 7 shows an example of long run removal processing. The image shown in FIG. 7B is output with respect to the document image shown in FIG. 7A. FIG. 8 shows the run removing means 4
The circuit configuration of is shown.

First, the latches 410, 420, 430, 4
The run information 31 is sequentially input to 40, and the run length, the Y coordinate, the X coordinate, and the run length are stored every 3 clocks. The comparators 450 and 460 are, for example, 13 bits (A
3rd version, 400 dpi (dots per inch) equivalent to the number of main scanning pixels), the comparator 450 compares the threshold Ths with the run length based on the equation (2) and satisfies the equation (2). Is output as the determination signal 451. That is, "1" is output only when the run is equal to or greater than the threshold Ths.

On the other hand, in the comparator 460, Th1 and run length are compared based on the equation (3). If the equation (3) is satisfied, "0" is output, and otherwise, "1" is output as the determination signal 461. To be done. That is, "1" is output only in the case of a run that is the threshold Th1 or less. The gate 470 is an OR gate, and the OR signals of the determination signals 451 and 461 are output as the determination signal 471.

Reference numerals 480, 482 and 484 are latches,
When the determination signal 471 is "1", the X coordinate, the Y coordinate, and the run length are stored respectively. Counter 486 is latch 4
X, Y coordinates stored in 80, 482, 484,
A counter that generates a selection signal for sequentially selecting run lengths. A selector 488 causes a selector 488 to sequentially latch the latches 480, 482, 48 in the order of X coordinate, Y coordinate, and run length.
The signal stored in 4 is output as the run removal signal 41.

Next, the labeling / circumscribing rectangle extraction means 5 integrates (labels) the connected runs based on the image signal 41 output from the run removal means 4 as one area.
9A shows a run obtained by the run length encoding means 3, and FIG. 9B shows the run information. Figure 9
In (a), the first run is connected to the second run. In addition, the first run and the third run are also connected. That is, the first, second, and third runs are all connected. In this way, the labeling / circumscribing rectangle extraction means 5 integrates (labels) the connected runs as one area. FIG. 9C shows FIG. 9A.
The image information shown in is labeled and output as a label (A).

Further, the labeling / circumscribing rectangle extraction means 5 obtains the position and size of the rectangle circumscribing each of the labeled regions. From FIG. 9C, the label (A) is a combination of the run (1), the run (2), and the run (3). Labeling / circumscribing rectangle extraction means 5
Then, the start points (x1, y1), (x2, y) of these runs
2), the smallest x and the smallest y of (x3, y3) are obtained as the starting point (x0, y0) of the circumscribed rectangle.
That is, the start points of n runs included in the target label are (x1, y1), (x2, y2) ... (xn, yn), respectively.
Then, x0 = min (x1, x2, ... Xn) (4) y0 = min (y1, y2, ... Yn) (5) Moreover, the end point (x
e, ye), and the size of the circumscribed rectangle (xs, ys)
Is calculated by the following formula.

Xs = xe−x0 + 1 (6) ys = ye−y0 + 1 (7) FIG. 11 shows the circumscribed rectangle information 51 calculated by the above procedure for the run information shown in FIG. 9A.

FIG. 10 shows the labeling / circumscribing rectangle extraction means 5
2 is an example of the circuit configuration of FIG. Output signal 4 of run removing means 4
For No. 1, first, line information of the first line (X coordinate, Y coordinate of run start position, run length) is stored in the memory 512 via the selector 510. The run information stored in the memory 512 is transmitted via the selector 514 to the comparator 520,
At 522, 524, 526 and 528, the information of the second line is compared.

In the following description, the start position of the run on the first line is X0, Y0, the run length is L0, the start position of the run on the second line is X1, Y1, and the run length is L1.
First, the comparator 520 compares the start position X0 of the first run on the first line with the end position X1 + L1 of the first run on the second line.

At this time, if X0> X1, "1" is output as the comparison signal 521, and "0" is output otherwise.

Similarly, the comparator 522 outputs "1" as the comparison signal 523 if X0> X1 + L1 and "0" otherwise.

The comparator 524 outputs "1" as the comparison signal 525 if X0 + L0> X1 + L1 and "0" otherwise.

The comparator 526 outputs "1" as the comparison signal 527 if X0 + L0> X1 and "0" otherwise.

The comparator 528 outputs "1" as the comparison signal 529 if Y0> Y1 and "0" otherwise.

On the other hand, the adder / subtractor 530 calculates X0 + L0-X1 + 1 or X1 + L1-X0 + 1 as the integrated run length when the runs are connected, and outputs X0, Y0, X as its output signal 531.
1, Y1, X0 + L0-X1 + 1, X1 + L1-X0 +
1 is output.

In the judgment table 540, the comparison signal 521,
6 types of conditions are set based on 523, 525, 527 and 529, and selectors 514 and 544 and memories 546 and 548
And a run selection signal 543 are output. The memory selection signal 545 is a signal for selecting the memory 546 for internal calculation (memory for storing run information for one line) and the buffer memory 548 for outputting the labeling result, and is “0”.
The memory 546 is selected when, and the memory 548 is selected when "1".

The selection signal 542 is a 4-bit signal, the lower 3 bits are determined by the six conditions described below, and the upper 1 bit is the comparison signal 529 as it is. First, the first condition is that the comparison signal 523 is “1”,
Under this condition, the run of the second line is not connected to the run of the first line, and the memory select signal 541 is "0".
Is set as “000” as the lower 3 bits of the selection signal 542.
Is output as a run selection signal 543. Second
Condition is that the comparison signal 521 is “1”, the comparison signal 523 is “0”, and the comparison signal 525 is “1”. Under this condition, the run of the second line is connected to the run of the first line,
“0” is selected as the memory selection signal 541 and the selection signal 542
"001" as the lower 3 bits of the run selection signal 54
As "3", "1" is output.

The third condition is that the comparison signal 521 is "1", the comparison signal 523 is "0", and the comparison signal 525 is "0". Under this condition, the run of the second line is the first line. In connection with the run, "0" is set as the memory selection signal 541,
"010" is output as the lower 3 bits of the selection signal 542 and "0" is output as the run selection signal 543. The fourth condition is that the comparison signal 521 is “0”, the comparison signal 523 is “1”,
When the comparison signal 525 is “1”, the run of the second line is connected to the run of the first line under this condition, and “0” is set as the memory selection signal 541 and the lower three bits of the selection signal 542.
"011" is output as a bit and "1" is output as a run selection signal 543.

The fifth condition is that the comparison signal 521 is "0", the comparison signal 523 is "1", and the comparison signal 525 is "0". Under this condition, the run of the second line is the first line. In connection with the run, "0" is set as the memory selection signal 541,
"100" is output as the lower 3 bits of the selection signal 542 and "0" is output as the run selection signal 543. The sixth condition is that the comparison signal 527 is "0", and the first condition
It indicates that the connection with the run of the line has been completed, and “1” is set as the memory selection signal 541, and the lower three bits of the selection signal 542.
"101" is output as a bit and "0" is output as the run selection signal 543. Select signal 542 in selector 544
The label information is output by.

First, when the lower 3 bits of the selection signal 542 are "000", the start position of the label is (X1, Y
1), (L1, Y-Y1 + 1 (where Y is the line number being processed)) is output as the label size. Y0 when the lower 3 bits of the selection signal 542 are "001"
When the smaller signal of Y1 and Y1 is Y2, the label start position is (X1, Y2), and the label size is (X
0 + L0-X1 + 1, Y-Y2 + 1) is output. When the lower 3 bits of the selection signal 542 are "010", (X1, Y2) is output as the label start position and (L1, Y-Y2 + 1) is output as the label size. Selection signal 542
If the lower 3 bits of the label are “011”, the label start position is (X0, Y2) and the label size is (L0,
Y-Y2 + 1) is output.

The lower 3 bits of the selection signal 542 are "10".
If it is 0 ", the label start position is (X0, Y2),
As the label size, (X1 + L1-X0 + 1, Y-Y
2 + 1) is output. When the lower 3 bits of the selection signal 542 are "101", the start position of the label is (X0, Y
0), and outputs (L0, Y-Y0 + 1) as the label size. Selector 544 according to memory selection signal 541
The label information output from the memory 546 or the memory 5
Select whether to output to 48.

Further, the run selection signal 543 updates the run information 513 on the first line and the run information 41 on the second line. That is, when the run selection signal 543 is "0", the run information 513 on the first line is updated to the next run. When the run selection signal 543 is “1”, the second
The run information 41 on the line is updated to the next run. The above processing is repeated until the end of one line.

When the processing of the first line is completed, the memory 5
The run information of the second line stored in 46 is the selector 5
The data is stored in the memory 512 via 10 and the above calculation is performed by the run information 513 on the second line and the run information 41 on the third line. The above is repeated until the end of one page.

Next, the ruled line area determination means 6 outputs ruled line area information 61 from the circumscribed rectangle information 51. As a characteristic of ruled lines, horizontal ruled lines generally have a large horizontal width and a small vertical width. The vertical ruled line has a short horizontal width and a long vertical width. Utilizing this, the width threshold Th1 and the width threshold Th
2 is set, and the circumscribed rectangle information 5 that satisfies the following conditions
Extract from 1 as a horizontal ruled line.

Xs> th1 and ys <th2 (8) Further, the horizontal width threshold Th3 and the vertical width threshold Th4 are set, and those satisfying the following conditions are extracted from the circumscribed rectangle information 51 as vertical ruled lines.

Xs <th3 and ys <th4 (9) Then, a region that does not satisfy any of the above formulas (8) and (9) is a non-ruled line region. FIG. 12 shows the flow of the following procedure.

FIGS. 6C and 7C show the above-described run removing means 4 and labeling / circumscribing rectangle extracting means 5 from the document images of FIGS. 6A and 7A, respectively. The horizontal ruled line area and the vertical ruled line area are extracted through the ruled line area determination means 6.

FIG. 13 shows an example of the circuit configuration of the ruled line area determining means 6. First, as the rectangular signal 51, the starting coordinates (x, y) and size (xs, ys) of the rectangle are input.
Latches 614, 612, 61 by clocks not shown
X, y, and xs are stored in 0, respectively. Comparator 62
0, 622, 624, and 626 have xs and Th, respectively.
1, ys and Th2, xs and Th3, ys and Th4 are compared, and when xs> Th1, “1” is set as the comparison signal 621.
Otherwise, it is “0”, and when ys <Th2, the comparison signal 623
Is “1”, otherwise is “0”, and when xs <Th3 is “1” as the comparison signal 625, otherwise is “0”, ys
When> Th4, “1” is output as the comparison signal 627, and “0” is output otherwise. In the determination circuit 630, the comparison signal 621
And 623 are "1" or the comparison signals 625 and 627 are "1", "1" is output as the determination signal 631 and x, y, xs and ys are stored in the latches 640, 642, 644 and 646, respectively. It

As the ruled line type signal 632, when the comparison signals 621 and 623 are "1", the comparison signal 6 is "0".
When 25 and 627 are "1", "1" is output.
The counter 650 is a latch 640, 642, 644, 64.
6 is a selection signal for sequentially selecting the information of No. 6 by the selector 660, and sequentially outputs x, y, xs, ys and the type of the rectangular signal determined as the ruled line as the ruled line area signal 61.

Utilizing the ruled line area signal 61 described above,
The image determination means 7 determines the type of image. The determination method will be described in detail below. The ruled line area signal 61 is used to determine from the position and length of the ruled line.

First, the number of horizontal ruled lines in the target image is nl, the starting points of the horizontal ruled lines are (xl (i), yl (i)), and the length of is 11 (i). However, i is 1 to nl. The number of vertical ruled lines is np, and the start point of the vertical ruled lines is (xp
(J), yp (j)) and the length is lp (j).
However, j is 1 to np.

Here, there are n types of images to be judged which have already been registered. Among them, the number of horizontal ruled lines, the number of vertical ruled lines, the starting point of the horizontal ruled line and its length, and the starting point of the vertical ruled line and its The length is Nl _m , Np _m , (X1 _m (k), Yl _{m
(K)), Ll m (} k), (Xp m (l), Yp m
(L)), and Lp _m (l) (provided that j is 1 to n, k
Is 1~Nl _m, l is 1~Np _m).

First, the start points (xl (1), yl (2)) to (xl (nl), yl) of the nl horizontal ruled lines of the target image.
(Nl)) for each (Xl _m (k), Yl _m
(K)) having the shortest distance is obtained (k at this time is k = o), and the square sum average Al _m of the difference in the distance and the length is obtained by the following formula.

[0059]

[Equation 1] Similarly, Ap _m is calculated for the vertical ruled line.

[0060]

[Equation 2] Furthermore, their average A _m

[0061]

[Equation 3] Calculate as This A _m is calculated for all n types of registered images, and the image having the smallest value A _m is determined to be of the same type as the target image. Image determination means 7 is CP
It consists of U and memory.

As described above, the image signal of the pixel of interest in the image to be processed is binarized by the binarizing means, the black run length is calculated from the binarized image signal by the run length encoding means, and this code is used. The short run is removed from the converted run length code by the run removing means, the area of the connected run is examined based on the image signal from which the short run is removed, and the rectangle circumscribing this area is labeled and the circumscribed rectangle is extracted. The ruled line area is determined by the ruled line area determination means based on the size of the extracted rectangle, and the type of image is determined by the image determination means from the determined ruled line area.

As a result, the type of the target image can be determined from the information such as the position and length of the ruled line extracted from the target image.
Therefore, in an image processing apparatus such as an electronic filing apparatus that needs to identify and determine the type of a document, the document classification work can be performed without relying on human labor. As a result,
Documents can be registered efficiently and efficiently. The present invention is not limited to the above-mentioned embodiment, and various modifications can be made without departing from the spirit of the invention.

[0064]

As described above in detail, according to the present invention,
The type of the target image can be determined from the information such as the position and length of the ruled line extracted from the target image. Therefore, in an image processing apparatus such as an electronic filing apparatus that needs to identify and determine the type of a document, the document classification work can be performed without relying on human labor. As a result, document registration is efficient and
It becomes possible to carry out efficiently.

[Brief description of drawings]

FIG. 1 is an overall configuration block diagram showing an image processing apparatus according to an embodiment of the present invention.

FIG. 2 is a block diagram showing an example of a circuit configuration of a binarizing unit.

FIG. 3 is an explanatory diagram of a process of run length encoding.

FIG. 4 is a block diagram showing an example of a circuit configuration of run-length encoding means.

FIG. 5 is an explanatory diagram of a run removing unit.

FIG. 6 is a diagram showing an example of ruled line area determination.

FIG. 7 is a diagram showing an example of ruled line area determination.

FIG. 8 is a block diagram showing an example of a circuit configuration of a run removing unit.

FIG. 9 is an explanatory view of labeling means.

FIG. 10 is a block diagram showing an example of a circuit configuration of labeling means.

FIG. 11 is an explanatory diagram of a circumscribing rectangle extraction unit.

FIG. 12 is an explanatory diagram of a ruled line area determination unit.

FIG. 13 is a block diagram showing an example of a circuit configuration of ruled line area determination means.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 ... Input image signal 2 ... Binarizing means 21 ... Binary image signal 3 ... Run length coding means 31 ... Run length signal 4 ... Run removing means 41 ... Image signal after run removing 5 ... Labeling / circumscribing rectangle extraction Means 51 ... Rectangular signal 6 ... Ruled line area judging means 61 ... Ruled line area signal 7 ... Image judging means 8 ... Judgment signal

Claims (2)

[Claims] 1. A binarizing unit for binarizing an image signal of a pixel of interest in an image to be processed, and a run length encoding unit for calculating a black run length from the image signal binarized by the binarizing unit. , A run removing means for removing a short run from the run length code encoded by the run length encoding means, and an area of the run to be connected based on the image signal in which the short run is removed by the run removing means A circumscribing rectangle extracting means for determining a rectangle circumscribing this area, ruled line determining means for determining a ruled line area based on the size of the rectangle extracted by the circumscribing rectangle extracting means, and a ruled line area determined by the ruled line determining means An image processing apparatus comprising: an image determination unit that determines the type of image. 2. A binarizing unit for binarizing an image signal of a pixel of interest in an image to be processed, and a run length encoding unit for calculating a black run length from the image signal binarized by the binarizing unit. , A run removing means for removing a short run from the run length code encoded by the run length encoding means, and an area of the run to be connected based on the image signal in which the short run is removed by the run removing means A circumscribing rectangle extracting means for determining a rectangle circumscribing this area, a ruled line determining means for determining a ruled line area based on the size of the rectangle extracted by the circumscribing rectangle extracting means, and a position of the ruled line determined by the ruled line determining means An image processing apparatus comprising: an image determination unit that determines the type of image based on the degree of similarity between the length and the position / length of a ruled line of a document that is registered in advance.