JPH0575850A - Picture area discriminating device - Google Patents

Abstract

PURPOSE:To precisely discriminate between a character diagram area and a dot photograph area. CONSTITUTION:A minimum density and maximum density detection circuit 5 detects the minimum density level and the maximum density level of picture elements in a block. A maximum density difference calculation circuit 6 calculates the density difference of the detected maximum density level and the detected minimum density level. A density difference absolute value total sum calculation circuit 7 determines the total sum of the absolute values of the density differences of neighboring picture elements lying along a main and a sub scanning directions. Since a discrimination circuit 9 receives feature quantity related to the density in the main scanning direction and the sub scanning direction of the block, that is, an object picture area to be processed from the density difference value total sum calculation circuit 7, it can discriminate between a diagram and a dot pattern.

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 in an electronic file, a digital copying machine, a scanner or the like, and more particularly to an image area identifying apparatus for identifying a binary image area in the same image.

[0002]

2. Description of the Related Art Conventionally, many methods for identifying image areas such as a character image area and a photographic image area have been proposed. Among these, there are many methods in which an image is divided into blocks of a predetermined size and the feature amount extracted from the blocks is used for identification. In addition, the feature amount to be extracted is generally the sum of density differences between adjacent pixels in the main scanning direction.

[0003]

However, when distinguishing a halftone picture and a line figure, it is difficult to separate fine line figures and halftone dots in the vertical direction because only the features in the main scanning direction are used. In order to solve this, there is a method of detecting a differential processing edge component.
Alternatively, there is a problem in that it is necessary to perform calculation using 8 pixels, which requires a long processing time and increases the size of the hardware.

The present invention has been made in order to solve such a conventional problem, and includes a character / line figure area (a character area only, a line figure area only, or an area having both characters and line figures) and a mesh. An object of the present invention is to provide an image area identification device capable of accurately identifying a dot photograph area.

[0005]

An image area identifying apparatus of the present invention is an image area identifying apparatus for identifying whether a processing target image area belongs to a character line graphic area or a halftone dot photographic area. A feature extraction means for extracting a feature relating to the density in the main scanning direction and the sub-scanning direction of the area is provided, and the feature extraction means is used to perform identification.

In order to extract the characteristics relating to the density, it is preferable to obtain the sum of absolute values of the density difference between adjacent pixels or the number of density pulses having a predetermined height or more.

[0007]

In the image area discriminating apparatus having the above construction, since the characteristics relating to the density are extracted not only in the main scanning direction but also in the sub scanning direction, it is possible to discriminate the character line figure area and the halftone dot picture area with high accuracy.

[0008]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 shows the configuration of an embodiment of the image area identifying apparatus of the present invention. The original including the image to be processed is read by the image sensor 1. The image signal output from the image sensor 1 is converted into a digital signal by the A / D converter 2, and further, by the block division circuit 3, each line as shown in FIG. It is divided into blocks including a plurality of lines including the lines and temporarily stored in the block memory 4. Block memory 4
The minimum density and maximum density detection circuit 5 detects the minimum density level and the maximum density level of the pixels in the block on the basis of the pixel data stored in. The maximum density difference calculation circuit 6 calculates the maximum density level detected by the circuit 5 and the density difference between the maximum density levels.

The density difference absolute value sum calculation circuit 7 calculates the sum of absolute values of density differences of adjacent pixels along the main and sub-scanning directions as shown in FIG. The pulse number counting circuit 8 calculates the number of density pulses having a predetermined height or more in the main and sub-scanning directions.

The discrimination circuit 9 receives the outputs of the minimum density and maximum density detection circuit 5, the maximum density difference calculation circuit 6, the density difference absolute value sum total calculation circuit 7 and the pulse number counting circuit 8,
The processing target image area, that is, the area of the block is identified.
Since the identification circuit 9 receives the feature amount relating to the density of the block, that is, the image area to be processed in the main scanning direction and the sub scanning direction from the density difference absolute value sum calculation circuit 7 and the pulse number counting circuit 8, the line drawing shown in FIG. And the halftone dot pattern shown in FIG. 3 can be identified.

When the identification circuit 9 determines that the block belongs to the character line graphic area, it connects the switch SW to the terminal N1. As a result, the blocks stored in the memory 4 are supplied to the binarization circuit 10 and binarized. Also,
When the identification circuit 9 determines that the block belongs to the halftone dot picture area, it connects the switch SW to the terminal N2. As a result, the blocks stored in the memory 4 are smoothed by the low-pass filter (LPF) 11 and then supplied to the dithering circuit 12 for dithering. When the identification circuit 9 determines that the block is the photograph area,
The switch SW is connected to the terminal N3. As a result, the blocks stored in the memory 4 are supplied to the dither circuit 12 and subjected to dither processing.

FIG. 6 is an example of an operation for obtaining the number of density pulses having a predetermined height or more in the main scanning direction and the sub scanning direction in the image area to be processed, that is, the block, that is, the block division circuit 3 of the embodiment of FIG. An example of the operation of the minimum density and maximum density detection circuit 5, the maximum density difference calculation circuit 6, and the pulse number counting circuit 8 will be described.

First, in step S1, the block division circuit 3 divides an image into blocks each including a plurality of pixels in the main and sub-scanning directions (that is, each line includes a plurality of lines including a plurality of pixels). To divide. Next, in step S2, the counting circuit 8
Clear the internal counter to zero. Next, in step S3, the detection circuit 5 detects the maximum density level and the minimum density level of the pixels in the block. Then, step S4
At, the maximum density difference calculation circuit 6 obtains the density difference between the maximum density level and the minimum density level. Next, in step S5, the count circuit 8 uses the built-in threshold value selection circuit (not shown) to set the threshold values T1 and T2 corresponding to the density difference obtained by the calculation circuit 6 to the built-in comparator (not shown).
Set to.

Next, in step S6, the count circuit 8 accesses the pixels in a predetermined direction (main and sub-scanning directions) and extracts the pixels having the maximum and minimum density levels. Then, in step S7, the counting circuit 8 obtains the pulse height P from the difference between the density levels of the pixels having the maximum and minimum density levels. The counting circuit 8 determines that the pulse height P is greater than the threshold T1 and the threshold T
When it is 2 or less (YES in step S8), the value of the internal counter is incremented by 1 (step S9).

When the pulse detection in the block is completed (YES in step S10), the count value of the circuit 8 and the built-in counter is checked (step S11), and the count value becomes the threshold value T3.
In the above case, the block is determined to be a halftone area such as a halftone dot photograph (step S12), and if it is smaller than the threshold value T3, the block is determined to be a character line figure area (step S13).

[0016]

According to the image area identifying apparatus described above, the feature relating to the density is extracted not only in the main scanning direction but also in the other scanning direction, so that the character line figure area and the halftone dot picture area are accurately identified. it can. Further, unlike the conventional edge extraction, the number of pixel accesses is not large, and the conventional feature extraction in the main scanning direction can be used as it is, so that the processing time can be shortened and the cost can be reduced.

[Brief description of drawings]

FIG. 1 is a block diagram showing the configuration of an embodiment of an image area identifying apparatus of the present invention.

FIG. 2 is a diagram showing an example of a line figure.

FIG. 3 is a diagram showing an example of a halftone dot pattern.

FIG. 4 is an explanatory diagram showing a relationship between blocks and main and sub-scanning direction waveforms.

FIG. 5 is an explanatory diagram showing a relationship between a density waveform and a density difference absolute value.

FIG. 6 is a flowchart showing an example of an operation for obtaining the number of density pulses having a predetermined height or more in the main scanning direction and the sub scanning direction in the processing target image area, that is, the block.

[Explanation of symbols]

 3 Block division circuit 7 Concentration difference sum calculation circuit 8 Pulse number counting circuit

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Toru Fujii, No. 10 Hanazono Dodo-cho, Ukyo-ku, Kyoto City, Kyoto Prefecture Omron Co., Ltd. Co., Ltd. (72) Hajime Okumura Hajime Okumura, No. 10 Hanazono Dodo-cho, Ukyo-ku, Kyoto City, Kyoto Prefecture OMRON Corporation

Claims (3)

[Claims] 1. An image area identification device for identifying whether a processing target image area belongs to a character line graphic area or a halftone dot photographic area, the density relating to the main scanning direction and the sub-scanning direction of the processing target image area. An image area identifying apparatus comprising: a feature extracting unit that extracts a feature, and performing the identification using an output of the feature extracting unit. 2. The image area identifying apparatus according to claim 1, wherein the feature extracting means has means for obtaining a total sum of absolute values of density differences between adjacent pixels in the main scanning direction and the sub scanning direction. 3. The image area identifying apparatus according to claim 1, wherein the feature quantity extracting means has means for obtaining the number of density pulses having a predetermined height or more in the main scanning direction and the sub scanning direction. ..