JP2853140B2 - Image area identification device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION (Industrial Application Field) The present invention relates to a binary area in a document image in which a binary image represented by a character line image or the like and a halftone image represented by a photographic image or the like are mixed. The present invention relates to a document image area identification device that identifies a document image and a halftone area.

(Prior Art) When a binary image and a halftone image included in a document are reproduced well as a digital image, it is necessary to perform processing according to the characteristics of the binary region and the halftone region. Therefore, it is necessary to identify a character line image and a photo image. Further, in consideration of improvement of image compression in communication, image identification is indispensable.

As a conventional system, for example, there is one described in Japanese Patent Application Laid-Open No. 58-205376. As shown in the upper part of FIG. 2, the density characteristic of the character line image shows a characteristic in which the density difference between adjacent pixels is large. On the other hand, as shown in the upper part of FIG.
The density difference between the adjacent pixels becomes gentle. In the above-mentioned conventional method, an image is identified by utilizing such a difference in density characteristics between a binary image and a halftone image. That is, M
In this method, the maximum density difference in a block is determined in units of a block of × N pixels, and when the density difference is larger than a threshold value, the area is identified as a binary area, and when the density difference is smaller than a threshold value, it is identified as a halftone area.

(Problems to be Solved by the Invention) However, in the conventional method as described above, since the density difference within M × N pixels is obtained, the image must use multi-value data and the multi-value data must be processed. No. Therefore, there is a disadvantage that a hardware configuration for performing the arithmetic processing becomes large.

Further, in the conventional method, an edge component present in a halftone image is also detected and is erroneously recognized as a character area, so that the image quality of the halftone area deteriorates.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-described drawbacks of the related art, and has as its object to make it possible to identify a character line image and a photographic image in a document image with a simple hardware configuration. is there.

It is another object of the present invention to prevent erroneous recognition of an edge of a halftone area and to obtain a good reproduced image by coping with a halftone image.

(Means for Solving the Problems) As shown in FIG. 1, the image region identification apparatus of the present invention for achieving the above object performs binarization on an image in which a character line image and a photographic image are mixed. Binarizing means 1 and 2
An isolated point removing means 2 for removing an isolated point from the binarized image, a contour extracting means 3 for extracting a contour from the image from which the isolated point has been removed, and converting the binary image and the contour image to M × N A region determination means for treating a character region and a halftone region based on a ratio of the number of binary black pixels present in M × N pixels to the outline-extracted pixels. Features.

(Operation) The input image is multi-valued input from a scanner or the like (not shown). The isolated point removing means 2 removes a noise component and a halftone dot component from the image by removing a binary output isolated point. The contour extracting means 3 extracts a contour from the image from which the isolated points have been removed. The area determining means 4 determines a binary area (character area) and a halftone area based on the ratio of black pixels in the M × N pixel area based on the image subjected to the binarization processing and the image information extracted from the outline.

According to the present invention, since all processes for identifying a character line image and a photographic image in a document image are performed using binary data, the hardware configuration is simplified and the processing speed is increased.

Further, according to the present invention, it is possible to prevent erroneous recognition of the edge of the halftone area and to obtain a good reproduced image by coping with the halftone image.

(Examples) The contents of the present invention will be described in detail based on examples.

The input image includes a character region, a photograph region, and a halftone dot region, and the density characteristics and the characteristics after binarization are as shown in FIGS. 2, 3, and 4, respectively. First, these characteristics will be specifically described.

As shown in FIG. 2, the density characteristic of the character area is a characteristic of sharp shading. On the other hand, since there are many background areas, white characteristics increase as characteristics after binarization. Further, since a character has a line width, a black area does not continue in both the vertical and horizontal directions.

As shown in FIG. 3, the density characteristic of the photographic region has a gentle gradation. Further, since an image is generally composed of planes, the black region after binarization has a certain area.

FIG. 4 shows the density characteristics of the halftone dot area. Halftone is originally 2
Since it is a value image, it should show the characteristics of characters, but blurring occurs because the size of the halftone dot is similar to the resolution of the scanner. Therefore, in a region where the image is thin and the halftone dots are isolated, the characteristics are close to the character characteristics, and in a region where the image is dark and the halftone dots are dense, the characteristics are close to the characteristics of the photographic image. The character line image and the halftone image can be distinguished by using the above difference in the characteristics. Specifically, the number of pixels in the case of binarization and 2
An isolated point is removed from the value image, and the number of pixels after the contour detection is performed is compared with the value image.

5, 6, and 7 show the case where binarization is performed on three types of images, that is, a character, a photograph, and a halftone dot, and the case where an isolated point is removed from a binary image, and then the contour is obtained. FIG. 3 shows a schematic diagram when extraction is performed.

The isolated point in the character area is only noise, and the line width of the character is usually about 1 to 4 dots. Therefore, the ratio between the number of pixels of the binary image and the number of pixels after contour extraction is at most 2
It is about twice.

There are almost no isolated points in the photographic area. Further, since the image is basically composed of planes, the ratio between the number of pixels of the binary image and the number of pixels after contour extraction is very large.

In the halftone dot area, halftone dots in a low density area are removed as isolated points. That is, the halftone dot area that has a property similar to a character is removed, and an area close to the characteristics of a photograph remains. Therefore, the ratio between the number of pixels of the binary image and the number of pixels after contour extraction becomes very large.

As described above, the ratio between the number of pixels of the binary image and the number of pixels after contour extraction is examined. If the ratio is larger than the threshold value, it can be identified as a halftone area, and if it is smaller than the threshold value, it can be identified as a character area. In order to compare the number of pixels, there is a method of referring to an M × N block as an identification range. As the values of M and N, a standard value is about “character line width to character size”.

The threshold value depends on the resolution of the input system, but is preferably about several times the number of contour pixels when the line width of the character is considered to be 1 to 4 dots.
Although the threshold value is fixed, since the ratio between the black pixels of the binary image and the black pixels after the contour extraction is actually used, the threshold value can be accurately determined without being influenced by the density of the input image. .

The hardware configuration of the present embodiment based on the principle of area identification described above will be described.

As shown in FIG. 8, the apparatus according to the present embodiment performs two-dimensional processing on an image in which a character line image and a photographic image are input in a multi-valued manner.
A binarizing circuit 11 for performing binarization, an isolated point removing circuit 12 for removing an isolated point from the binarized image, and a contour extracting circuit 13 for extracting a contour from the image from which the isolated point has been removed And 2
The value image and the contour image are treated as a block of M × N pixels,
An area determination circuit 14 for identifying a character area and a halftone area based on the ratio of the number of binary black pixels existing in N pixels to the contour-extracted pixels is provided. The input units of the isolated point removal circuit 12 and the contour extraction circuit 13 are provided with line memories 15 and 16 for sequentially taking in the input image in three lines at a time, and the input unit of the area determination circuit 14 has five lines. A line memory 17 for taking in images sequentially in parallel is provided. Further, the apparatus according to the present embodiment regards the input image as a character image, performs processing suitable for all attributes of the character image, and supplies the processing result to the image switching circuit 20.
18 and the input image is regarded as a halftone image, and all processes suitable for the attributes of the halftone image are performed.
The image processing apparatus includes a halftone processing circuit 19 to be supplied to the image processing circuit 20 and an image switching circuit 20 for switching and outputting an image suitable for the attribute of each image based on the output of the area determination circuit 14.

As shown in FIGS. 9 (a) and 9 (b),
An isolated point is removed by a connected or 8-connected mask pattern. Here, a mask pattern for removing one dot isolated point is shown as an example. FIG. 10 shows an example of an isolated point removing circuit configuration in the case of four connections. As shown in FIG. 10, the line memory 15 _1, 15 ₂ and the latch circuit 21 to 24 retrieves the value of the upper, lower, left and right adjacent pixels of the pixel of interest, the OR circuit (OR
Circuit) 25, and the value of the pixel of interest, which is the output of the latch path 22, and the output of the OR circuit 25 are input to the logic-related circuit (AND circuit) 26. At one time, the output of the AND circuit 26 is set to a white pixel value regardless of the value of the pixel of interest.

Contour detection can be extracted by a simple logical operation by referring to data for three lines. FIG. 11 shows an example of the configuration of the contour detection circuit.

In FIG. 11, binarized data sequentially output by scanning an image is input, and two scan lines are stored in the line memories 16 ₁ and 16 ₂ , whereby the output of the line memory 16 ₁ is output. when the target pixel output b, outputs c (adjacent pixels upward) 1 line before the corresponding pixel of the target pixel from the line memory 16 _2, the corresponding pixel (downward after one line of the target pixel input data Is output as an adjacent pixel a). Also outputs a pixel of interest e and preceding pixel adjacent pixels d and neighboring pixels f after one pixel by using the latch 30, 31 from the output of the line memory 16 _1.

The exclusive OR operation (EXOR) circuit 32 performs an exclusive OR operation on the target pixel b and the adjacent pixel a in the downward direction, and performs an AND operation on the output g and the target pixel b with an AND circuit 33.
, A signal h representing the lower contour portion of the image is obtained. Further, the exclusive OR operation of the pixel of interest b and the adjacent pixel c in the upward direction is performed by the EXOR circuit 34, and the AND operation of the output i and the pixel of interest b is performed by the AND circuit 35. Obtain a signal j representing the part.
The signals i and j are mixed by a logical sum (OR) circuit 36 to obtain a signal k representing the upper and lower contours of the image.

The EXOR circuit 37 determines the pixel of interest e and the adjacent pixel d immediately before the pixel d.
And an exclusive OR operation with the output 1 and the pixel of interest e
By performing a logical AND operation with AND circuit 38,
A signal m representing the outline on the right side of the image is obtained. Also,
The exclusive OR operation of the pixel of interest e and the adjacent pixel f on the left is performed by the EXOR circuit 39, and the AND operation of the output n and the pixel of interest e is performed by the AND circuit 40. Is obtained. OR signals m and o
The signals p representing the right and left contour portions of the image are obtained by mixing by the circuit 41.

An OR circuit 43 outputs a signal representing an outline by performing a logical OR operation of a signal k representing the upper and lower contours of the image and a signal p representing the left and right contours. The latch 42 is used to adjust the timing of the pixels of interest b and e because there is a time lag of one pixel. By sequentially performing the above processing while scanning the image, the contour portion can be accurately obtained. Since this contour detection circuit performs sequential processing by hardware using only simple logical operations, the processing is fast and real-time processing is possible.

FIG. 12 shows an example of the configuration of the area determination circuit. In this example, the ratio between the number of pixels in the binary image and the number of pixels in the outline image in the 5 × 5 pixel area is checked. If the ratio is twice or more, the area is determined as a halftone area, and the others are determined as character areas. Line memory 17 _{1 -1}
7 ₄ provides the output of the binarization circuit 11 to the decoder 45 retrieves the binary output of each respective five lines minutes in parallel. The decoder 45 converts the same pattern of the number of black bits in the input 5 bits into a 3-bit output representing the number of black bits. The 5 × 5 pixel counter 46 latches the four outputs of the decoder 45, and when the fifth output arrives, adds the latched four outputs and the fifth output to obtain a 5 × 5 pixel counter. Obtain the number of pixels of the binary image in the pixel area. Similarly to the output of the contour detection circuit 13, the line memories 175 to 178, the decoder 47 and the 5 × 5 pixel number counter 48 obtain the number of pixels of the contour image in the 5 × 5 pixel area. The number of pixels of the obtained binary image is compared with the number of pixels of the contour image by the comparator 49.
When the input A is larger than the input B, the comparator 49 outputs a determination output indicating that the image is in a half tone. The output b of the number of pixels of the contour image is 1 bit as shown in FIG. Since the minute digits are input shifted to the higher order, the input B of the comparator 49 is B = 2b, and the input A is A = a. Therefore, when a> 2b, that is, when the ratio of a / b is 2 or more, it is determined to be a halftone region, and otherwise, it is determined to be a binary region.

The character processing circuit 18 performs processing on the input image data according to the characteristics of the characters, and the halftone processing circuit 19 performs processing on the input image data according to the characteristics of the halftone image.

The image switching circuit 20 switches and outputs the outputs of the character processing circuit 18 and the halftone processing circuit 19 based on the output of the area determination circuit 14, and outputs a composite image that has been processed according to each area.

(Effect of the Invention) According to the present invention, it is possible to identify a binary area and a halftone area in a document image in which a character line image and a halftone image are mixed. Since all processing is performed using binary data, the hardware configuration is simplified, the operating speed is increased, and real-time processing becomes possible.

Further, according to the present invention, the edge region of the halftone region, which has conventionally been erroneously recognized, can be accurately identified, and a halftone image can be dealt with.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a basic configuration of the present invention. FIG. 2 is a diagram showing density characteristics and binary characteristics of a character image. FIG. 3 is a diagram showing density characteristics and binary characteristics of a photographic image. FIG. 4 is a diagram illustrating density characteristics and binary characteristics of a halftone dot image. FIG. 5 (a) is a diagram showing a binarized character image, and FIG. 5 (b) is a diagram showing a binarized character image after performing isolated point removal and contour extraction processing. FIG. 6 (a) is a diagram showing a binarized photographic image, and FIG. 6 (b) is a diagram showing a photographic image after performing an isolated point removal and contour extraction process on the binarized photographic image. 7A is a diagram showing a binarized halftone dot image, and FIG. 7B is a diagram showing a halftone dot image after subjecting the binarized halftone image to isolated point removal and contour extraction processing. It is. FIG. 8 is a block diagram showing a schematic configuration of one embodiment of the present invention. FIG. 9A is a diagram showing an example of a mask pattern for removing eight connected isolated points, and FIG. 9B is a diagram showing an example of a mask pattern for removing eight connected isolated points. FIG. 10 is a diagram showing an example of a configuration of an isolated point removing circuit. FIG. 11 is a diagram showing an example of the configuration of the contour detection circuit. FIG. 12 is a diagram showing an example of the configuration of the area determination circuit. 1 ... binarization means, 2 ... isolated point removal means, 3 ... contour extraction means, 4 ... area determination means.

Continuation of the front page (58) Field surveyed (Int.Cl. ⁶ , DB name) G06T 7/40 H04N 1/40

Claims (1)

(57) [Claims] A binarizing means for binarizing an image in which a character line image and a photographic image are mixed; an isolated point removing means for removing an isolated point from the binarized image; A contour extracting means for extracting a contour from the image from which the points have been removed; a binary image and a contour image are treated as blocks of M × N pixels;
An image area identification apparatus, comprising: area determination means for identifying a character area and a halftone area based on a ratio of the number of binary black pixels existing in × N pixels to the pixels whose contour has been extracted.