KR100206338B1 - Binary coding method of letter image having both character and picture - Google Patents

Abstract

end. The technical field to which the invention described in the claims belongs

The present invention relates to a method of binarizing an image obtained by scanning a document in which characters and pictures are mixed in an image input apparatus.

I. The technical problem to be solved by the invention

Provided is a binarization method capable of improving image quality and compression ratio even for an image in which characters and pictures with noise components are mixed.

All. Summary of Solution of the Invention

Detects the size and orientation of the edge of the pixel of interest in the scanned image, compares the size of the edge with a preset threshold, and examines the continuity of the edge according to the orientation when the pixel of interest is the boundary of the character. If present, the pixel of interest is binarized to the same value as the binarization value for the previous pixel in the same direction. If there is no edge continuity, the pixel of interest is binarized by applying a local threshold.

la. Important uses of the invention

It is used to binarize document images with mixed text and pictures.

Description

How to binarize text and pictures

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image input device, and more particularly, to a method for binarizing an image obtained by scanning a document in which characters and pictures are mixed.

Typically, an image input apparatus such as a facsimile, scanner, digital copier, or the like converts an analog image signal obtained by scanning a document into digital image data and processes it. At this time, the analog image signal is converted to digital image data having a gradation corresponding to the original document for each pixel. Since the gradation has a gradation, the amount of data becomes very large. For example, in the case of 256 gray levels, each pixel is represented by 8 bits. Accordingly, by binarizing the image data according to the scan, the amount of data is drastically reduced and then encoded and transmitted or a copy document is output. The binarization determines each pixel having a gray level as a white pixel or a black pixel, and the white pixel and the black pixel are represented by one bit data of 1 or 0 relatively.

1 shows a block diagram of a conventional scanner as an example of the image input apparatus. The central processing unit 100 detects the document mounting by the document detection sensor 112 and controls the image processor 104 to scan the document when a scan start command is input from the operation panel 110. The scanning unit 102 includes an optical system for scanning an original and scans the original to generate an analog image signal. The image processor 104 drives the scan unit 102 to convert the image signal output from the scan unit 102 into digital data, and to process and binarize the image. The ROM (Read Only Memory) 106 stores the operation program of the CPU 100 and various reference data in advance. The random access memory (RAM) 108 temporarily stores data according to an operation of the CPU 100. The operation panel 110 provides a key input by the user to the CPU 100. The document detection sensor 112 detects that the document is mounted and notifies the central processing unit 100.

In an image input apparatus such as the above-described scanner, binarization adopts a different method depending on the type of document image. The document image is classified into a text document consisting of text, a picture document consisting of a picture (or a picture), and a document in which text and pictures are mixed.

2 is a flowchart of an image processor 104 according to a conventional method of binarizing images in which characters and pictures are mixed. First, the image processor 104 determines the difference between these values, that is, the local brightness difference, by obtaining the maximum value and the minimum value among the peripheral pixel values of the pixel of interest, which are the pixels to be processed, in steps (200) to (204) of FIG. The brightness difference is compared with a preset threshold Tdif. At this time, if the local brightness difference is larger than the threshold Tdif, the image processor 104 recognizes that the pixel of interest is the boundary of the character and binarizes it by applying a local threshold in steps 206 to 210.

On the other hand, if the local brightness difference is smaller than the threshold Tdif, the image processor 104 recognizes that the pixel of interest is the inside of the character, the background, or the picture part in steps 212 to 228, and processes each case separately. That is, the image processor 104 recognizes that the pixel of interest is a background when the pixel value of interest is greater than the preset maximum threshold value Tmax in step 212 and binarizes the pixel of interest to white in step 214. On the contrary, if the pixel value of interest is smaller than the preset minimum threshold value Tmin in step 216, the image processor 104 recognizes that the pixel of interest is inside the character and binarizes the pixel of interest in black in step 218.

If none of the above is true, the image processor 104 recognizes that the pixel of interest is once a picture portion and checks whether there is continuity of the picture in step 220 to determine whether it is a noise component. At this time, the continuity of the area is examined under the premise that the pixels in the picture area cannot exist independently. Thus, the window shown in FIG. 3 is used as a method of examining continuity. In the window shown in FIG. 3, when the pixel x in the j column of the i-th line is the pixel of interest, the shaded peripheral pixels, that is, the j-1, j, j + 1 columns of the adjacent i-1th line, respectively When pixels and pixels in column j-1 of the i-th line exist in the picture area, it is determined that the pixel of interest also belongs to the picture area. If the continuity of the picture exists, the image processor 104 binarizes the pixel of interest in step 222 by applying an intermediate tone expression such as dithering or error diffusion. If there is no continuity of the picture, the image processor 104 binarizes by applying a global threshold in steps 224 to 228. In step 224, the image processor 104 compares the pixel value of the pixel with the global threshold value, binarizes the pixel of interest with the white pixel if the pixel value of interest is greater than the global threshold, and blackens the pixel of interest if the pixel value of interest is smaller than the global threshold. Reason with cows.

In the binarization method described above, a part regarding the criterion for determining whether the pixel of interest is the edge of the character, that is, the boundary of the character, is problematic. That is, since the edge is detected by the difference between the maximum value and the minimum value of the neighboring pixels, a portion which is not an edge of the actual character, that is, a noise component is extracted, and even though the edge of the extracted character is not straightened. Therefore, due to the non-linearized edges and the edges of noise components, the compression rate decreases when performing data compression such as run-length coding. Therefore, the transmission efficiency decreases and the image quality deteriorates.

As described above, the conventional method has a disadvantage in that the image quality is not only degraded for an image in which noise components exist but also the edges are not linearized as the edge is detected and binarized without considering the directionality and continuity of the edge. .

Accordingly, an object of the present invention is to provide a binarization method capable of improving image quality and compression ratio even for an image in which a character and a picture having noise components are mixed.

1 is a block diagram of a conventional scanner;

2 is a conventional processing flow chart,

3 is an exemplary view illustrating a method of determining continuity of a picture area in FIG. 2;

4 is a process flow diagram according to an embodiment of the present invention;

5 is an exemplary window for detecting the size and direction of a typical edge;

Figure 6 is an exemplary view showing a method for investigating continuity according to the direction in the present invention,

7 is an exemplary view illustrating a method of determining local thresholds in the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Many specific details are set forth in the following description and in the accompanying drawings to provide a more general understanding of the invention. It will be apparent to those skilled in the art that the present invention may be practiced without these specific details. And a detailed description of known functions and configurations that may unnecessarily obscure the subject matter of the present invention will be omitted.

First, the present invention binarizes an edge part in consideration of the directionality and continuity of the edge in order to solve the problem of the conventional method in the image input apparatus such as the scanner shown in FIG. In other words, if the continuity of the edge is present, the binarization result is straightened. In the case where the edge does not exist, the prior art processing method is applied as it is.

4 is a flowchart illustrating a process of binarizing one pixel for convenience, according to an exemplary embodiment of the present invention. The same applies to all pixels. It is programmed to be performed by the image processor 104 of FIG. 1 according to the flow chart of FIG. 4.

As the document is detected by the document detection sensor 112 and the scan start command is input from the operation panel 110 in the above state, the image processor 104 is controlled by the central processing unit 100 under the control of the scanning unit ( When the original is scanned by 102, an image signal corresponding to the original scan is output from the scanning unit 102. Then, the image processor 104 converts the image signal output from the scan unit 102 into digital image data, stores the pixel value in the RAM 108 in units of lines to be scanned, and performs binarization according to the flowchart of FIG. 4. do. In the following description, it is assumed that the number of lines for storing the scanned image is based on three lines as a default.

First, the image processor 104 designates the pixel of interest to be binarized in operation 300 of FIG. 4, and then detects the size and direction of the edge in operation 302. At this time, as shown in Figs. 5 (a) to 5 (d), the size and the direction of the edge are detected using four windows that can determine the direction. FIG. 5 (a) shows a window in the direction of 0 °, FIG. 5 (b) shows a window in the direction of 45 °, and FIG. 5 (c) shows a window in the direction of 90 °, and FIG. 5 (d). ) Shows the window at 135˚. 5 (a) to 5 (d) show three pixels, i.e., i-th line, i-th line and i + 1th line, respectively, By giving the corresponding weights to the pixels of the j-1 column, the j column, and the j + 1 column, the edge detection method is a known Kirsch method. Therefore, detailed description thereof will be omitted.

After detecting the size and orientation of the edge by the edge detection method using the four windows as described above, the image processor 104 determines the size of the edge, that is, four sizes obtained by using four windows in step 304. The largest of the values is compared with a preset threshold. At this time, if the size of the edge is larger than the threshold, the pixel of interest is the boundary of the text. If the edge is smaller than the threshold, the pixel of interest is not the boundary of the text, but the interior, background, or picture.

At this time, if the size of the edge is smaller than the threshold value, the image processor 104 performs steps 318 to 334 because the pixel of interest is not the boundary of the letter but the inside or the background or the picture. Steps 318 to 334 are the same as steps 212 to 228 of FIG. 2 described above. Therefore, description thereof is omitted.

On the other hand, if the size of the edge is larger than the threshold in step 304, the pixel of interest may be viewed as the boundary of the character. However, in order to prevent the degradation of the image quality or the straightening of the edge due to the noise component, the pixel may not be straightened (306). In step 316, the edge portion is binarized in consideration of the directionality and continuity of the edge.

In step 306, the image processor 104 determines whether or not the continuity with the previously detected edge is based on the direction of the edge detected in step 302. At this time, according to the directionality of the edge determined in one direction among 0 °, 45 °, 90 °, and 135 ° by the windows of FIGS. 5 (a) to 5 (d) as described above, FIGS. Examine the continuity by applying one of them. 6 (a) to 6 (d) show that the pixel of interest detected as an edge is examined for continuity with the shaded pixel. That is, when it is detected that the pixel of interest is an edge having a directionality of 0 °, it is checked whether there is an edge of 0 ° like the pixel of interest in the hatched portion as shown in Fig. 6A. Similarly, when the pixel of interest is detected to be an edge having a directionality of 45 °, it is checked whether the pixel of interest has an edge of 45 ° like the pixel of interest as shown in FIG. If it is detected that the branch has an edge of 90 degrees, such as the pixel of interest, in the hatched portion as shown in Fig. 6 (c), and if it is detected that the pixel of interest has an directional edge of 135 °, Fig. 6 Investigate whether there are 135 ° edges, such as the pixel of interest, in the hatched areas as shown in (d). By examining the continuity in this way, the edge can be straightened.

After examining the continuity in step 306, the image processor 104 checks whether the survey results are continuity in step 308. If there is continuity, the edge will be straightened if the pixel of interest is binarized with the previous pixel in the same direction. In order to straighten the edges, the image processor 104 binarizes the pixel of interest to the same value as the previous pixel in the same direction in step 310. At this time, the previous pixel becomes the hatched pixel in one of Figs. 6 (a) to 6 (d) according to the direction of the pixel of interest.

On the other hand, if there is no continuity in step 308, it is not necessary to consider the previous pixel for the pixel of interest. Accordingly, the image processor 104 applies and localizes the local threshold in the same manner as in the steps 206 to 210 of FIG. 2 described above in the steps 312 to 314. That is, the image processor 104 compares the pixel value of interest with the local threshold in step 218, binarizes the pixel of interest to white in step 220 if it is greater than the local threshold, and in step 222 if it is smaller than the local threshold. The pixels are binarized to black.

Herein, a method of determining the local threshold is shown in Figs. 7 (a) to 7 (d). Fig. 75 (a) shows that when the edge of the pixel of interest has a direction of 0 degrees, the average value of the hatched portion is set to the local threshold. Similarly, Figs. 7 (b), 7 (c), and 7 (d) show that when the edge of the pixel of interest has directionalities of 45 °, 90 °, and 135 °, the average value of the hatched portion is set to the local threshold. see. At this time, the portion marked with ▩ may be assigned a weight.

When the above-mentioned binarization process for one pixel is finished, the same operation is repeated until the next pixel is designated and binarized again until the binarization of the entire image is completed.

Therefore, since the edges are binarized in consideration of the directionality and continuity of the edges, the edges can be straightened and generation of isolation points due to noise can be prevented. Therefore, only the edges of the actual characters can be excellently extracted even for an image having a noise component.

As described above, the present invention can improve the compression ratio when compressing and encoding the binarization result when the edge continuity exists, and improve the image quality by extracting only the edge of the actual character excellently even for the image having the noise component. There is an advantage to this.

Claims (3)

In the method for binarizing an image obtained by scanning a document in which characters and pictures are mixed, Detecting a size and an orientation of an edge of a pixel of interest of the scanned image; Comparing the size of the edge with a preset threshold to determine whether the pixel of interest is a boundary of a character; If it is detected that the pixel of interest is a boundary of the character, checking whether the edge according to the directionality is continuous; Binning the pixel of interest to the same value as the binarization value for the previous pixel in the same direction when the edge is continuous; Binning the pixel of interest by applying a local threshold when there is no continuity of the edge; Binarizing the pixel of interest to a white pixel if it is detected that the pixel of interest is not a boundary of a character but a background; Binarizing the pixel of interest to black pixels if the pixel of interest is detected as being inside the character rather than the boundary or background of the character; Checking whether there is a continuity of the picture when the pixel of interest is detected as a picture rather than a boundary or background of the letter or the inside of the letter; Binarizing the pixel of interest by halftone expression when there is continuity of the picture; And binarizing the pixel of interest by applying a global threshold if there is no continuity of the picture. The binarization method according to claim 1, wherein the detecting of the size and the directionality detects the size and the directionality in four directions of 0 °, 45 °, 90 °, and 135 ° with respect to the pixel of interest. 2. The method of claim 1, wherein the continuity checking process checks the previous pixel in the same direction as the directionality of the pixel of interest, and detects that there is continuity if the previous pixel is the same directional edge, otherwise there is no continuity. Binarization method characterized by the above-mentioned.

Images