JP2010011316A - Image processing apparatus, image processing method, image processing program, and recording medium with the program recorded thereon - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processing apparatus capable of displaying images of comics so as to easily view characters in balloon parts of cartoons without spoiling an original image by keeping differences in frame sizes of original cartoons when electronically distributing the image data of comics. <P>SOLUTION: The image processing apparatus for processing image data includes: a contour extracting means for extracting a contour of an image; an image size adjusting means for enlarging or reducing the image in such a way that the extracted contour is settled within a standard area displayed on a display part of a terminal when the image is electronically distributed; a character string recognizing means for recognizing a character string in the image; and a character size adjusting means for enlarging or reducing characters, constituting the recognized character string, to a predetermined size. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

The present invention relates to an image processing apparatus for displaying a digital image of a comic or the like on a terminal such as a personal computer, a mobile phone, or a PDA.

In recent years, services for electronically distributing various contents such as games and comics have been spreading for mobile phones, PDAs and the like. For example, when a comic is electronically distributed, each comic frame is downloaded as one image data to a mobile phone or the like. In creating the image data for electronic distribution, editing such as reading a manuscript document already printed on a paper medium with a scanner, shaping the image, cutting out each frame, and applying an effect is performed. However, image data editing is generally performed by a human operation using image editing software, which is very troublesome.

By the way, since the display part of portable terminals, such as a mobile phone, is not so large, there exists a problem that characters, such as words displayed on the speech balloon part, are difficult to read. In order to eliminate such difficulty in reading characters, for example, it has been proposed to play back character information of a balloon corresponding to an image after a predetermined time has elapsed after playing back image data of a still image comic (patent) Reference 1 or 2). With such a configuration, the user can confirm the character information of the balloon portion with a large character. In addition, it has also been proposed to improve visibility to the user by enlarging and displaying only predetermined frames of the comic image data (Patent Document 3). According to this method, it is possible to solve the problem of poor visibility without performing a frame advance operation.

JP 2005-204338 A JP 2006-139710 A JP 2003-76666 A

However, in the case of Patent Document 1 or 2, since the character information is displayed over the image, the original image may be broken, and the displayed comic (picture) is fully enjoyed. Even if it is desired, there is a problem that character information is displayed after a predetermined time has elapsed. Further, even in the case of Patent Document 3, if the original is displayed in a small frame but is enlarged more than necessary, the image of the original may be destroyed. In the present invention, when electronically distributing comic image data, image processing is performed such that characters in the comic balloon can be displayed easily without leaving a difference in the size of the frame in the original, and without destroying the original image. Providing equipment.

The present invention is an image processing apparatus for processing image data, and includes a contour extracting means for extracting a contour of an image, and a standard region displayed on a display unit of a terminal when the extracted contour electronically distributes the image. Image size adjusting means for enlarging or reducing the image so as to fit in the image, character string recognizing means for recognizing the character string in the image, and enlargement or reduction so that the characters constituting the recognized character string have a predetermined size The present invention relates to an image processing apparatus comprising character size adjusting means. With this configuration, the image (frame) is not enlarged or reduced more than necessary, so image editing that can be displayed on a mobile phone or the like while reflecting the difference in size of the frame in the original comic. It becomes possible. In addition, since the character size is also adjusted to a predetermined size, the visibility is excellent, the character size of each frame is unified, and a sense of incongruity between frames does not occur.

When processing a plurality of images, the image processing apparatus may include a standard region setting unit that sets the standard region according to the contour size and / or image complexity of the plurality of images extracted by the contour extraction unit. preferable. With such a configuration, it is possible to set a standard area according to each work to be distributed electronically, and to perform image processing without performing unnecessary enlargement or reduction processing.

A character information recognition unit that recognizes character information of a character string recognized by the character string recognition unit, and an expanded character string that is formed by an enlarged character expanded by the character size adjustment unit includes a balloon surrounding the character string. A balloon area determining means for determining whether or not the character string is within the area; and a character information recognized by the character information recognizing means when the enlarged character string does not fit in the balloon area and And when the line feed character string obtained by executing the line feed of the expanded character string before or after the expanded character having character information that matches the line breakable character fits within the balloon area, the expanded character string It is preferable that it comprises a line feed executing means for executing the line feed. With such a configuration, even when the enlarged character string does not fit in the speech balloon, editing can be performed so that it fits in the speech balloon. Since line breaks are only made when the line breaks do not make it difficult to read, there is no particular difficulty in reading due to line breaks.

In addition, a character information recognition unit that recognizes character information of the character string recognized by the character string recognition unit, and an expanded character string that is composed of the expanded characters expanded by the character size adjustment unit A balloon area determining means for determining whether or not the character string is within the area, and a character information recognized by the character information recognizing means when the enlarged character string does not fit in the balloon area; When the character spacing adjustment character string obtained by executing the adjustment between the enlarged character having character information that matches and the character information matching the character spacing adjustment character and the adjacent enlarged character fits in the balloon area, It is preferable to comprise character spacing adjustment execution means for performing the character spacing adjustment. With such a configuration, even when the enlarged character string does not fit in the speech balloon, editing can be performed so that it fits in the speech balloon. Since adjustment between characters is performed only when adjustment between the characters does not make it difficult to read, the problem of difficulty in reading due to adjustment between characters does not occur.

A balloon area determining means for determining whether or not an enlarged character string composed of the enlarged characters enlarged by the character size adjusting means fits in a balloon area surrounding the character string, and the enlarged character string does not fit in the balloon area. It is preferable to include a balloon area adjusting unit that adjusts the balloon area so that the balloon area is enlarged when there is not. With such a configuration, even when the enlarged character string does not fit in the speech balloon, editing can be performed so that it fits in the speech balloon.

The present invention relates to an image processing method for processing image data, a contour extracting step for extracting the contour of an image, and a standard region in which the extracted contour is displayed on a display unit of a terminal when the image is electronically distributed. An image size adjusting step for enlarging or reducing the image so as to fit within, a character string recognizing step for recognizing a character string in the image, and an enlargement or reduction so that the characters constituting the recognized character string have a predetermined size The present invention relates to an image processing method including a character size adjustment step for reduction.

The present invention also provides an outline extraction step for extracting the outline of an image, and enlarges or reduces the image so that the extracted outline is within a standard area displayed on the display unit of the terminal when the image is electronically distributed. An image size adjusting step, a character string recognizing step for recognizing a character string in the image, and a character size adjusting step for enlarging or reducing the character constituting the recognized character string to a predetermined size. The present invention relates to a program for causing a computer to execute a processing method.

Further, the present invention provides a contour extraction step for extracting the contour of an image, and enlarges or reduces the image so that the extracted contour is within a standard area displayed on the display unit of the terminal when the image is electronically distributed. An image size adjusting step, a character string recognizing step for recognizing a character string in the image, and a character size adjusting step for enlarging or reducing the character constituting the recognized character string to a predetermined size. The present invention relates to a computer-readable recording medium recording a program for causing a computer to execute a processing method.

According to the present invention, when editing comic image data, since the frame is not enlarged or reduced more than necessary, it is possible to leave a difference in the size of the original frame. It can be displayed on a mobile phone or the like without breaking. In addition, since the character size is also adjusted to a predetermined size, the visibility is excellent, the character size of each frame is unified, and a sense of incongruity between frames does not occur.

FIG. 1 is a diagram showing a hardware configuration of an image processing apparatus according to the present invention. An image processing apparatus according to the present invention includes a control unit 101 that controls the entire image processing apparatus, a memory unit 103 that stores data, an information input unit 105, a contour extraction unit 107, and an image size adjustment unit 109. , Character string recognition unit 111, character size adjustment unit 113, standard area setting unit 115, character information recognition unit 117, balloon region determination unit 119, line feed execution unit 121, character spacing adjustment unit 123, balloon region adjustment unit 125, display unit 127, and each processing unit is connected by a bus 129.

The control unit 101 corresponds to a CPU (Central Processing Unit). The memory unit 103 is generally composed of a ROM (Read Only Memory) and a RAM (Random Access Memory). The display unit 127 corresponds to a display.

Next, referring to FIG. 2, the flow of image processing according to the present invention will be described. First, in step S <b> 10, image data is received by the information input unit 105. The information input unit 105 may be a scanner that converts an image drawn on a paper medium into digital data, or may receive image data that has been converted into digital data in advance. Normally, image data read by a scanner is subjected to various processes such as tilt correction, filter processing for removing dirt and stains, and segmentation for each frame by image editing software. It may be performed by a processing device, or image data that has been edited in advance may be input to the information input unit 105.

In step S12, the contour extraction unit 107 extracts the contour of the image. When the image is processed frame by frame, the outline of the frame is extracted. Each pixel is digitized based on the density of each pixel in the image data input by the information input unit 105. For example, it is 255 for white and 0 for black, and is represented by one of density values from 0 to 255 depending on the color density. Here, all the pixels of the image data are scanned in the vertical direction and the horizontal direction, and pixels whose density value change with the adjacent pixels is equal to or greater than a predetermined value are extracted. That is, only a pixel adjacent to a pixel having a completely different density value is extracted, as in the case where a black pixel and a white pixel are adjacent to each other on the left, right, or top. The extracted pixels include pixels other than the pixels that form the contour of the image. By extracting only the outermost pixels among the extracted pixels, the contour of the image, that is, the contour of the frame can be extracted. . The outermost pixel is the pixel at the top and the pixel at the bottom of the pixel in a certain column, the pixel at the left of the pixel in the row and the pixel at the right of the pixel Point to. The outermost pixel can form a line segment, which becomes the outline of the frame.

In step S14, the standard area setting unit 115 sets the standard area. The standard area represents an area displayed on the display unit of the terminal when the processed cartoon image data is electronically distributed to the terminal, and is usually rectangular. The image size adjustment, which will be described later, is performed based on this standard area. The ratio between the vertical length and the horizontal length of the standard area depends on the ratio of the display unit of the electronically distributed terminal, and can be set depending on the type of the electronically distributed terminal. For example, when an image is electronically distributed to a mobile phone and the ratio of the vertical length to the horizontal length of the display unit is 1.5 to 1, the vertical length and horizontal width of the standard area The ratio of lengths in the direction is 1.5 to 1.

Some works tend to be relatively large, while others tend to be relatively small. In addition, if there are works that have a finely detailed design or a lot of text, the design is relatively easy. Because there are works that are expressed in or with few characters, the standard area is set for each work. When there are a plurality of frames to be processed, the standard region is set according to the outline size of the plurality of frames extracted by the contour extraction unit. For example, an average value is taken for the vertical length of the frames, and the average value is the vertical length of the standard area. When the ratio of the vertical length and the horizontal length of the standard area is determined to be 1.5 to 1, the horizontal length of the standard area is 2 of the average value for the vertical length. / 3. Also, for example, among the plurality of frames, the vertical length with the largest number is the vertical length of the standard region, and the standard region is calculated based on the ratio of the vertical length and the horizontal length of the display unit. It is also possible to set the length in the horizontal direction.

Also, the size of the contour region can be determined not only according to the size of the frame but also according to the complexity of the image, that is, the complexity of the pattern drawn in the frame. For example, all the pixels of the image data are scanned in the vertical direction and the horizontal direction, and pixels whose density value changes with adjacent pixels are equal to or greater than a predetermined value are extracted. Then, the size of the standard area is set according to the number of extracted pixels. If the number of extracted pixels is large, the design is complicated. Therefore, by setting the standard area small, the image is adjusted so that characters and designs in the frame are displayed larger on the terminal during electronic distribution. On the other hand, when the number of extracted pixels is small, the design is simple and the standard area is set to be relatively large. For example, as described above, even when the average value is taken for the length of the frame in the vertical direction and the standard area is determined based on this average value, the change in the density value between adjacent pixels is a predetermined value. It is possible to change the size of the standard area between a large number and a small number of pixels. The correspondence between the number of extracted pixels and the setting of the size of the standard area can be determined in advance. For example, when the size of the standard area when the number of extracted pixels is 100 or less is 1, When the number of extracted pixels is 101 or more, the size of the standard area can be set as small as 0.95. In this embodiment, the standard area setting unit 115 automatically sets the standard area. However, a person may manually set the standard area after confirming the contents of each work. Is possible.

In step S16, the image size adjustment unit 109 enlarges or reduces the image so as to be within the standard area. FIG. 3 is a diagram showing the relationship between the standard area and the frame in the present invention. FIG. 3A shows the relationship between the standard area and the frame before the image adjustment by the image size adjusting unit. The balloon 205 in which the person 205 and the line of the person are written in the frame 201. Is drawn. Since the frame 201 is larger than the standard area 203, when the image is not reduced, the frame 201 cannot be accommodated on the display unit of the terminal during electronic distribution, and a part of the balloon 207 is not displayed. FIG. 3B shows the relationship between the standard area and the frame after the image adjustment by the image size adjustment unit. The frame 201 is contained in the standard area 203. Therefore, the frame 201 fits on the display unit of the terminal during electronic distribution, and both the person 205 and the balloon 207 are displayed without being interrupted. If the image is already within the standard area before the image is reduced by the image size adjusting unit 109, the image may be enlarged within the standard area, and the enlargement process is not performed. May be.

In step S18, the character string recognition unit 111 recognizes a character string in the image. FIG. 4 is a diagram illustrating a frame (FIG. 4A) to be subjected to image processing and a histogram (FIG. 4B) for recognizing a character string. In FIG. 4A, a person 205 and a speech bubble 207 are drawn in the frame 201, and a speech string and a character string constituting a kana of the speech are drawn in the speech bubble 207. First, the frame 201 is divided into an arbitrary number of rectangles equally from the top in the horizontal direction. In FIG. 4A, it is divided into six. Then, all the pixels in each divided rectangle are scanned in the vertical direction. For each rectangle, when the horizontal direction of the image is the x-axis and the horizontal direction is the y-axis, the number of pixels whose density values are represented within a certain value (for example, density values 0 to 25) at each x coordinate. Are totaled, a histogram as shown in FIG. 4B is obtained. In this histogram, the vertical axis direction represents the number of pixels of black or a color very close to black in each x coordinate. Each peak in the histogram corresponds to the character string in the balloon 207, and the peak width corresponds to the width of the character string. Accordingly, the peak of the character string corresponding to the speech bubble 207 has a wide width and a high peak. On the other hand, the peak of the character string corresponding to the phonetic name of the balloon 207 has a narrow width and a low peak height. When a character string exists in a scanned rectangle, a peak having a wide width and a high height and a peak having a narrow width and a low height are alternately obtained. It can be seen that there is a character string. Thus, the character string can be recognized by specifying the x coordinate and the y coordinate where the character string exists. Here, the frame 201 is equally divided into a plurality of rectangles from the top. This is to eliminate the influence of pixels constituting the pattern other than the character string, so that the pixels are divided into more rectangles. By scanning, a more accurate character string can be recognized. In addition, here, the frame 201 is divided into a plurality of rectangles equally divided from the top in the horizontal direction, and the pixels are scanned in the vertical direction. Further, the character string is recognized by dividing the frame into a plurality of rectangles equally divided in the vertical direction and scanning the pixels in the horizontal direction.

Next, in step S20, the character size adjustment unit 113 enlarges or reduces the character so as to have a predetermined size. The entire image is enlarged or reduced by the image size adjustment unit, and the enlargement rate and reduction rate are different for each frame, so that the character size is unified. The character size is preferably about 14 points when displayed on the terminal. At this time, enlargement or reduction can be performed for each character, but it is desirable to perform enlargement or reduction for each character string. When enlargement or reduction is performed for each character, the space between characters or the line is changed for each frame. However, if the entire character string is enlarged or reduced, such a problem does not occur.

Next, in step S22, the balloon area determination unit 119 determines whether or not the adjusted character string (enlarged character string) fits in the balloon area. Here, the enlarged character string is a character string composed of enlarged characters enlarged by the character size adjusting unit 113. The balloon area is an area composed of line segments composed of black pixels surrounding the character string before the character size is enlarged. If the enlarged character string fits within the balloon area, the image processing ends. Since the reduced character string composed of the reduced characters reduced by the character size adjusting unit 113 naturally fits in the balloon area, the image processing ends.

If the enlarged character string does not fit within the balloon area, the character information recognition unit 117 recognizes characters constituting the character string in step S24. This character recognition is performed by a normal OCR function (optical character recognition function).

Next, in step S26, a determination is made as to whether a line feed can be executed. Whether or not the line feed can be executed is based on the condition that the character information recognized by the character information recognition unit 117 matches the line feedable character. Here, the line-breakable character is a character that is determined in advance as being capable of a line break before or after that, and examples thereof include “!”, “...”, “?”, And the like. Whether the line feed is performed before or after the expanded character that matches the line breakable character can be set for each line breakable character. If the character string obtained by executing the line break of the expanded character string before or after the expanded character that matches the line breakable character fits within the balloon area, the line break executing unit 121 executes the line break in step S28. Is done. When a line break is executed, the line break is also executed in the same way with respect to the phonetic name. When a line feed is executed, the image processing ends.

If it is determined in step S26 that the line feed cannot be executed, it is determined in step S30 whether or not the character string in the character string can be adjusted. Whether or not the adjustment between characters is possible is based on the condition that the character information recognized by the character information recognition unit 117 matches a predetermined character adjustment character. An example of the inter-character adjustment character is katakana. If the character string obtained by executing the adjustment of the character between the enlarged character that matches the character adjustment character and the enlarged character positioned before and after the character is within the balloon area, the character adjustment unit 123 is set in step S32. The inter-character adjustment is executed by. The adjustment between characters refers to deleting a part of white pixels existing between the preceding and succeeding characters and closing the space between the characters. For example, when the character string is vertically written, several lines of white pixels having the same width as the width of the character string are deleted. On the contrary, when the character string is written horizontally, white pixels having the same width as the vertical width of the character string are deleted. The interval to be deleted can be set according to the character and the size of the character. When the size of the character is large, the interval to be deleted is also reduced. When the size of the character is small, the interval to be deleted is also set. It can be made relatively large. Further, according to the size of the character, it is possible to provide a minimum value of the character-to-character spacing after adjusting the character spacing. When the character spacing is adjusted, the image processing ends.

In addition, when both a line feedable character and a character adjustment character exist in the character string, the character string obtained by executing both the line feed and character adjustment of the enlarged character string is within the balloon area. If it fits, you may perform line breaks and adjust between characters at the same time.

If it is determined in step S30 that adjustment between characters is not possible, the balloon area adjustment unit 125 enlarges the balloon area in step S34. The balloon area is enlarged based on a predetermined magnification set in advance. When the balloon area is enlarged, it is determined again in step S22 whether or not the enlarged character string fits in the balloon area. Based on the expanded balloon area, it is determined whether or not line breaks can be executed and adjustment between characters is possible, and image processing is performed so that the character string fits in the balloon area.

Although the image processing apparatus has been described in the present embodiment, the present invention can also be applied to a program for causing a computer to execute these processes and a recording medium on which the program is recorded.

It is a figure which shows the hardware constitutions of the image processing apparatus concerning this invention. It is a figure which shows the flow of the image processing concerning this invention. It is a figure which shows the relationship between the standard area | region and frame | top | piece in this invention. It is a figure showing the histogram for recognizing the frame used as the object of image processing, and a character string.

Explanation of symbols

DESCRIPTION OF SYMBOLS 101 Control part 103 Memory part 105 Information input part 107 Outline extraction part 109 Image size adjustment part 111 Character string recognition part 113 Character size adjustment part 115 Standard area setting part 117 Character information recognition part 119 Balloon area determination part 121 Line feed execution part 123 character Space adjustment unit 125 Balloon area adjustment unit 127 Display unit 129 Bus 201 Frame 203 Standard area 205 Person 207 Balloon

Claims (8)

An image processing apparatus for processing image data,
Contour extracting means for extracting the contour of the image;
Image size adjusting means for enlarging or reducing the image so that the extracted contour fits within a standard area displayed on the display unit of the terminal when the image is electronically distributed;
A character string recognition means for recognizing a character string in an image;
An image processing apparatus comprising character size adjusting means for enlarging or reducing a character constituting a recognized character string so as to have a predetermined size. A standard region setting unit that sets the standard region according to the size of the contour of the plurality of images extracted by the contour extracting unit and / or the complexity of the image when processing a plurality of images. The image processing apparatus according to claim 1, wherein: Character information recognition means for recognizing character information of a character string recognized by the character string recognition means;
A balloon area determining means for determining whether or not an enlarged character string composed of the enlarged characters enlarged by the character size adjusting means fits within a balloon area surrounding the periphery of the character string;
Enlarged characters that have character information that matches the character set recognized by the character information recognition means with the predetermined line feedable character, and the character information that matches the line feedable character, when the enlarged character string does not fit in the balloon area A line feed execution means for executing a line feed of the expanded character string when a line feed character string obtained by executing a line feed of the expanded character string before or after The image processing apparatus according to claim 1. Character information recognition means for recognizing character information of a character string recognized by the character string recognition means;
A balloon area determining means for determining whether or not an enlarged character string composed of the enlarged characters enlarged by the character size adjusting means fits within a balloon area surrounding the periphery of the character string;
In the case where the enlarged character string does not fit in the balloon area, the character information recognized by the character information recognition means matches the predetermined character adjustment character and has character information that matches the character adjustment character. When the character spacing adjustment character string obtained by executing the character spacing adjustment between the enlarged character and the adjacent enlarged character fits within the balloon area, the character spacing adjustment execution means executes the character spacing adjustment. The image processing apparatus according to claim 1, wherein the image processing apparatus is an image processing apparatus. A balloon area determining means for determining whether or not an enlarged character string composed of the enlarged characters enlarged by the character size adjusting means fits within a balloon area surrounding the periphery of the character string;
The image processing apparatus according to claim 1, further comprising a balloon area adjustment unit configured to adjust the balloon area to be enlarged when the enlarged character string does not fit in the balloon area. An image processing method for processing image data,
A contour extraction step for extracting the contour of the image;
An image size adjustment step for enlarging or reducing the image so that the extracted contour is within the standard area displayed on the display unit of the terminal when the image is electronically distributed;
A character string recognition step for recognizing a character string in the image;
An image processing method comprising: a character size adjustment step of enlarging or reducing a recognized character string to a predetermined size. A contour extraction step for extracting the contour of the image;
An image size adjustment step for enlarging or reducing the image so that the extracted contour is within the standard area displayed on the display unit of the terminal when the image is electronically distributed;
A character string recognition step for recognizing a character string in the image;
A program for causing a computer to execute an image processing method including a character size adjustment step of enlarging or reducing a character constituting a recognized character string so as to have a predetermined size. A contour extraction step for extracting the contour of the image;
An image size adjustment step for enlarging or reducing the image so that the extracted contour is within the standard area displayed on the display unit of the terminal when the image is electronically distributed;
A character string recognition step for recognizing a character string in the image;
A computer-readable recording medium on which a program for causing a computer to execute an image processing method including a character size adjusting step for enlarging or reducing a character constituting a recognized character string to a predetermined size is recorded.

Images