JP2005055973A - Personal digital assistant - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To solve the problem that because a personal digital assistant has a comparatively small screen whose size is several inches, characters on the screen become small when the entire image of a photographed object is displayed on the screen, and an operator can not confirm the characters on the screen visually prior to the character recognition. <P>SOLUTION: The personal digital assistant has the screen including a first frame and second frame for display. The personal digital assistant, based on operation input into an operation part, stores an image acquired by an image acquisition part in a storage part, then calls up the image stored in the storage part to display the image on the first frame, and concerning the image stored in the storage part, displays characters included in the image on the second frame by enlarging the characters larger than those displayed on the first frame. Thereby, the characters are enlarged partially and displayed while the operator is viewing the image after photographing on the screen, facilitating the visual confirmation of the object of character recognition. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an improvement in character recognition technology in a portable information terminal such as a mobile phone or a PDA, which has an electronic camera or the like and can acquire image data.
[0002]
[Prior art]
In the above technical field, when an image is collected and recognized by a mobile terminal, the character line position is extracted from the collected low-resolution image, and then an enlarged display is performed on the partial image at the character line position. A technical idea for improving the recognition accuracy by increasing the resolution of the character line partial image has been proposed (Patent Document 1).
[0003]
[Patent Document 1]
Japanese Patent Laid-Open No. 2003-78640
[Problems to be solved by the invention]
The number of pixels of portable information terminals, particularly image acquisition means (electronic cameras, etc.) of mobile phones has increased, and those exceeding 1 million pixels have appeared. On the other hand, the screen of the portable information terminal is relatively small, such as several inches, so if you try to display all the images to be captured on that screen, the characters on the screen will become smaller (and may be crushed in some cases) There is a problem that the operator cannot visually recognize the screen before recognition.
[0005]
In addition, displaying a large number of frames and windows (hereinafter simply referred to as frames) on the screen of the mobile phone leads to a reduction in the size of each of them, and there is a problem that visibility is reduced.
[0006]
[Means for Solving the Problems]
In order to solve the above problems, for example, the following means are adopted.
[0007]
The display of the portable information terminal has a screen including the first frame and the second frame, and the portable information terminal stores the image acquired by the image acquisition unit based on the operation input to the operation unit in the storage unit. Thereafter, the image stored in the storage unit is called out and displayed in the first frame, and the characters included in the image of the image stored in the storage unit are larger than the size of the characters displayed in the first frame. Largely displayed in the second frame. As a result, while viewing the image after shooting on the screen, the characters can be partially enlarged to facilitate the visual recognition of the character identification target.
[0008]
Further, based on the operation input to the operation unit, the result of character identification by the character identification unit for the image displayed in the second frame is displayed in the first frame instead of the image stored in the storage unit. . Thereby, it is possible to efficiently utilize the limited screen space of the portable information terminal while enabling the comparison between the visual recognition of the character identification target and the character identification result.
[0009]
DETAILED DESCRIPTION OF THE INVENTION
Examples of preferred embodiments of the present invention will be described below with reference to FIGS. The embodiment of the present invention is not limited to this example.
[0010]
FIG. 1 is a configuration diagram illustrating an outline of a mobile phone 100 (which may be a PDA, and is also collectively referred to as a portable information terminal, a portable terminal, and a portable device) according to the present embodiment. When image data is input from an image input unit (image acquisition unit) 110 such as a business card, magazine, or signboard, the display unit 120 displays the display screen as a normal display frame (also referred to as a first frame). And the enlarged display frame (also referred to as the second frame) are divided into two frames, the image data input to the normal display frame 121 of the display unit is displayed, and the character line selection frame 123 is displayed in the character line candidates (images). To do. The character line image in the character line selection frame 123 in the normal display frame 121 of the display unit is cut out, enlarged, and displayed on the enlarged display frame 122 of the display unit.
[0011]
A recognition execution button 131 to be pressed when the user executes character recognition of the character line image surrounded by the character line selection frame 123 in the normal display frame 121 of the display unit 120, and recognition of the image displayed on the normal display frame 121. Select the upper character line or character string that is the object (move the character line selection frame 123 up), right-click the enlarged image of the selected character line displayed in the enlarged display frame 122 of the display unit 120 A right button 133 used for scrolling, a lower button 134 used for selecting a character line or a character string below the normal display frame 121 (moving the character line selection frame 123 downward), and an enlarged display frame 122 The left button 135 used when scrolling the enlarged image of the selected character line displayed on the left is generally used when the user makes a call. Also it is used as a button, collectively referred to as the operation input unit 130.
[0012]
FIG. 2 is a diagram illustrating a processing procedure of the mobile terminal in FIG. Control of the processing shown below is mainly performed by the control unit 140 unless otherwise specified.
[0013]
Based on the input to the operation input unit 130 by the user, the image input unit 110 such as a CCD or an image sensor provided in the mobile information terminal or the mobile phone 100 is used to capture an image to be imaged and temporarily stored in the apparatus. It is acquired as a digital image on a memory (collectively referred to as a storage unit) provided in the memory or control unit 140 (step 201).
[0014]
The digital image acquired in step 1 is displayed on the normal display frame 121 of the display unit (step 202). A character line selection frame is displayed on the character line of the digital image displayed on the normal display frame 121 of the display unit (step 203).
[0015]
Character line segmentation is performed on the character line in which the character line selection frame 123 in the normal display frame 121 of the display unit is displayed (step 204), and the extracted character line is displayed on the enlarged display frame 122 of the display unit. The display is enlarged (step 205).
[0016]
As a result, the image acquired from the input unit of the portable information terminal can be recognized while checking the image display on the display unit and comparing it with the enlarged image without having to bother with the character line to be recognized when performing character recognition. The target can be selected.
[0017]
Note that the normal display and the enlarged display are different for the same image with respect to the enlargement / reduction ratio and the display range. The enlarged display has a display range narrower than that of the normal display, and the size of characters included in the image is normal. It is displayed larger than the size of the displayed character.
[0018]
After the user finishes selecting the character line to be recognized, the user presses the recognition execution button 131 to determine the character line to be recognized (step 206).
[0019]
Character recognition is performed on the character line selected by the user as a character recognition target (step 207), and a character recognition result is output (step 208).
[0020]
The character recognition result output in step 208 is displayed in the recognition result display frame 124 (first frame) instead of the normal display frame (step 209), and the operation unit 130 performs an operation such as saving it. The user can store a part of the specific area of the image input by the image input unit 110 in the form of character recognition combined with an address book or the like.
[0021]
If the character recognition is misread or unread when the character is recognized, the user can correct it using each button of the operation input unit 130 (step 210).
[0022]
As a result, when the recognition result is confirmed and corrected after character recognition, the recognition result can be confirmed and corrected while looking at the enlarged image without looking at the subject itself. Yes.
[0023]
FIG. 3 is a diagram for explaining the display of the enlarged display frame 122 of the display unit with respect to the display example of the screen transition of the normal display frame 121 of the display unit 120 when the character line selection frame is displayed in step 203.
[0024]
The display unit 120 displays a full screen display 301 that is a character line selection screen, a currently selected line 303, and an enlarged display screen 302 of the currently selected line. When the user presses the upper button 132 or the lower button 134, this is detected, and the display of the currently selected line 303 is moved, and a new character line to be recognized is selected and displayed. When the up button is pressed, the line immediately above the currently selected line is set as the next currently selected line, and when the down button is pressed, the line immediately below the currently selected line is set as the next currently selected line.
[0025]
When the selected character line changes, an enlarged image of the selected character string row is displayed on the enlarged display frame 302 of the display unit.
[0026]
FIG. 4 shows the selected character (character surrounded by the character line selection frame 123) in the frame 121 on the display unit in the enlarged display frame 122 of the display unit. It is a figure explaining the method of displaying large.
[0027]
Since the display screen of a portable information terminal is generally small, it is often displayed on the screen in a reduced size than the captured image. In the normal display frame 401 of the display unit, the captured image data 410 is reduced to a size that fits in the frame and displayed. In the enlarged display frame 402 of the display unit, a selected character line (a character line surrounded by the character line selection frame 403) in the normal display frame 401 of the display unit is cut out from the image data, and the original image is reduced. The rate is displayed lower than that of the normal display frame.
In order to reduce the reduction ratio, the original image size is displayed as it was taken without reduction (ie, the reduction rate is 0%), or the original image size is enlarged (ie, reduced). The rate is also negative).
[0028]
FIG. 5 is a diagram illustrating screen transition of the display unit 120 after character recognition. After the character recognition result, the first character of the recognition result displayed in the recognition result display frame 501 of the display unit is selected in the frame 503. Similarly, the first character of the image data enlarged and displayed in the enlarged display frame 502 of the display unit is selected in the frame 504. When the user presses the right button 133, the recognition result selection frame 503 displayed in the recognition result display frame 501 of the display unit is moved to the right by one character from the currently selected character. Correspondingly, the selection frame 504 for image data displayed in the enlarged display frame 502 of the display unit is moved to the right by one character from the currently selected character. At that time, the scroll bar 505 is moved so that the selection frame 504 is always displayed in the screen, and the image data of the enlarged display frame 502 on the display screen is shifted. When the user presses the left button 135, the recognition result selection frame 503 displayed in the recognition result display frame 501 of the display unit is moved to the left by one character from the currently selected character. Correspondingly, the selection frame 504 of the image data displayed in the enlarged display frame 502 of the display unit is moved to the left by one character from the currently selected character. Also in this case, the scroll bar 505 is moved so that the selection frame 504 is always displayed on the screen, and the image data of the enlarged display frame 502 on the display screen is shifted.
[0029]
FIG. 6 is a diagram illustrating screen switching. After character recognition, a recognition result display frame and an enlarged display frame are usually displayed on the display unit (screen 601). The operation unit 130 displays the normal display frame and the enlarged image display frame on the display unit (screen 602), displays only the recognition result display frame on the display unit (screen 603), and displays only the normal display frame on the display unit (screen 604). Only the display frame is displayed on the display unit (605), and the screen is switched such that the recognition result display frame and the normal display frame are displayed on the display unit (screen 606). When the normal display frame is displayed in the display unit, character recognition can be performed again by determining the recognition target.
[0030]
FIG. 7 is a diagram for explaining a method of correcting a recognition result after character recognition. When the determination button is pressed on the display unit 700 in which the recognition result display frame 701 and the enlarged display frame 702 are displayed, it is possible to input a character in which the character line selection frame 703 in the recognition result display frame 701 is currently displayed. When the right button or left button is pressed, the characters before and after can be input. By placing the cursor on the character you want to correct and entering the correct character, you can save it with the correct recognition result.
[0031]
【The invention's effect】
Visual recognition of the character identification target can be facilitated.
[0032]
In addition, it is possible to efficiently utilize the limited screen space of the portable information terminal while enabling the comparison between the character recognition target and the character identification result.
[Brief description of the drawings]
FIG. 1 shows a detailed configuration diagram of a portable information terminal.
FIG. 2 is a flowchart of a character recognition method.
FIG. 3 is a diagram for explaining display of screen transition on the display unit during a character line selection operation;
FIG. 4 is a diagram illustrating a method for enlarging image data.
FIG. 5 is a diagram for explaining display of screen transition of the display unit after character recognition.
FIG. 6 is a diagram illustrating screen switching of the display unit after character recognition.
FIG. 7 is a diagram illustrating a method for correcting a recognition result after character recognition.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 100 ... Portable information terminal, 110 ... Image input part, 120 ... Display part, 130 ... Operation part, 140 ... Control part.

Claims (4)

An image acquisition unit that acquires an image to be captured, a storage unit that stores an image acquired by the image acquisition unit, an operation unit that receives an operation input, and characters included in the image acquired by the image acquisition unit are identified. A portable information terminal having a character identification unit, a display unit that displays an image acquired by the image acquisition unit and a character identification result by the character identification unit, and a control unit,
The display unit displays a screen including a first frame and a second frame;
The control unit stores an image acquired by the image acquisition unit based on an operation input to the operation unit in the storage unit, calls an image stored in the storage unit, and displays the image on the first frame. And the portable information terminal characterized by displaying the character contained in the image larger than the size of the character displayed on the said 1st frame about the image memorize | stored in the said memory | storage part on the said 2nd frame. The portable information terminal according to claim 1,
Based on the operation input to the operation unit, the control unit replaces the image stored in the storage unit with the result of character identification by the character identification unit for the image displayed in the second frame. A portable information terminal displayed on the first frame. The portable information terminal according to claim 2, wherein
The said control part edits the character identification result currently displayed on the said 1st frame based on the operation input to the said operation part, The portable information terminal characterized by the above-mentioned. The portable information terminal according to claim 2, wherein
The portable information terminal according to claim 1, wherein when the part selected in one of the first frame and the second frame moves, the control unit changes the other display accordingly.

Images