TW200539044A - Portable image-capturing interpretation electronic device and method for operating same - Google Patents

Abstract

A portable image-capturing interpretation electronic device and method for operating same, including: a photographing device for photographing a translation range. The method of operation can be categorized as "selection followed by photographing" or "photographing followed by selection." The method of "selection followed by photographing" first selects a frame to locate texts to be translated via a selection unit of the image-capturing unit at the time of photographing so as to obtain an image within the selected frame. The method of "photographing followed by selection" allows selection of the textual portions within the digitized image as obtained from photographing via the frame of the selection unit to capture an image frame as selected. Then, the texts within the image frame are recognized and translated into corresponding translation, and the translation outcomes are then displayed on a display.

Description

200539044 V. Description of the invention (1) [Technical field to which the invention belongs] The present invention relates to a portable photographic interpretation electronic device and a method for operating the same, and in particular, it can lock a text to be translated through a selection box to recognize and translate and generate a translation Electronic device and its operation and method: prior art], the keyboard of an electronic dictionary) is used to input and use translation modules. Generally speaking, portable interpretation electronic devices (such as external structures mainly include a keyboard and a display) Translate text, translate according to the input text to be translated (for example, Chinese to English, English to Chinese, etc.), generate corresponding translations, and display the translation results on the display. Because the portable interpretation electronic device is used Querying new words is very convenient and fast, so it has become an indispensable language learning tool for students at present. The portable interpretation electronic device is a relatively small information product. Therefore, most of them can be placed in schoolbags, handbags, and even In the pocket of clothes, it is convenient for users to carry around, and to inquire foreign language words anytime, anywhere Learn foreign languages. The smaller the size of the portable interpretation electronic device, the smaller its keyboard, which will inevitably have many restrictions on input (for example, the number of keys is limited, and a key may represent multiple letters or symbols; the area of the key is too small, which makes pressing Increasing the probability of wrong keys), resulting in inconvenient input, resulting in some disadvantages (for example, complex input methods, long input time, etc.) In addition, for language learners (especially beginners), the use of Entering foreign language text (such as Japanese, Korean, French, German, etc.) is a very difficult challenge for portable interpretation electronic devices, because most language learners have not learned foreign language input methods, so it is impossible Easily in the circle ...

Page 5 200539044 V. Description of the Invention (2), Enter foreign language text on the portable interpretation electronic device. In addition, if you want to input foreign language text on the portable interpretation electronic device, the keyboard of the portable interpretation electronic device must also have input keys (input symbols) corresponding to the foreign language text, which makes the use of the keyboard more complicated. Translation has also become more difficult. Due to the difficulty of entering foreign language text, the practicality of the portable interpretation electronic device is greatly reduced. Therefore, a simple and efficient input method is very important for the portable interpretation electronic device. In order to solve the input problem of the portable paraphrasing electronic device, the related prior technology is to combine the portable paraphrasing electronic device with a scanner, that is, a translation pen. The translation pen has a pen-shaped casing, and a scanning device (scanner) is provided at one end of the pen-shaped casing. The translation pen includes a light-emitting element for generating light to be projected onto the text to be translated; a charge-coupled element (CCD ) To receive the light reflected by the text to be translated and generate an electronic potential signal correspondingly; an analog / digital converter to convert the electronic potential signal into a digital signal; a data register · to store the digital signal Image data; a character recognition controller to identify the image data and generate the text of the text to be translated; a translation module to query the translation corresponding to the text string; and display the translation result through the display on the pen-shaped casing. However, the aforementioned translation pen of the prior art is a way to replace keyboard input by scanning the screen. Although it can solve the problem of foreign language text input, the translation pen can only scan the text on the flat file at a close distance, and There are some restrictions on the scope and functions (for example, large text cannot be recognized after scanning). Therefore, the related prior art combines portable paraphrasing electronic devices with

Page 6 200539044 V. Description of the invention (3) A camera-type electronic translator with two types of cameras. The device has a camera and is also an input device. The camera-type electronic translator includes a lens for collecting light in a range to be translated; a charge-coupled device (CCD) for generating corresponding electronic signals according to the collected light; an analog / digital A converter for converting an electronic signal into a digital signal, an image temporary storage area for storing the image material of the digital signal, a display unit for displaying the digital image of the image data, and a character recognition unit for A text string is generated by identifying image data; a language translation unit is used to query the corresponding translation of the text string and display the translation result through the display unit. Compared with the above-mentioned camera-type electronic translator and translation pen, the advantage is that the camera-type electronic translator can shoot the text to be translated from a long distance (for example, the text on an advertisement signboard or a kanban board), regardless of the distance and the size of the text. The disadvantage is that the recognition accuracy of the text is low and the processing time required is long. [Summary of the Invention] In view of the shortcomings of the related-art photographic electronic translators, the reasons are due to the images taken by the photographing device, which covers a wide range (more non-text image blocks) , Especially around the image), and the background is more complex, which results in a low recognition rate and a long processing time. In fact, the image block of the text to be translated in the captured image only occupies a small part. Therefore, if only the text portion in the image is selected, the scope of the recognition module can be reduced, and the accuracy of text recognition can be increased. Reduce the time required for text recognition. Therefore, the object of the present invention is to provide a portable photographic interpretation electronic device.

Page 7 200539044 V. Description of the invention (4) The device can reduce the range of the image by selecting the text portion of the image to increase the accuracy of text recognition and reduce the time required for text recognition. The device includes: a photograph A unit to capture a range to be translated; a display unit to display digital images of the range to be translated and display translation results; a selection unit whose implementation is divided into "select first, then photo" and "first photo, then select" Among them, "select first and then take" is to lock the text to be translated through the selection box of the selection unit on the viewfinder when shooting, and capture a selection box image. "Picture first, then select" is the picture on the display unit. The digital image selects the text portion of the digital image through the selection box of the selection unit to capture a selection frame image; a recognition module is used to identify the selection frame image, Generate a text string; and a translation module to query the translation corresponding to the text string. The photographing unit includes a lens to collect light in the range to be translated; an image sensing unit to generate corresponding electronic signals according to the light collected by the lens; a signal conversion unit to convert electronic signals into digital signals; A storage unit is used to store the image data of the digital signal; and a video conversion unit is used to convert the image data into a video output signal and display the digital image on the display unit. Another object of the present invention is to provide a method for operating a portable photographic interpretation electronic device, which has a photographing unit, a display unit, a selection unit, a recognition module, and a translation module. "Select first, then take" and "select first, then select", the steps are explained as follows: Among them, "select first and then take" is to lock the text to be translated through the selection box of the selection unit on the viewfinder when shooting, and capture a selection Frame image; "first shot

Page 8 200539044 V. Description of the invention (5) Reselection ”means that the digital image on the display unit after shooting is selected through the marquee of the selection unit to select the text portion of the digital image to capture a marquee image. Then, the recognition module recognizes the marquee image to generate a text string; and the translation module queries the translation corresponding to the text string. The steps of shooting the text to be translated through the photography unit include the following steps: use the lens to collect the light of the text to be translated; focus the light of the text to be translated on the image sensing unit and generate the corresponding electronic signal; use the signal conversion unit to convert the electronic signal Is a digital signal; the image data of the digital signal is stored in a storage unit; and the video conversion unit is used to convert the image data into a video output signal and display the digital image on the display unit. Regarding specific and feasible implementation modes of the present invention, the following description is given with reference to the drawings: [Embodiment] "Figure 1" is a description of a preferred embodiment of a portable photographic interpretation electronic device according to the present invention, which can be applied to translation Phones, digital assistants (PDAs), mobile phones and digital cameras. As shown in "Figure 1", it contains a photographing unit 10 for shooting a range to be translated (for example, shooting text on books, newspapers, magazines, etc., or ', or advertising signs, kanban boards, etc. Text) to produce a digital image of the range to be translated. The range to be translated is the landscape range formed by aiming at the subject through the viewfinder, and the range to be translated is less limited by distance and font size. The portable photographic interpretation electronic device of the present invention includes a display unit 20 for displaying a digital image taken. The display unit 20 is a display of a translator, and a liquid crystal display is preferred, and a super-twisted orientation can be used. LCD

Page 9 200539044 V. Description of the invention (6) Display (STN-LCD) or thin-film transistor liquid crystal display (TFT-LCD). It is better to use a touch-sensitive display. The display unit 20 can display not only the captured digital images, but also information during translation, for example, a selection box image of the selection unit 3 0, a text string recognized by the text recognition module 40, and a translation module 5 0 translation results. The portable photographic interpretation electronic device of the present invention is characterized by including a selection unit 30, and its implementation modes are divided into "choose first and then photograph" and "choose first and then choose", which are respectively explained as follows: “Photo”: Set the position of a selection frame on the viewfinder of the photography unit 10 through the selection unit 30 during shooting. After pressing the shutter button, a selection frame image can be generated. The feasible implementation method is as follows: the selection unit 30 includes a control interface for controlling a selection box, wherein the control interface includes a set of directional control buttons (or arrow keys), and has at least four of up, down, left, and right Direction buttons (buttons) enable the selection frame to be moved up, down, left, and right in the viewfinder to lock the text to be translated. The selection frame includes a vertical frame and a horizontal frame, which are used to lock the type of text in different arrangements. In addition, the control interface can adjust the size of the marquee to match the size of the text to be translated. Alternatively, a display unit can be used instead of the viewfinder. "Picture first, then select": After shooting, the digital image on the display unit is selected through the selection unit 3 Q, and a selection frame is set to the text portion of the digital image to select a selection frame image. The feasible implementation method is as follows: (A) The selection unit 30 includes a control interface for manipulating a selection box, wherein the selection box can be a vertical box and a horizontal box, and is used to lock the text types of different layout methods. The control interface contains a set of directional control buttons (or

Page 10 200539044 V. Description of the invention (7) Direction key), it has at least four direction buttons (keys) of up, down, left and right, so that the selection box can be moved up, down, left and right to the text to be translated to capture a selection In addition, the size of the selection frame can also be adjusted using the control interface to match the size of the text in the digital image; or (b) the selection unit 30 includes an indicator device for manipulating an indicator selection on the display unit. The text to be translated generates a marquee image containing the text to be translated. The pointing device can be a stylus. Select (circle or click) the text portion of the digital image on the touch display to obtain a marquee image. . The portable photographic interpretation electronic device of the present invention includes a recognition module 40 for recognizing a selection frame image of a selection unit and identifying a text string (plain text) of text to be translated. The recognition module 40 is an optical character recognition (OCR) system, which is an image processing software that analyzes and processes digital images and recognizes the text contained in the digital images. Technology is not a feature of the present invention, so I will not go into details. The purpose of the present invention is to use an optical text recognition system to process the marquee image, not the entire digital image that is captured. Therefore, the unnecessary background image and noise can be removed first to reduce the amount of data for image processing. In this way, the accuracy of text recognition and the time required for text recognition can be reduced. The portable photographic interpretation electronic device of the present invention includes a translation module 50 for querying the translation corresponding to the recognized text string. Among them, as shown in "Figure 2", the translation module 50 includes an editing module 52. When the text string recognized by the recognition module 40 is partially wrong, it is used to edit it to be correct.

Page 11 200539044 V. Description of the invention (8) Translation text; a query module 5 4 with a dictionary database 5 5 can be a multi-language database, including English-Chinese translation, Chinese-English translation Translations, Chinese-Chinese explanations, English-English explanations, etc., used to match a corresponding translation based on the text string to the dictionary database 5 5. Therefore, the translation can be a translation in different languages of the text, or The interpretation of the same language of the text; a fuzzy query (spell correction) module 5 6 is used to automatically match the most appropriate translation from the dictionary database 5 5 when the text _ cannot match a corresponding translation; An output module 58 is used to output a translation result (including at least a text string and a corresponding translation), and display the translation result on the display unit 20. "Fig. 3" is a block diagram illustrating a photographing unit of a portable photographic interpretation electronic device according to the present invention. As shown in Fig. 3, the photographing unit includes a lens for collecting light of text to be translated. This lens is a zoom lens (optical zoom, digital zoom), and can be focused manually or automatically. The camera unit also includes a viewfinder (or replace the viewfinder with a liquid crystal display) and a shutter button. The user forms a range to be translated through the viewfinder, and starts the shooting process of the image after pressing the shutter button. The viewfinder can be displayed by the display unit. Instead of 2 0, the shutter key is a function key; an image sensing unit is composed of image sensing elements, such as a charge coupling device (CCD), complementary metal oxide semiconductor (CMOS), or contact image sensing (CIS ) ... etc., receive the light collected by the lens through the above-mentioned image sensing element, focus on the image sensing element, and generate the corresponding electronic signal; a signal conversion unit is an analog / digital converter to convert the image The electronic signal of the sensing unit becomes the corresponding digital signal; a storage

Page 12 200539044 V. Description of the invention (9) The storage unit is a type of memory (for example, Random Access Memory, RAM) or a memory card, which is used to store the image data of digital signals in the storage unit A video conversion unit is a video converter that converts the image data of the storage unit into a screen output signal and displays the digital image on the display unit. Therefore, as long as the lens is aimed at the text to be translated, the translation can be performed after pressing the shutter button. There is no need to use the keyboard for input, and no input error will occur. It can save the time required for input and solve foreign text input. Tricky question. "Figure 4-A" is a flowchart of the operation method of the portable photographic interpretation electronic device of the present invention. Please refer to "Figure 4-A" and explain as follows: It has a photographing unit, a display unit, and a Selection unit, one identification module, one translation module. On the viewfinder of the photography unit (or can be replaced by the display unit), lock a text to be translated through the selection frame of the selection unit, and when the shutter button of the photography unit is pressed, a selection frame image can be obtained (step 4 0 0); The selection frame can be moved through a control interface. The selection frame can be a vertical frame or a horizontal frame, and the size of the selection frame can be adjusted to fit the text size. The above selection frame image is displayed on the display unit (step 4 1 0 ); After that, the marquee image is recognized by the recognition module to obtain the corresponding text string (step 4 2 0); receiving the text string, passing the text string through the translation module, and querying the translation corresponding to the text string (step 4 3 0) (including the result of the fuzzy query), and output the translation result (the text string and its corresponding translation) to the display unit. "Figure 4-B" is a flowchart of the operation method of the portable photographic interpretation electronic device of the present invention, please refer to "Figure 4-B", and it is explained as follows:

Page 13 200539044 V. Description of the invention (10) It has a camera unit, a display unit, a selection unit, a recognition module, and a translation module. A digital image of a range to be translated is captured by a photography unit to generate a digital image of the range to be translated (step 4 40); the above digital image is displayed on the display unit (step 4 50); the digital image on the display unit passes through the selection unit Marquee Select the text portion of the digital image to capture a marquee image (step 460); where the marquee can be moved through a control interface, and its marquee can be a vertical or horizontal frame, and can be resized Select the frame to match the text size of the digital image; then, identify the selection frame image with the recognition module to obtain the corresponding text string (step 470); receive the text string and feed the text string into the translation module. The translation corresponding to the query text string (including the result of the fuzzy query) (step 480); and outputting the translation result (the text string and its corresponding translation) to the display unit. "Figure 5" is a flowchart of the photographic unit of the portable photographic interpretation electronic device of the present invention. The operation method of the photographic unit is as follows: First, aim the lens at the range to be translated (the target with text). The method is ( a) Place the text to be translated in the middle of the viewfinder; or (b) Place the text to be translated in the middle of the display. At this time, the lens will focus. When the user presses the shutter button, the light in the range to be translated can be collected through the lens (step 50 0); the image sensing unit receives the light in the range to be translated and focuses the light in the range to be translated. On the image sensing element, a corresponding electronic signal is generated (step 5 1 0); the signal conversion unit receives the above electronic signal and converts it into a corresponding digital signal (step 5 2 0); using a storage unit to store the above digital Image data of the signal (step 530); and using the video conversion unit, the image data

Page 14 200539044 V. Description of the invention (11) The material is converted into the video output signal and the digital image is displayed on the display unit (step 5 40). The above is only the preferred embodiment of the present invention. Is not intended to limit the scope of implementation of the present invention; that is, all equivalent changes and modifications made in accordance with the scope of patent application for the present invention are covered by the scope of the present invention patent.

Page 15 200539044 Brief Description of the Drawings Figure 1 is a block diagram of the portable photo interpretation electronic device of the present invention; Figure 2 is a translation module of the portable photo interpretation electronic device of the present invention Block diagram; Figure 3 is a block diagram of a photographic unit of a portable photographic interpretation electronic device according to the present invention; Figure 4-A is a method of operating a portable photographic interpretation electronic device according to the present invention Flowchart; Figure 4 -B is a flowchart of the operation method of the portable photographic interpretation electronic device of the present invention; and Figure 5 is a photograph of the portable photographic interpretation electronic device of the present invention Flow chart of the unit. [Illustration of symbolic symbols] 10 camera unit 11 shutter button 12 lens 14 image sensor unit 16 signal conversion unit 18 storage unit 19 video conversion early unit 20 display early unit 30 select unit 40 identification mode group 50 translation mode group

Page 16 200539044 Figure. 弍 Brief description 52 Editing module 54 Query module 55 Dictionary database 56 Fuzzy query module 58 Step out module 400 Set the position of the marquee step 410 Display the marquee image Step 420 Identify the marquee image, Generate text string Step 430 Query text • Corresponding translation step 440 Capture the range to be translated Step 450 Display the digital image of the range to be translated Step 460 Select the text portion of the digital image to obtain a marquee image Step 470 Identify the marquee image to generate a text string Step 480 Query text string corresponding translation Step 500 Collect the ArAr consumed light to be translated Step 510 Generate the corresponding electronic signal Step 520 Convert the electronic signal to a digital signal Step 530 Store image data of digital signal Step 540 Convert image data to video m output signal and display digital image

Claims (1)

200539044 VI. Application for patent scope 1. A portable photo-interpretation electronic device, the system includes a photographic range to be translated; a display unit for displaying a digital image of a range of translation and displaying a translation result; The text portion of the digital image generates one and one translation modules for receiving the text string and querying the corresponding translation, which is characterized in that: a selection unit is used to execute the image at the position where one of the photographing units is framed Generate the marquee image for recognition and translation during capture, using a unit to capture and display the text string of the identification module to be turned over; the text string the device includes a viewfinder set to select a marquee to generate the translation 2. If you apply for special placement, 3. If you apply for special placement, frame 4 of the frame. 4. If you apply for special placement, of which 5. If you apply for special placement, which is the same as the image of the arranger, you will write. The viewfinder is the best range, and the selection range is the best. The range of profit is the control of the range of interest. The text of the selection box is 6. A kind of portable photo release unit is used to photograph and display the module to be turned. Use the range of translation to identify the possible items described in 1 item. The portable camera interpretation electronic system can be replaced by the display unit. The portable photographic interpretation electronic device described in item 1 includes a control interface for moving the portable photographic interpretation electronic device described in item 3, and the size of the marquee can be adjusted. The portable photographic interpretation electronic device described in item 1 is a vertical frame or a horizontal frame ^ to lock different types. Electronic device, the system includes a photographic range to be translated; a display unit for displaying a digital image and a translation result; and identifying a text portion of the digital image to generate a text Page 18 200539044 VI. Patent application string; and a translation corresponding to the translation pattern string The device includes a marquee image and a marquee image to translate the translation. 7. If the scope of the patent application is set, the position of the selection frame. 8. If the scope of the patent application is set, the control is 9; if the scope of the patent application is set, the selection is the same as the arrangement of the article 10. — A portable camera includes the following steps: setting a selection to display the selection to identify the selection Receiving the text 1 1. If the operation method is set in the patent application, it is used to lock different series 1 2 — a kind of portable camera The if group 5 is used to receive the text string and query the text, and is characterized by: a selection unit for manipulating the text portion of the digital image on the display unit to obtain a selection marquee image for identification and translation, In order to generate the portable photographic interpretation electronic installation unit described in item 6, including a control interface for moving the portable photographic interpretation electronic installation interface described in item 7, the size of the marquee can be adjusted. . The portable photo-interpretation electronic frame described in item 6 is a vertical frame and a horizontal frame to lock the untyped type. The operation method of the electronic device is explained, and its feature includes the position of the frame to generate a selection frame image; the frame image; the frame image to generate a text string; and to query the translation corresponding to the text string. The portable photographic interpretation electronic device described in item 10, wherein the selection frame is a vertical frame or a horizontal frame, and the type of the text is in a line style. Interpretation of operating method of electronic device, its characteristic package Page 19, 200539044 6. The scope of patent application includes the following steps: shooting a range to be translated; displaying a digital image of the range to be translated; obtaining a marquee image that moves a marquee to the text portion of the digital image; identifying the marquee image Generate a text string; and receive the text _, query the translation corresponding to the text string. 13. The operating method of the portable photo-interpretation electronic device as described in item 12 of the scope of patent application, wherein the selection frame is a vertical frame or a horizontal frame to lock the type of text in different layout methods. Page 20