JP5150035B2 - Mobile terminal, information processing method, and information processing program - Google Patents

Description

The present invention is, for example, a mobile phone, PHS (Personal Handy-phone).
System), PDA (Personal Digital Assistant), PC (Personal Computer), digital camera, etc., recognizes the image of the character string from the read image data and converts it into a character string, or converts the converted character string into a predetermined language The present invention relates to a portable terminal , an information processing method, and an information processing program.

Conventionally, an image of a character string printed on paper is read, and an OCR (Optical Character Recognition) function is used to recognize the character string from the image and convert it into character information. An electronic dictionary that displays a translation corresponding to the character string on a display unit has been proposed (see, for example, Patent Document 1).
JP-A-5-274346

  However, in the above-described conventional technology, the process when one type of translation dictionary is installed is described, but the process when a plurality of translation dictionaries is installed is not described. Therefore, there is no description about a method for selecting a recognition dictionary to be used from among a plurality of recognition dictionaries when an image of a read character string is converted into character information using the OCR function. Similarly, there is no description of a method for selecting a translation dictionary to be used from a plurality of translation dictionaries when acquiring translation of a word read by character recognition.

  That is, in the above-described conventional technology, sufficient consideration has not been given to problems and usability in realizing character recognition corresponding to a plurality of languages or translation corresponding to a plurality of languages. For this reason, when multiple languages are supported, an appropriate recognition dictionary cannot be selected according to the read character string image, and the read character string image cannot be converted into correct character information. There was a problem. Similarly, there is a problem that an appropriate translation dictionary cannot be selected according to the recognized character string, and the recognized character string cannot be translated into a correct language.

Therefore, the present invention can easily select an appropriate recognition dictionary from a plurality of recognition dictionaries according to the language of the read character string, even when the read character string is used. Can be converted into correct character information, and an appropriate translation dictionary can be easily selected from multiple translation dictionaries according to the recognized character string. An object of the present invention is to provide a portable terminal , an information processing method, and an information processing program that can be translated into Japanese.

In order to achieve the above object, the portable terminal according to the first aspect of the present invention is used when recognizing image capturing means for capturing image information and identification information included in the image information captured by the image capturing means. a recognition dictionary corresponding to a plurality of languages, storage means for storing a recognition dictionary used history table describing the use history of the recognition dictionary corresponding to the plurality of languages, history of use described in the recognition dictionary using the history table Recognition means for recognizing identification information included in the image information captured by the imaging means using a recognition dictionary according to the order obtained from the above (in ascending / descending order) .

As a preferred aspect, for example, as in claim 2, in the mobile terminal according to claim 1, the use history of the recognition dictionary is the number of times of use of each recognition dictionary , and the recognition means You may use the recognition dictionary according to the order of use of a dictionary .

As a preferred embodiment, for example, as in claim 3, in the mobile terminal according to claim 1, the use history of the recognition dictionary is the latest use time of each recognition dictionary , and the recognition means You may use the recognition dictionary according to the youngest order of the newest use time of a recognition dictionary .

In a preferable embodiment, for example, good urchin according to claim 4, wherein, in the portable terminal according to claim 1, the recognition dictionary instruction means for instructing whether of recognition dictionary corresponding to the plurality of languages, using any recognition dictionary The recognizing means, when instructed by the recognizing dictionary instruction means, uses the recognition dictionary in accordance with the instruction by the recognizing dictionary instruction means, to convert the image information captured by the imaging means into image information. The included identification information may be recognized.

Moreover, as a preferable aspect, for example, as in claim 5, in the portable terminal according to claim 1, related information related to the identification information is described, a translation dictionary corresponding to a plurality of languages, and the recognition unit A translation dictionary determining unit that determines a translation dictionary to be used from among translation dictionaries corresponding to the plurality of languages, and a translation dictionary determined by the translation dictionary determining unit. A translation unit that translates identification information included in the image information recognized by the recognition unit may be provided.

In a preferable embodiment, for example, good urchin of claim 6, wherein, in the portable terminal according to claim 5, further translation language specifying means for specifying a translation language provided, said translation dictionary determining means, the recognition dictionary Instead, a translation dictionary to be used may be determined from the translation dictionaries corresponding to the plurality of languages based on the translation language specified by the translation language specifying means.

Further, as a preferred aspect, for example, as in claim 7, in the mobile terminal according to claim 6, the mobile terminal according to claim 6 includes position information acquisition means for acquiring position information, and the translated language specifying means is configured to acquire the position information acquisition means. The translation language to be used may be specified based on the position information acquired by the above.

Further, as a preferred aspect, for example, as in claim 8, in the mobile terminal according to claim 6, a translation dictionary instruction means for instructing which translation dictionary to use among the translation dictionaries corresponding to the plurality of languages And the translation means uses the translation dictionary in accordance with the instruction from the translation dictionary instruction means when the instruction is given by the translation dictionary instruction means to convert the image information recognized by the recognition means to the image information recognized by the recognition means. The included identification information may be translated.

Further, as a preferred aspect, for example, as in claim 9, in the mobile terminal according to any of claims 6 to 8, reference to related information related to the identification means recognized by the communication means and the recognition means. And when the reference of the related information is instructed by the related information reference instruction unit, the related information is transmitted via the communication unit based on the identification information recognized by the recognition unit. And related information acquisition means for acquiring the information.

In order to achieve the above object, an information processing method according to claim 10 includes an imaging step for capturing image information and a recognition dictionary usage history table in which usage histories of recognition dictionaries corresponding to a plurality of languages are described . A recognition step of recognizing identification information included in image information captured by the imaging means using a recognition dictionary according to the order obtained from the usage history (in ascending / descending order), and the recognition dictionary usage history table An update step of updating a use history of the recognition dictionary corresponding to the plurality of languages.

To achieve the above object, an information processing program according to an eleventh aspect of the present invention is a recognition dictionary usage history in which a computer has an imaging function for capturing image information and a recognition dictionary usage history corresponding to a plurality of languages. A recognition function for recognizing identification information included in image information captured by the imaging unit using a recognition dictionary according to an order (ascending / descending order) obtained from the use history of the table, the recognition dictionary use history table An update function for updating a use history of the recognition dictionary corresponding to the plurality of languages is executed.

According to this invention, even when the multiple language support, it is possible to easily select an appropriate recognition dictionary from a plurality of recognition dictionaries in accordance with the language of the read character string, read The advantage is that the character string image can be converted into correct character information.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

A. First embodiment A-1. Configuration of First Embodiment FIG. 1 is a schematic diagram showing an appearance of a mobile phone according to the first embodiment. FIG. 2 is a block diagram showing the configuration of the mobile phone according to the first embodiment of the present invention. In the first embodiment, a case will be described in which an image recognition function (OCR function) mounted on a mobile phone is used to recognize and read an English word written on a paper surface and output the recognition result. .

  As shown in FIG. 1, a mobile phone 100 includes a main body portion provided with an input portion 101 and the like, and a lid portion provided with a display portion 107 and the like. As shown in FIG. 2, the mobile phone 100 includes an input unit 101, a CPU 102, an imaging unit 103, a storage unit 104, an image recognition unit 105, a communication unit 106, and a display unit 107.

  The input unit 101 is an input unit for inputting a telephone number and other information such as a keyboard, and is used when a user gives an input to the mobile phone, such as when turning on / off the power of the mobile phone, or imaging a subject. To do.

  The CPU 102 operates based on a program stored in the storage unit 104, and controls each unit according to an input from the input unit 101, for example. The imaging unit 103 is configured by, for example, a camera, and captures a human face, a scene, characters, and the like as a subject, converts the image into image information that can be handled by the CPU 102, and the converted image information is necessary. In response, the data is output to the display unit 107 or the like. The user selects an image to be captured while monitoring the image information output to the display unit 107, and issues an imaging instruction by pressing an operation key (hereinafter referred to as a shutter key) assigned as a shutter key, for example. . When the shutter key is pressed, the captured image information is stored in the storage unit 104.

  The storage unit 104 includes, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), and the like, and stores data and software handled by the mobile phone 100 in addition to the image information. In addition, the storage unit 104 includes a recognition dictionary 108 and a language-recognition dictionary correspondence table 109. The recognition dictionary 108 and the language-recognition dictionary correspondence table 109 will be described later.

  The image recognition unit 105 recognizes identification information such as characters and symbols included in the image information. Here, the identification information is information represented by characters, symbols, etc., and is represented by characters, symbols, etc., such as homepage addresses, e-mail addresses, addresses, telephone numbers, map information, or English words. Any information other than the above example may be used as long as the information can identify the thing. In other words, the image recognition unit 105 has an OCR function, and a specific configuration for realizing the OCR function is described in Patent Document 1, for example.

  Here, recognition refers to extracting identification information included in image information captured by the imaging unit 103, dividing the identification information into predetermined areas, converting the divided areas into predetermined parameter values, It means determining what kind of information the divided area is based on the parameter value.

  More specifically, for example, considering the case of “recognizing” the character “abc” in the image information, first, the position of “abc” in the image information is specified (character Column extraction), and then divided into “a”, “b”, and “c”, and “a” is a predetermined parameter value (for example, the structure of the line segment as viewed from the vertical, horizontal, and diagonal lines) The white portion is converted to a parameterized value with “0” and the black portion “1”. Then, the character (character code) associated with the parameter value most similar to the converted parameter value is selected from the recognition dictionary 108.

  The recognition dictionary 108 is a table in which parameter values and characters such as alphabets (character codes) corresponding to the parameter values are described, and are stored in the storage unit 104. By the way, the mobile phone 100 of the present invention includes a recognition dictionary corresponding to each language in order to support a plurality of languages such as English, Korean, and Japanese. And when recognizing English, it recognizes using the recognition dictionary (English recognition dictionary) corresponding to the alphabet, and when recognizing Korean, the recognition dictionary (Korean recognition dictionary) corresponding to the Hangul character. Recognize using

  If the number of characters is large, such as Japanese or Korean characters, the file size increases if all characters are stored in one recognition dictionary. Therefore, it may be divided and stored in a plurality of recognition dictionaries. For example, in the case of Japanese, only the first level characters defined by JIS may be stored.

  By the way, for example, if the mobile phone 100 is set to recognize using an English recognition dictionary, Korean cannot be recognized. Therefore, the user needs to set the mobile phone 100 to be recognized using the Korean language recognition dictionary and recognize it again.

  In this way, it is necessary to change the recognition dictionary every time the language to be recognized changes. For example, a user who frequently goes back and forth between Korea and Japan sets the Korean language recognition dictionary when going to Korea. If you go to, you need to set it in the Japanese recognition dictionary, which is very time consuming. Therefore, in the first embodiment, the location information of the mobile phone 100 is acquired, the language used from the location information is specified, and the image is captured by the imaging unit 103 using the recognition dictionary corresponding to the language. It is automatically set to recognize the identification information included in the image information. A method for acquiring the location information of the mobile phone 100 will be described later.

  Therefore, in the first embodiment, the storage unit 104 includes the language-recognition dictionary correspondence table 109 described above in order to automatically set a recognition dictionary to be used for recognition for the specified language. As shown in FIG. 3, the language-recognition dictionary correspondence table 109 is a table showing the correspondence between the language 301 and the file name 302 of the recognition dictionary for the language. That is, when a language is specified, the recognition dictionary to be used for recognition can be uniquely determined by referring to the language-recognition dictionary correspondence table 109.

  Further, it is necessary to specify identification information to be recognized before recognition. As a means for specifying, for example, if a “+” mark displayed at the center of the display unit 107 is brought on the identification information. The part from the space information to the space information in the vicinity from the position of the “+” mark may be automatically specified as a single word.

  In addition, the user may be able to directly specify the recognition target portion with a cursor or the like using the input unit 101, or may be able to select a plurality of recognition targets at the same time. Furthermore, in the case of a moving image, the moving image may be set so that it can be frame-fed as a still image, and identification information to be recognized can be selected on the frame-advancing screen.

  Furthermore, in order to determine the recognition target, if the “provisional determination” for determining the target for the time being and “mainly determined” when the target temporarily determined is not wrong, the recognition target is determined at the temporary determination stage. When there is an error in the identification, it is possible to easily change the target character and the like, so that usability can be improved.

  Next, the display unit 107 includes, for example, an LCD (Liquid Crystal Display), an organic EL (Electroluminescence), and the like, and displays an image captured by the imaging unit 103 and identification information recognized by the image recognition unit 105. In addition, the display unit 107 displays, for example, power status, radio wave intensity, remaining battery level, server connection status or operating status such as unread mail, input telephone number, mail destination, mail transmission document, video, still image, incoming call, etc. Display the received data such as the telephone number of the calling party, the incoming mail document, the connected internet screen, and the screen necessary for using the functions of the mobile phone.

  The communication unit 106 exchanges data with other information processing apparatuses. It is also used when exchanging information with a base station, a location server, and a GPS (Global Positioning System) satellite to acquire the position coordinates of a mobile phone in latitude and longitude. In addition, the mobile phone 100 also performs communication processing for accessing the Internet, other information processing apparatuses, and the like. Also, the communication unit 106 is not limited to the case where only one is used as shown in FIG. Also good.

  The language setting unit 110 uses the position coordinates of the mobile phone acquired by the communication unit 106 to identify the language used in the place (country or region), and in the software program stored in the storage unit 104 Save to a variable that represents the existing language. The language setting unit 110 holds a “position-language correspondence table” that describes the correspondence between the position coordinates and the language used at the location of the position coordinates.

  As shown in FIG. 4A, the position-language correspondence table 200 includes a language 201, position coordinates (east longitude) 202, position coordinates (north latitude) 203, and the like. For example, if the acquired position coordinates are (East longitude 255 ° 20′10 ″, North latitude 41 ° 39′10 ″), the position coordinates are within the range of the position coordinates (east longitude) 205 and the position coordinates (north latitude) 206. Therefore, the language used in this place is English 204. In this method, it is necessary to represent all areas on the earth with fine rectangular areas, which increases the data size. Therefore, by expressing the area as a polygon, all the areas on the earth can be expressed as long as there are only the position coordinates of the vertexes of the polygon, so that the data size can be reduced. For example, as shown in FIG. 4B, the area surrounded by vertices A, B, E, and D is German, and the area surrounded by vertices B, C, and D is French.

  In addition to the above method, the language can be specified by acquiring the location of the mobile phone based on an LAI (Location Area Identity) signal transmitted from the mobile phone base station, and based on the location of the mobile phone. Therefore, there is a method for specifying the language used there, which is disclosed in Japanese Patent Application Laid-Open No. 2002-247646.

  In addition, the CPU 102 uses the mode determination flag to determine whether the imaging mode is a normal imaging mode that captures a normal still image or moving image, or a recognition mode that recognizes identification information using the image recognition unit 105. Determine. Here, the mode determination flag is a variable that exists in the software program stored in the storage unit 104, for example, and is set to a different value between the recognition mode and the normal imaging mode. Based on this, for example, the recognition mode and the normal imaging mode are switched by an operation using the input unit 101.

  Hereinafter, in the first embodiment, a case where there are two types of “recognition mode” and “normal imaging mode” is considered, but the present invention is not limited to this, and there may be other modes.

A-2. Operation of the First Embodiment Next, the processing procedure of the mobile phone 100 in the first embodiment will be described with reference to the flowchart shown in FIG.

  First, when the mobile phone 100 waits for a key input (step S501) and the CPU 102 detects a key input for starting the camera function (step S502), initialization of variables related to the camera function stored in the storage unit 104, etc. The camera activation process is performed (step S503). Thereafter, the CPU 102 determines whether the imaging mode is “recognition mode” or “normal imaging mode”. In the “recognition mode”, when the shutter key or the like is pressed after starting the imaging unit 103 in step S503, the image data of the imaging target is acquired and the acquired image data is stored. The data is temporarily stored in the unit 104 (step S504).

  Next, the image recognition unit 105 reads the image data (step S505). Thereafter, the language setting unit 110 specifies the language used in the place (country or region) using the position coordinates of the mobile phone acquired by the communication unit 106, and the language stored in the storage unit 104 is determined. Language type information is set in the variable to be represented (step S506). Next, the CPU 102 reads the language type information from the variable, refers to the language-recognition dictionary correspondence table 109, identifies the recognition dictionary file name, and passes the recognition dictionary file name to the image recognition unit 105 (step S507).

  Next, in order to select a word to be recognized from words included in the image data, a word closest to the “+” mark displayed at the center of the display unit 107 is set as a recognition target word ( Step S508). Then, the CPU 102 displays a frame around the word specified as the recognition target word, and clearly indicates to the user what the word currently specified as the recognition target is (step S509). Thereafter, the image recognition unit 105 performs character recognition processing.

  In the character recognition process, first, where the character line is in the image data is extracted by the character line extraction process. When the range of the character line is determined, if the interval between the set of black pixels in the character line is greater than or equal to a predetermined value, the set is a character string delimited by a space. That is, it is recognized as a word. The coordinates of the range of the character string extracted in this way are stored in the storage unit 104.

  Next, the image recognition unit 105 performs character recognition processing for the designated recognition target portion (inside the frame) using the recognition dictionary with the recognition dictionary file name acquired in step S107 (step S510), and displays the recognition result on the display unit. It is displayed on 107 (step S511).

  Thus, since the recognition dictionary is selected according to the language specified by the language setting unit 110, it is not necessary for the user to set the recognition dictionary again, and an appropriate one of the plurality of recognition dictionaries is selected according to the language of the read character string. A simple recognition dictionary can be easily selected, and an image of a read character string can be converted into correct character information, improving usability.

  In the first embodiment described above, for example, when an English word is recognized in Korea, it is automatically recognized using a Korean recognition dictionary. However, if recognition is not possible using the Korean recognition dictionary, Then, recognition may be performed using a recognition dictionary of another language such as an English recognition dictionary. In this way, since the user can recognize characters other than Korean in Korea without changing the setting of the recognition dictionary, the usability can be further improved.

B. Second Embodiment Next, a second embodiment of the present invention will be described. In the second embodiment, as shown in FIG. 6, the number 303 of use of the recognition dictionary corresponding to each language of the recognition dictionary 108 and the use time 304 are stored in the language-recognition dictionary correspondence table 109 as shown in FIG. For example, the CPU 102 can refer to the number of times 303 and instruct the image recognition unit 105 to use the recognition dictionary in the order of the most frequently used times. Similarly, the recognition dictionaries corresponding to the respective languages of the recognition dictionary 108 may be used in the order of use time 304. This makes it possible to select a recognition dictionary that is most suitable for the user, improving usability.

C. Third Embodiment Next, a third embodiment of the present invention will be described. In the second embodiment described above, the use order of the recognition dictionary corresponding to each language of the recognition dictionary 108 is set according to the number of times 303 and the use time 304. In this case, the CPU 102 uses the language-recognition dictionary correspondence table 109. Depending on the recognition character used, the recognition time may be longer depending on the use order of the recognition dictionary corresponding to each language of the recognition dictionary 108 determined from the number of times 303 and the use time 304. For example, the order of use of the recognition dictionary corresponding to each language of the recognition dictionary 108 is 1. English, 2. Korean, 3. Arabic, 4. In order to recognize Japanese when it has become Japanese, after using the English recognition dictionary, the Korean recognition dictionary, and the Arabic recognition dictionary, recognition is attempted using the Japanese recognition dictionary. Is done.

  In order to omit such extra processing, it is possible to previously set which recognition dictionary is used for each key of the input unit 101. That is, when there is a key input from the input unit 101, the recognition dictionary to be used may be determined by giving priority to the key input over the use order set by the number of times 303 and the use time 304. For example, in the input unit 101, “1” key is set to English, “2” key is set to Korean, “3” key is set to Japanese. Specifically, as shown in FIG. 6, a key assignment 305 field is provided in the language-recognition dictionary correspondence table 109, and an identifier such as a number indicating the type of key is described in the field.

  Here, FIG. 7 is a flowchart for explaining processing when recognizing an image of a read character string using the language-recognition dictionary correspondence table 109 provided with a key assignment 305 field.

  First, processing similar to that in steps S501 to S503 shown in FIG. 5 is performed, and the camera is activated. In this state, when the “1” key is pressed by the user, the CPU 102 detects that the “1” key is pressed (step S601), and the CPU 102 refers to the language-recognition dictionary correspondence table 109 (step S601). In step S602), an identifier representing the “1” key is searched from the key assignment 305 column (step S603). When an identifier representing the “1” key is found, the recognition dictionary file name “OCR_eng.dat” associated with the identifier is stored in the storage unit 104 (step S604). Then, after performing the same processing as steps S504 to S505 in FIG. 5, the CPU 102 passes the recognition dictionary file name saved in the storage unit 104 to the image recognition unit 105 in step S605. Thereafter, processing similar to that in steps S508 to S511 in FIG. 5 is performed, and the recognition result is displayed.

  Thus, by assigning keys, the user can specify a recognition dictionary to be used by the image recognition unit 105 among recognition dictionaries corresponding to each language of the recognition dictionary 108. Therefore, since the recognition dictionary corresponding to a different language is not used, recognition time is shortened and usability improves.

  Note that in the third embodiment described above, in addition to key assignment, a language spoken by a user may be detected using voice recognition technology to specify a language.

D. Fourth Embodiment D-1. Configuration of Fourth Embodiment Next, a fourth embodiment of the present invention will be described. Here, FIG. 8 is a block diagram showing a configuration of a mobile phone according to the fourth embodiment of the present invention. It should be noted that parts corresponding to those in FIG. So far, it has been described that characters are recognized and the recognition result is displayed. In the fourth embodiment, as shown in FIG. 8, each of a plurality of languages is stored in the storage unit 104 of the mobile phone 100. By providing the translation dictionary 111 corresponding to, foreign languages such as English words recognized and read are translated into Japanese and displayed.

  The translation dictionary 111 here includes, for example, identification information such as words of a foreign language (English, French, etc.) and a Japanese translation of the identification information. Further, it may include a URL of a home page in which various details such as various Japanese translations of the identification information, usage / examples, etc. are written. Furthermore, data such as pictures and sounds may be used as long as it is understood that the information is identification information.

  In the second embodiment, the “recognition dictionary-translation dictionary correspondence table” indicating the correspondence between the recognition dictionary used by the image recognition unit 105 and the translation dictionary used to translate the recognized word is stored in the storage unit 104. Save to.

  FIG. 9 shows the contents of the recognition dictionary-translation dictionary correspondence table 400. The recognition dictionary-translation dictionary correspondence table 400 includes columns of a recognition dictionary file name 302 and a translation dictionary file name 306. For example, a recognition dictionary file name “OCR_eng.dat” and a translation dictionary file name “TRANS_eng_jap. “dic” indicates a correspondence relationship. Here, “OCR_eng.dat” is a recognition dictionary corresponding to English letters (alphabet), and “TRANS_eng_jap.dic” is a Japanese dictionary in which English words and their Japanese translations are described. The image recognition unit 105 can determine the translation dictionary to be used for translation by referring to the correspondence table after the recognition, and can save the user's trouble.

D-2. Operation of Fourth Embodiment Next, the processing procedure of the mobile phone in the fourth embodiment will be described with reference to the flowchart shown in FIG. First, processing similar to that in steps S501 to S509 in FIG. 5 is performed, and a recognition target is determined from characters included in the captured image. Thereafter, the image recognition unit 105 performs character recognition processing (step S701), and determines whether the recognition is successful (step S702).

  As a determination method, for example, when the difference between the predetermined parameter value for the character to be recognized and the parameter value stored in the recognition dictionary 108 is within a predetermined range. There is a method such as recognition success for the character. If the recognition is successful for all characters in the character string selected as the recognition target, the recognition is successful in step S702. Even if not all characters are recognized successfully, recognition may be successful in step S702 if, for example, 80% or more of the entire character string is recognized successfully.

  If the recognition is not successful in step S702, the CPU 102 searches for other recognition dictionaries that have not been used yet (step S711). If found, the recognition dictionary is used again. Character recognition processing is performed (step S701). On the other hand, if there is no recognition dictionary that is not used, a display such as “Recognition failed” is displayed on the display unit 107 (step S712).

  On the other hand, when the recognition is successful in step S702, the CPU 102 stores the recognition result in the storage unit 104 (step S703). Further, the CPU 102 stores the used recognition dictionary file name in the storage unit 104 (step S704). Then, the CPU 102 refers to the column of the recognition dictionary file name 302 in the recognition dictionary-translation dictionary correspondence table 400, searches for a file name that matches the recognition dictionary file name stored in the storage unit 104, and finds that the matching file name is If found, the translation dictionary file name associated with the recognition dictionary file name is acquired (step S705).

  Next, the CPU 102 reads the recognition result recognized by the image recognition unit 105 from the storage unit 104, and the CPU 102 accesses the file having the translation dictionary file name acquired in step S705. Then, a word that matches the recognition result is searched from word data included in the translation dictionary (step S706).

  As a method of searching for a word, first, a search is made for a word that matches exactly the character string, and when there is no match, a word that is different by one character but matches the other characters is searched. preferable. By adopting this method, even when the image recognition unit 105 mistakenly recognizes a character on the paper, it is possible to find the word closest to the character string, and it is time-consuming to repeat the character recognition by taking an image many times. Can be omitted. If there is no word that differs only by one character, you can search by increasing the number of different characters, such as a word that differs only by two characters, a word that differs only by three characters, and in this case, even if the recognition rate is low Find words.

  If a matching word is found in the translation dictionary by the search, the CPU 102 reads the Japanese translation corresponding to the word from the translation dictionary of the corresponding language of the translation dictionary 111 (step S708), and displays the display unit. A Japanese translation is displayed at 107 (step S709). On the other hand, when a matching word is not found in the translation dictionary, a display such as “No matching word found” is displayed on the display unit 107 (step S712).

  In this way, the mobile phone in the fourth embodiment can continuously display Japanese translations for a plurality of languages without the user having to reset the translation dictionary one by one.

  The translation dictionary file name 331 field in the recognition dictionary-translation dictionary correspondence table 400 may be described by adding a field to the language-recognition dictionary correspondence table 109. By doing so, the number of tables referred to by the CPU 102 is reduced, and the capacity of the storage unit 104 can be reduced and the software structure can be simplified.

  The recognition dictionary-translation dictionary correspondence table 400 has values entered in the respective fields of the translation dictionary file name 331 and the recognition dictionary file name 302 when a translation dictionary is newly stored in the storage unit 104 of the mobile phone 100. It is preferred that The value may be input from the input unit 101 by the user. At that time, it is preferable to display a message prompting the user to input on the display unit 107. For example, as shown in FIG. 11A, a recognition dictionary file name list 802 stored in the storage unit 104 is displayed. The user can select a recognition dictionary by pressing the number key corresponding to the file name. For example, when the user presses the “1” key, a message notifying the user that “TRANS_eng_jap.dic” and “OCR_eng.dat” are associated is displayed as shown in FIG.

  Also, the format of the translation dictionary is determined, and a recognition dictionary identifier representing a recognition dictionary corresponding to a predetermined location (for example, the beginning of a file) is stored. Then, when a new translation dictionary is stored in the storage unit 104, the CPU 102 refers to the recognition dictionary identifier stored in the translation dictionary and inputs a value to the recognition dictionary-translation dictionary correspondence table 400. Also good.

E. Fifth Embodiment Next, a fifth embodiment of the present invention will be described. In the fourth embodiment described above, the case where one translation dictionary is determined for one recognition dictionary has been considered. However, in the fifth embodiment, each of a plurality of languages is defined for each recognition language. A case will be described in which a plurality of translation dictionaries corresponding to is provided and the recognized character string is translated using any one of the plurality of translation dictionaries. Which translation dictionary is used, that is, in which language is translated, the language used in the place is specified based on the position information, and the recognized character string is translated using the translation dictionary corresponding to the language. It has become.

  For example, when English is recognized, there are an English-Japanese dictionary that translates English to Japanese, an English-Korean dictionary that translates English to Korean, and an English-German dictionary that translates English to German. Therefore, the user needs to select which translation dictionary is used for translation when translating. Also, if you set a translation dictionary to use in advance, you can save time and effort to select it every time you recognize it. However, as mentioned above, for example, there are users who frequently travel between Korea and Japan, and frequently use English-Korean dictionaries. When using an English-Japanese dictionary, it is necessary to frequently set the translation dictionary to be used, which is troublesome.

  Therefore, in the fifth embodiment, the location information of the mobile phone 100 is acquired, the language used at the location is specified from the location information, and the recognized character string is translated into the specified language. For this purpose, as shown in FIG. 12, a correspondence table 900 in which a translation dictionary file name 901, a translated language 902, and a translated language 903 are associated is held in the storage unit 104. Then, the CPU 102 refers to the correspondence table 900 based on the language set by the language setting unit 110 and sets a translation dictionary to be used. Here, the language to be translated 902 is an identifier representing the language of the word to be translated, for example, “English” 905. The translation language 903 is an identifier representing a language used for translation, and is, for example, “Japanese” 906. The translation dictionary file name 901 is a translation dictionary file name for translation from the translated language 902 to the translated language 903. For example, “TRANS_eng_jap.dic” 904 corresponds to the word “English” 905 and the word. This is a dictionary in which the meaning of “Japanese” 906 is described.

  In the fifth embodiment, the image recognition unit 105 recognizes the image of the read character string using the recognition dictionary corresponding to the language specified by the user, and then uses the recognition dictionary used and the language-recognition dictionary correspondence table 109. Determine the language to be translated. Specifically, the language of the word to be recognized is substituted into the variable Lang_in on the program representing the language to be translated. For example, the recognition dictionary used is OCR_eng. In the case of dat, the language is “English” from the language-recognition dictionary correspondence table 109, and English is substituted for the variable Lang_in. Next, the language set by the language setting unit 110 according to the position information is substituted into a variable Lang_out on the program representing the translation language. The CPU 102 reads the variable Lang_in and the variable Lang_out, and searches for a translation dictionary file name that is equal to the translated language 902 and the translated language 903 in the correspondence table 900. If it is found as a result of the search, the translation dictionary file name file is accessed to search for a word translation. By doing so, the user can save time and effort for setting, and usability is improved.

  In the correspondence table 900, when a translation dictionary is newly stored in the storage unit 104 of the mobile phone 100, values are input in the respective fields of the translation dictionary file name 901, the recognized character language 902, and the translation language 903. It is preferable. The value may be input from the input unit 101 by the user. At this time, it is preferable to display a message prompting the user to input on the display unit 107. In addition, the translation dictionary format is determined, and the translated language and the translated language are stored in a predetermined location of the translation dictionary, for example, at the top of the file. A value may be input to 900.

  FIG. 13A is a screen display example when an English word is recognized and its translation is displayed in a place where Japanese is spoken in the mobile phone 100 of the fifth embodiment. An English word “thank” surrounded by a frame 1001 indicates that it is a recognition target word, and the translation result is displayed on the result display unit 1002. Since it is Japanese-speaking, “Thank you” 1003 is displayed. FIG. 13B is a screen display example when the translation result is displayed in the same manner as in FIG. 13A in a place where the mobile phone 100 is speaking Chinese. The translation result is displayed as “Xie Xie” in Chinese.

  In some regions, a plurality of languages are used. For example, English and French are used in Canada, and English and Hindu are used in India. In that case, if the user selects which language to translate, the usability is further improved. In this case, in the position-language correspondence table 200 shown in FIG. 3, it is assumed that at least one or more languages used in the place are set for the position information. That is, a plurality of languages are set in the position information indicating a place where a plurality of languages are used.

  FIG. 14 shows an example of the screen display. FIG. 14A shows that the word “now” has become a recognition target word. When the user presses the “select” key in this state, the screen transitions to FIG. FIG. 14B is a screen that allows the user to select which language to translate. In this state, for example, when the “1” key is pressed, the setting is made so as to translate into Japanese, and a transition is made to FIG. FIG. 14C is a screen showing the result of translating the word “now” to be recognized into Japanese. The translation result display unit 1104 displays the translation of the recognition target word “now” in Japanese.

  In addition, after displaying the translation result of the recognized word, the user may connect to a site such as a dictionary application and browse the detailed meaning of the recognized word and various usages. Specifically, in a state where the translation result is displayed on the display unit 107, if the user inputs to the input unit 101, the user connects to the site and displays the contents of the site on the display unit 107. In this case, the position information of the mobile phone 100 may be used when determining the URL of the site to be connected.

  Specifically, a site URL (not shown) column is added to the correspondence table 900, and URLs (parts) corresponding to the respective translation dictionary files are described. For example, the URL (part) of the site corresponding to the translation dictionary file TRANS_eng_jpa.dic is “http://xxx.???.com/english-japanese/”. Then, the CPU 102 creates a URL to be connected using the URL of the site (a part thereof) and the word recognized by the image recognition unit 105. The communication unit 106 connects to the URL created by the CPU 102 and displays the content of the URL on the display unit 107. For example, when the word “mobile” is recognized, the URL to be connected is “http://xxx.???.com/english-japanese/mobile.html”.

  In the above-described embodiment, the recognition dictionary and the translation dictionary are described as one language per file, but a plurality of languages may be combined into one file. For example, an English recognition dictionary, a Japanese recognition dictionary, and a Korean recognition dictionary are collectively stored as one file from the top. Then, instead of the recognition dictionary, data indicating in which part of the file the recognition dictionary is stored is described in the correspondence table. For example, when the Japanese recognition dictionary is stored from the 1500th byte from the beginning of the file, “1500” is described in the correspondence table together with the file name. If you want to use the Japanese language recognition dictionary, you can access it from the 1500th byte of the file. As a result, it is possible to handle a file in which a plurality of recognition dictionaries and translation dictionaries are collected, and usability is improved.

Note that the various functions described above may be realized by software, and the user can realize the various functions by receiving the software from a recording medium such as a CD-ROM or a server, for example. This makes it easy to install only necessary functions, and to add, delete, or update various functions according to preference.
Furthermore, it goes without saying that a new embodiment can be configured by combining the above-described examples.
Further, the present invention is not limited to the above-described embodiments, and there are various embodiments using the principles and characteristics disclosed herein.

It is a schematic diagram which shows the external appearance of the mobile telephone 100 by this invention. It is a block diagram which shows the structure of the mobile telephone which concerns on 1st Embodiment of this invention. It is a conceptual diagram which shows the content of the language-recognition dictionary correspondence table | surface 109 by this 1st Embodiment. It is a conceptual diagram which shows the content of the position-language correspondence table by this 1st Embodiment. It is a flowchart for demonstrating the process of the mobile telephone which concerns on this 1st Embodiment. It is a conceptual diagram which shows the content of the language-recognition dictionary correspondence table 109 by 2nd, 3rd embodiment of this invention. It is a flowchart for demonstrating the process of the mobile telephone which concerns on this 3rd Embodiment. It is a block diagram which shows the structure of the mobile telephone which concerns on 4th Embodiment of this invention. It is a conceptual diagram which shows the content of the recognition dictionary-translation dictionary correspondence table | surface 400 by this 4th Embodiment. It is a flowchart for demonstrating the process of the mobile telephone which concerns on this 4th Embodiment. It is a schematic diagram which shows the example of a screen display of the mobile telephone which concerns on this 4th Embodiment. It is a conceptual diagram which shows the content of the correspondence table 900 which concerns on 5th Embodiment of this invention. It is a schematic diagram which shows the example of a screen display of the mobile telephone which concerns on this 5th Embodiment. It is a schematic diagram which shows the other example of a screen display of the mobile telephone which concerns on this 5th Embodiment.

Explanation of symbols

100 mobile phone 101 input unit (instruction means)
102 CPU (recognition dictionary determination means, translation dictionary determination means, translation means)
103 Imaging unit (imaging means)
104 storage unit 105 image recognition unit (recognition means)
106 Communication unit (location information acquisition means)
107 display unit 108 recognition dictionary 109 language-recognition dictionary correspondence table (recognition dictionary use order table)
110 Language setting part (language identification means)
111 translation dictionary 200 position-language correspondence table 400 recognition dictionary-translation dictionary correspondence table

Claims (11)

Imaging means for imaging image information;
Use of a recognition dictionary that is used when recognizing identification information included in image information captured by the imaging unit, and that describes a recognition dictionary corresponding to a plurality of languages and a use history of the recognition dictionary corresponding to the plurality of languages Storage means for storing a history table;
Recognizing means for recognizing identification information included in image information picked up by the image pickup means using a recognition dictionary according to an order (ascending / descending order) obtained from use histories described in the recognition dictionary use history table ; A portable terminal comprising: The recognition dictionary usage history is the number of times each recognition dictionary is used ,
The mobile terminal according to claim 1, wherein the recognition unit uses a recognition dictionary according to the order in which the recognition dictionary is used . The use history of the recognition dictionary is the latest use time of each recognition dictionary ,
The mobile terminal according to claim 1, wherein the recognition unit uses a recognition dictionary that follows the youngest use time of the recognition dictionary . A recognition dictionary instructing unit for instructing which recognition dictionary to use among the recognition dictionaries corresponding to the plurality of languages;
When there is an instruction from the recognition dictionary instruction means, the recognition means uses the recognition dictionary according to the instruction from the recognition dictionary instruction means to identify identification information included in the image information captured by the imaging means. The mobile terminal according to claim 1, wherein the mobile terminal is recognized. Related information related to the identification information is described, a translation dictionary corresponding to a plurality of languages,
A translation dictionary determining means for determining a translation dictionary to be used from translation dictionaries corresponding to the plurality of languages based on the recognition dictionary used by the recognition means;
The mobile unit according to claim 1, further comprising: a translation unit that translates identification information included in the image information recognized by the recognition unit using the translation dictionary determined by the translation dictionary determination unit. Terminal. A translation language specifying means for specifying the translation language;
The translation dictionary determining means determines a translation dictionary to be used from among translation dictionaries corresponding to the plurality of languages based on the translation language specified by the translation language specifying means instead of the recognition dictionary. The mobile terminal according to claim 5. Comprising position information acquisition means for acquiring position information;
The portable terminal according to claim 6, wherein the translation language specifying unit specifies a translation language to be used based on the position information acquired by the position information acquisition unit. A translation dictionary instruction means for instructing which translation dictionary to use among the translation dictionaries corresponding to the plurality of languages;
When there is an instruction from the translation dictionary instruction means, the translation means uses the translation dictionary according to the instruction from the translation dictionary instruction means to identify the identification information included in the image information recognized by the recognition means. The mobile terminal according to claim 6, wherein the mobile terminal is translated. Communication means;
A related information reference instruction unit for instructing reference of related information related to the identification information recognized by the recognition unit;
A related information acquisition unit configured to acquire the related information via the communication unit based on the identification information recognized by the recognition unit when the reference of the related information is instructed by the related information reference instruction unit; The mobile terminal according to claim 6, further comprising: An imaging step for imaging image information;
Image information picked up by the image pickup means using a recognition dictionary according to the order (in ascending / descending order) obtained from the use history of the recognition dictionary use history table in which use histories of recognition dictionaries corresponding to a plurality of languages are described A recognition step for recognizing the identification information contained in
An information processing method comprising: an update step of updating a use history of a recognition dictionary corresponding to the plurality of languages described in the recognition dictionary use history table. On the computer,
An imaging function for imaging image information;
Image information picked up by the image pickup means using a recognition dictionary according to the order (in ascending / descending order) obtained from the use history of the recognition dictionary use history table in which use histories of recognition dictionaries corresponding to a plurality of languages are described Recognition function for recognizing identification information contained in
An information processing program for executing an update function for updating a use history of a recognition dictionary corresponding to the plurality of languages described in the recognition dictionary use history table.

Images