Image reading device, and image forming apparatus

Abstract

To provide an image reading device and an image forming apparatus that, when characters included in a document are translated, can bring translated characters within a page frame of the document regardless of the language into which the characters are translated.SOLUTION: An image reading device according to an aspect of the present invention comprises a reading unit, an extraction unit, a translation unit, and a generation unit. The reading unit reads a document to generate document image data. The extraction unit performs character recognition processing on the document image data to extract character strings for every preset extraction area. The translation unit translates the extracted character strings into the translation language designated in advance to generate translated character strings. The generation unit substitutes the character strings with the translated character strings to generate translated document data. When generating the translated document data, the generation unit adjusts the font size of the translated character strings so as to bring the translated character strings within the extraction area.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present invention relates to an image reading device and an image forming device. [Background technology]

[0002] 2. Description of the Related Art In recent years, image reading devices that translate and output scanned document images have become known.

[0003] Patent Document 1 discloses an image reading device having such a translation function, which outputs a read image and a conversion result such as a translation so that the read image and the conversion result can be compared. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Re-tabled publication No. 2015-186312 Summary of the Invention [Problem to be solved by the invention]

[0005] Incidentally, when comparing the number of characters in English and Japanese, for example, it is known that the number of characters required to express the same meaning differs greatly between English, which is expressed only with the alphabet, which is a phonetic character, and Japanese, which is expressed mainly with kanji, which are motto characters, and hiragana, which are phonetic characters.

[0006] For this reason, there was concern that if the Japanese text contained in the manuscript was translated into English, the area containing the translated text would become too large and would not fit within the page frame of the manuscript.

[0007] Therefore, an object of the present invention is to provide an image reading device and an image forming device that, when translating characters contained in a document, can fit the translated characters into the page frame of the document regardless of the type of language. [Means for solving the problem]

[0008] An image reading device according to one aspect of the present invention includes a reading unit, an extraction unit, a translation unit, and a generation unit. The reading unit reads a document and generates document image data. The extraction unit performs character recognition processing on the document image data and extracts character strings for each predetermined extraction area. The translation unit translates the extracted character strings into a predetermined translation language to generate translated character strings. The generation unit replaces the character strings with the translated character strings to generate translation manuscript data. Furthermore, when generating the translation manuscript data, the generation unit adjusts the font size of the translated character strings so that the translated character strings fit within the extraction areas.

[0009] An image forming apparatus according to one aspect of the present invention includes the image reading apparatus described above, and an image forming section that forms an image indicated by the translation manuscript data on a sheet of paper. [Effects of the Invention]

[0010] According to the image reading device and image forming device of the present invention, when characters included in a document are translated, the translated characters can be fitted into the page frame of the document regardless of the type of language. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a schematic perspective view of an image forming apparatus according to an embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram of the image forming apparatus shown in FIG. [Figure 3] FIG. 3 is a schematic perspective view of the image reading device shown in FIG. 2. [Figure 4] FIG. 2 is a flow diagram of an entire job using the image forming apparatus of the present invention. [Figure 5] 5 is a flowchart showing the first half of the translation manuscript data generation process shown in FIG. 4. [Figure 6] FIG. 6 is a flowchart showing details of the character region extraction process shown in FIG. 5. [Figure 7] 5 is a flowchart showing the latter half of the process of generating translation manuscript data shown in FIG. 4. [Figure 8]1A and 1B are diagrams showing original images before and after translation according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0012] An embodiment of an image forming apparatus 200 according to the present invention will now be described with reference to the drawings. In the drawings, the same or corresponding parts are designated by the same reference characters and description thereof will not be repeated.

[0013] (1) Configuration of Image Forming Apparatus 200 (1-1) Overall structure The image forming apparatus 200 is, for example, a multifunction peripheral having a printer function, a scanner function, and a copy function. The image forming apparatus 200 may also have a facsimile function. In this embodiment, the image forming apparatus 200 forms images by electrophotography.

[0014] Fig. 1 is a schematic perspective view of an image forming apparatus 200 according to one embodiment. Fig. 2 is a block diagram of the image forming apparatus 200 shown in Fig. 1. As shown in Figs. 1 and 2, in this embodiment, the image forming apparatus 200 includes an image reading device 100 and an image forming unit 60.

[0015] In the image forming apparatus 200 according to the present invention, a character string included in the document image data generated by the image reading apparatus 100 reading a document is extracted by the process described below, and the obtained character string is translated to generate a translation character string. The image reading apparatus 100 then has a function of replacing the character string included in the document image data with a translation character string obtained by translating the original characters to generate translation document data.

[0016] Furthermore, the image forming apparatus 200 according to the present invention executes a process for replacing, for example, unclear character images included in a document with translated and clear translated character images. Specifically, the image reading apparatus 100 recognizes the font characteristics of the character images included in the document through a process described below, and generates translated character images by rasterizing a translation string obtained by translating the characters using the recognized font.

[0017] The image reading device 100 then replaces the character images included in the original image with the translated character images, thereby obtaining the newly created translated original data in which clear characters are displayed. The configuration of such an image reading device 100 will be described below.

[0018] The image reading device 100 is disposed above the image forming unit 60. The image reading device 100 includes a document table 10, a cover 30, a stock cover 33, and a document transport unit 90. For ease of understanding, the document transport unit 90 is indicated by a two-dot chain line in FIG.

[0019] The document table 10 is disposed above the image forming unit 60. The document table 10 has a substantially rectangular parallelepiped shape. An original is placed on the document table 10.

[0020] The cover 30 has a thin, approximately rectangular parallelepiped shape. The cover 30 is placed above the platen 10. The cover 30 can be opened and closed relative to the platen 10. In this embodiment, the cover 30 is attached to the platen 10 on the rear side thereof, and can rotate freely around a rotation shaft located at the rear end of the platen 10. Alternatively, the cover 30 may be attached to the platen 10 at the left end thereof, and can rotate freely around a rotation shaft located at the left end of the platen 10.

[0021] The document transport unit 90 is disposed on the upper surface 35 of the cover 30. In this embodiment, the document transport unit 90 is configured integrally with the cover 30. The document transport unit 90 is also called an automatic document feeder or ADF (Auto Document Feeder).

[0022] The stock cover 33 is disposed on the upper surface 35 of the cover 30. The stock cover 33 faces a storage area 35a that is a part of the upper surface 35 of the cover 30. A part of the stock cover 33 is located inside the document transport unit 90.

[0023] The stock cover 33 and the storage area 35a constitute a storage tray 50. That is, the image reading device 100 is equipped with the storage tray 50. The storage tray 50 has an opening 50h. The opening 50h is located on the front side of the storage tray 50. A user can put in and take out an object to be stored through the opening 50h. That is, a user can store an object to be stored inside the storage tray 50, for example. The object to be stored is, for example, a document before or after being read, or an object other than a document (for example, the user's personal belongings).

[0024] The rear side of stock cover 33 is closed. Therefore, when cover 30 is opened relative to platen 10, the objects contained in stock cover 33 can be prevented from falling to the rear side of image forming apparatus 200.

[0025] The image reading device 100 reads an original document using, for example, an original document transport unit 90. The original document transport unit 90 transports the read original document to the upper surface 33u of the stock cover 33. In other words, the original document transported by the original document transport unit 90 is placed on the upper surface 33u of the stock cover 33.

[0026] As shown in FIG. 2, the image forming apparatus 200 further includes a control unit 70, a storage unit 80, an input / output unit 40, an open / close sensor 52, a human sensor 54, and a communication unit 55.

[0027] Typically, the control unit 70 is disposed inside the image forming apparatus 200. The control unit 70 includes an arithmetic element. The arithmetic element includes a processor. For example, the processor includes a central processing unit (CPU). The processor may include an application specific integrated circuit (ASIC).

[0028] The storage unit 80 stores various data, control programs, and various application programs. The storage unit 80 also stores manuscript image data, character images, translated character images, and translation manuscript data. These will be described in detail later. In other words, the storage unit 80 functions as a storage unit that stores translation manuscript data. The storage unit 80 is an example of the "output unit" of the present invention. This allows the generated translation manuscript data to be saved and used for various purposes.

[0029] The storage unit 80 is configured by, for example, a read-only memory (ROM), a random access memory (RAM), and / or a solid state drive (SSD). The storage unit 80 may include an external memory. The external memory is removable media. The storage unit 80 may include, for example, a universal serial bus (USB) memory and / or a secure digital (SD) card as the external memory. The storage unit 80 may also include a cache memory provided in the CPU for temporarily storing data.

[0030] The control unit 70 controls the operation of each component of the image forming device 200 by executing a control program stored in the storage unit 80. Specifically, in response to a selection operation received by the touch panel, the control unit 70 executes a process corresponding to the selected command item. In this way, the control unit 70 controls the image reading device 100, the input / output unit 40, the open / close sensor 52, the human presence sensor 54, the communication unit 55, the storage unit 80, the document transport unit 90, and the image forming unit 60.

[0031] The reading unit 20 generates document image data based on the document reading results by the control unit 70 executing a control program. At this time, the control unit 70 performs optical character recognition processing on the document image data to identify characters, thereby obtaining character identification information.

[0032] The control unit 70 also performs character recognition processing on the document image data and performs the function of extracting character images included in a preset extraction area. The control unit 70 is an example of the "extraction unit" of the present invention.

[0033] The control unit 70 also translates the extracted character string into a pre-specified translation language to generate a translated character string. The control unit 70 is an example of the "translation unit" of the present invention. The control unit 70 inputs the character string to be translated into the translation engine, and obtains the translated character string output from the translation engine.

[0034] The translation engine translates an input sentence using a language model constructed by machine learning using, for example, a neural network. The language model is constructed by learning a data set of input sentences and correct output sentences. The language model is trained to output a translated string for an input string by learning the statistical relationship between the features of the input sentence and the correct output sentence. The translation engine is stored, for example, in the storage unit 80. Note that the control unit 70 may use a translation engine stored in an external server via a communication network.

[0035] The control unit 70 also performs a function of recognizing the font characteristics of the characters represented by the extracted character image. The control unit 70 is an example of the "recognition unit" of the present invention. The control unit 70 recognizes the font characteristics of the character image using a font recognition model.

[0036] The font recognition model is a trained model that analyzes, based on a character image, feature information that indicates the font features of the characters represented by the character image. The font feature information includes, for example, the following: Font Name: The name of the font used in the image Font size: The size of the text shown in the text image. Text direction: The direction in which the text in the text image is arranged (horizontal, etc.) Character Orientation: Character orientation in the character image (vertical, etc.) Halftone: Whether halftone processing is applied to the character image Matrix: Information about the arrangement of pixels that make up a character image Character image resolution: number of pixels in a character image

[0037] The font recognition model is trained to output, in response to an input character image, feature information of the font of the character represented by the character image. The font recognition model is constructed using an arbitrary neural network or the like, and is stored in the storage unit 80.

[0038] The control unit 70 also performs the function of generating a translation character image by rasterizing font data corresponding to the character image based on the recognized font characteristics. That is, for a target character image, the control unit 70 rasterizes new font data for the translation string generated by the translation unit for that character using font characteristic information of the pre-translation character image recognized by the recognition unit. The newly rasterized font data corresponds to the translation character image. The translation character image is generated, for example, for each character or sentence. This allows the translation string to follow the font characteristics of the pre-translation character image.

[0039] The control unit 70 further replaces character images (character strings) included in the document image data with translated character images for the corresponding characters to generate translation document data. When generating the translation document data, the control unit 70 adjusts the font size of the translation character string so that the translation character string fits within the extraction area. In this way, the image forming apparatus 200 of the present invention can adjust the font size of the translation character string, so that when characters included in the document are translated, the translated characters can fit within the page frame of the document regardless of the type of language. The control unit 70 is an example of the "generation unit" of the present invention.

[0040] (1-2) Image reading device 100 Next, details of the image reading device 100 will be described with reference to Fig. 3. Fig. 3 is a schematic perspective view of the image reading device 100 shown in Fig. 1. Note that in order to avoid complicating the drawing, the document transport unit 90 and the image forming section 60 are omitted from Fig. 3.

[0041] 3, document table 10 includes contact glass 11, light-transmitting portion 12, and reading slit 13. On document table 10, contact glass 11, light-transmitting portion 12, and reading slit 13 are located apart from one another. For example, contact glass 11 is located in front of light-transmitting portion 12. Furthermore, reading slit 13 is located to the left of contact glass 11 and light-transmitting portion 12.

[0042] The contact glass 11 is disposed on the upper surface of the document table 10. The contact glass 11 is translucent. A document to be read is placed on the contact glass 11.

[0043] The light-transmitting portion 12 is disposed on the upper surface of the document table 10. The light-transmitting portion 12 has light-transmitting properties. The light-transmitting portion 12 is preferably transparent. The light-transmitting portion 12 is disposed, for example, behind the contact glass 11.

[0044] The reading slit 13 is disposed on the upper surface of the document table 10. The reading slit 13 is translucent. The reading slit 13 is used to read the document transported by the document transport unit 90. The reading slit 13 has a first scan sensor (not shown) therein that forms part of the reading section 20. The first scan sensor is an image sensor that reads the back side of the document transported by the document transport unit 90.

[0045] The reading unit 20 is disposed inside the document table 10. The reading unit 20 reads an image of a document placed on the contact glass 11 by a user. The reading unit 20 has a second scan sensor (not shown) disposed therein. The second scan sensor is disposed below the contact glass 11. The second scan sensor is an image sensor used to read the document placed on the contact glass 11.

[0046] The image sensor may be, for example, a charge coupled device (CCD) or a contact image sensor.

[0047] The cover 30 can be opened and closed freely relative to the document table 10. That is, the cover 30 opens and closes relative to the contact glass 11 included in the document table 10. For example, the cover 30 may be provided with a support member that allows the cover 30 to be opened and closed. When the cover 30 is in the "open state," the top surface of the document table 10 is exposed. On the other hand, when the cover 30 is in the "closed state," the top surface of the document table 10 is covered by the cover 30.

[0048] The cover 30 has a light-shielding portion 31 and a light-transmitting portion 32. The light-shielding portion 31 blocks light. The light-shielding portion 31 is formed from, for example, a colored resin.

[0049] The light-transmitting portion 32 has light-transmitting properties. The light-transmitting portion 32 is formed of a light-transmitting resin material such as an acrylic resin. Therefore, light that enters from one side of the light-transmitting portion 32 exits from the other side. Note that the light-transmitting portion 32 may be glass or hollow as long as it has light-transmitting properties.

[0050] The input / output unit 40 is disposed on the front side of the side of the document table 10. A user inputs instructions via the input / output unit 40. The input / output unit 40 accepts the user's instructions. In this embodiment, the user's instructions include the type of job and the number of documents indicating the number of documents.

[0051] For example, when a user inputs an instruction to start a scan job via the input / output unit 40, the reading unit 20 reads an original document and captures an image of the original document.

[0052] The input / output unit 40 also outputs information to the user. For example, the input / output unit 40 notifies the user of necessary information regarding the control of the image reading device 100 and the image forming unit 60.

[0053] The input / output unit 40 includes a display unit 41 and an input unit 42. The display unit 41 displays an operation screen or the results of various processes. The display unit 41 has a display. For example, the display includes a liquid crystal display or an organic EL display.

[0054] The input unit 42 includes, for example, various keys for specifying the type and content of a job. The input unit 42 includes a keyboard and a mouse. Alternatively, the input unit 42 may include a touch sensor. Operation instructions for the image reading device 100 and the image forming unit 60 are input to the input unit 42.

[0055] The open / close sensor 52 is attached to the document table 10. In this embodiment, the open / close sensor 52 is attached to an area of ​​the top surface of the document table 10 that overlaps with the cover 30 when the cover 30 is closed. More specifically, the open / close sensor 52 is disposed on the same surface as the contact glass 11. The open / close sensor 52 detects whether the cover 30 is open or closed.

[0056] The human presence sensor 54 detects whether or not a person is present within the detection range of the human presence sensor 54. The human presence sensor 54 is attached to the platen 10. The human presence sensor 54 transmits a detection signal to the control unit 70 (see FIG. 2). For example, the human presence sensor 54 is a pyroelectric infrared sensor, and detects far infrared rays (radiant heat) emitted from the human body.

[0057] The communication unit 55 performs processing for the image forming apparatus 200 to communicate with external devices. The communication unit 55 functions as a transmission unit that transmits translation manuscript data to the outside. The communication unit 55 is an example of the "output unit" of the present invention. This allows the generated translation manuscript data to be transmitted to the outside, and can be used for various purposes.

[0058] (1-3) Image forming unit 60 Next, the configuration of the image forming unit 60 will be described with reference to FIG. 2. The image forming unit 60 performs predetermined editing by forming an image on a recording medium. The recording medium is, for example, paper such as a manuscript. The image forming unit 60 performs the function of forming an image indicated by the translation manuscript data on paper. This allows the generated translation manuscript data to be output and used for various purposes.

[0059] As shown in FIG. 2, the image forming unit 60 includes a transfer unit 61, an image carrier 62, a charging unit 63, an exposure unit 64, a developing unit 65, a fixing unit 66, a discharge unit 67, a storage unit 68, and a conveying unit 69.

[0060] The control unit 70 controls the image forming unit 60 to form a specified toner image on the document. That is, the control unit 70 controls the transport unit 69 so that the transport unit 69 transports the document stored in the storage unit 68. The storage unit 68 stores documents before images are formed on them. The documents are, for example, plain paper, recycled paper, thin paper, thick paper, coated paper, or overhead projector (OHP) sheets.

[0061] In addition, the control unit 70 controls the image carrier 62, the charging unit 63, and the exposure unit 64 so that the charging unit 63 charges the rotating image carrier 62 and the exposure unit 64 exposes the rotating image carrier 62 to light to form an electrostatic latent image based on the image.

[0062] The control unit 70 also controls the developing unit 65 so that the developing unit 65 forms a toner image by developing the electrostatic latent image on the image carrier 62. Furthermore, the control unit 70 controls the conveying unit 69 and the transfer unit 61 so that the toner image formed on the image carrier 62 is transferred to the document via the intermediate transfer body of the transfer unit 61.

[0063] Furthermore, the control unit 70 controls the conveying unit 69 and the fixing unit 66 so as to fix the toner image transferred onto the document onto the document. The control unit 70 controls the heating roller and pressure roller of the fixing unit 66 to rotate, and also controls the heating roller to heat to a predetermined temperature.

[0064] Furthermore, the control unit 70 controls the conveying unit 69 to discharge the document onto which the toner image has been fixed from the discharge unit 67 to the outside of the image forming apparatus 200. In this manner, the image forming unit 60 forms a predetermined image on the paper surface and outputs the paper surface on which the image has been formed.

[0065] (2) System 1 processing Next, the processing of the system 1 will be described with reference to Fig. 4 to Fig. 6. Fig. 4 is a flow diagram of an entire job using the image forming apparatus 200. Fig. 5 is a flow diagram showing the first half of the processing for generating translation manuscript data shown in Fig. 4. Fig. 6 is a flow diagram showing the second half of the processing for generating translation manuscript data shown in Fig. 4.

[0066] (2-1) Overall job by image forming apparatus 200 First, the overall job performed by image forming apparatus 200 will be described with reference to Fig. 5. As shown in Fig. 5, in a job using image forming apparatus 200, image forming apparatus 200 first scans a document to be scanned (step S101). Specifically, reading unit 20 of image forming apparatus 200 reads a document set on document table 10. The read scan data (document image data) is stored in storage unit 80. The document image data includes a character image showing a character string written on the document.

[0067] Next, the control unit 70 receives from the user the setting of the division of the extraction area in the document image. Specifically, the user operates the input unit 42 to input the setting of the division of the extraction area in the document image. The input unit 42 receives from the user the setting of the division of the extraction area. This allows the user to set the character area in the size desired. The input unit 42 is an example of the "receiving unit" of the present invention.

[0068] In the image reading device 100, the following multiple divisions are defined in advance as character regions to be extracted regions. Paragraph block Line Block Word Blocks

[0069] Of these, paragraph blocks are sections in which an extraction area is set for each paragraph of text that makes up a manuscript. Line blocks are sections in which an extraction area is set for each line of text that makes up a manuscript. Word blocks are sections in which an extraction area is set for each word that makes up a manuscript. The following explanation takes as an example a case in which a word block is specified by the user.

[0070] Next, the control unit 70 executes a process for generating translation manuscript data (step S103). Specific details of this process will be described later with reference to Figures 5 and 6. This process performs font recognition on the scanned manuscript image (manuscript data) to obtain translation manuscript data in which characters have been replaced.

[0071] Thereafter, the control unit 70 performs one of the following processes in response to an operation from the user. Translation manuscript data transmission job (step S104) Translation manuscript data storage job (step S105) Print job for translation manuscript data (step S106) Each of these processes will be explained in detail in turn.

[0072] In the job for sending the translation manuscript data in step S104, the control unit 70 sends the translation manuscript data, instead of the manuscript image data generated by scanning, to, for example, a destination newly specified by the user, via the communication unit 55. This allows the user to send to the destination translation manuscript data in which the blurred character images have been replaced with newly rasterized, clear translation character images, for example, when the characters in the manuscript image data are unclear.

[0073] Next, in the job to save the translation manuscript data in step S105, the control unit 70 sends the translation manuscript data to the storage section specified by the user in the scan process (step S101) instead of the manuscript image data generated by scanning. This allows the user to save the translation manuscript data in which the blurred character images have been replaced with newly rasterized, clear translation character images, for future use, for example, if the characters in the manuscript image data are unclear.

[0074] Next, in the print job for the translation manuscript data in step S106, the control unit 70 can cause the image forming device 200 to print the translation manuscript data in place of the manuscript image data generated by scanning, in accordance with the printing conditions specified by the user. This allows the user to output on paper the translation manuscript data in which the blurred character images have been replaced with newly rasterized, clear translation character images, for example, in cases where the characters in the manuscript image data are unclear.

[0075] This completes the entire job performed by the image forming apparatus 200. This improves user convenience when using document image data.

[0076] (2-2) First half of the translation manuscript data generation process Next, the first half of the process for generating translation manuscript data, which corresponds to step 103 in Fig. 4, will be described with reference to Fig. 5. As shown in Fig. 5, in the process for generating translation manuscript data, first, a character area is extracted (step S1031). When the character area is extracted, the characters contained in the character area are simultaneously translated. This process will be described in detail with reference to Fig. 6.

[0077] Fig. 6 is a flow diagram showing details of the character region extraction process shown in Fig. 5. As shown in Fig. 6, the control unit 70 first determines the character region according to the specified character region division (e.g., word block) (step S311). Specifically, the control unit 70 performs optical character recognition processing on the document image data, divides the character region according to the specified character region division, and obtains the character image of the first character region.

[0078] Next, the control unit 70 accepts the setting of the language to be translated (step S312). Specifically, the user operates the input unit 42 to input the setting of the language to be translated into the characters included in the document. The input unit 42 accepts the setting of the language to be translated from the user. This allows the characters included in the document to be translated into the language desired by the user. The input unit 42 is an example of the "accepting unit" of the present invention.

[0079] Next, the control unit 70 translates the characters (step S313). Specifically, the control unit 70 translates the characters included in the document image data. Specifically, the control unit 70 inputs the characters (sentence) to be translated into the translation engine, and acquires the translation character string output from the translation engine.

[0080] Next, the control unit 70 determines the translated character area (step S314). Specifically, the control unit 70 specifies an area of ​​the page frame of the document image data that is occupied by a character string in the original language that corresponds to the translated character string obtained by translation.

[0081] Next, the control unit 70 determines whether the translated character area is larger than the original character area (step S315). Specifically, the control unit 70 compares the area occupied by the translated character string with the area occupied by the character string in the original language to determine which is larger. In this case, the two character strings are compared based on the same font.

[0082] If it is determined in step S315 that the area occupied by the translated character string is larger than the area occupied by the character string in the original language (Yes in step S315), the control unit 70 determines the font size of the translated character string so that the area occupied by the translated character string is the same as the area occupied by the character string in the original language (step S316).

[0083] That is, the control unit 70 reduces the font size of the translation character string (step S317). Specifically, the control unit 70 determines the font of the translation character string so that it is the largest size possible within the range of the area occupied by the character string in the original language.

[0084] On the other hand, if it is determined in step S315 that the area occupied by the translated character string is not larger than the area occupied by the character string in the original language (No in step S315), the control unit 70 determines whether the font size of the translated character string is appropriate for the character area (step S318). Specifically, the control unit 70 determines whether excess space is generated in the character area due to the small font size of the translated character string.

[0085] If the control unit 70 determines that the font size of the translation character string does not fit the character area, the control unit 70 increases the font size of the translation character string (step S319). Specifically, the control unit 70 uses as large a font size as possible for the translation character string so that it fits within the character area.

[0086] Next, the control unit 70 highlights the character region (step S320). Specifically, the control unit 70 highlights the character region of the translation character string to indicate that it is a translated sentence. This completes the character region extraction process (step S1031 in FIG. 5). Through this series of processes, a translation character string for the characters included in the original document is obtained.

[0087] Next, the process of generating translation manuscript data will be described with reference to Fig. 5. After step S1031, the control unit 70 determines whether the character to be evaluated is the first character in the extracted pre-translation character area (step S1032).

[0088] If the character to be evaluated is the first character (No in step S1032), the control unit 70 performs font recognition on that character (the character indicated by the character image before translation) (step S1033). Specifically, the control unit 70 inputs the character image to a font recognition model, and obtains information indicating the font output from the font recognition model.

[0089] Next, the control unit 70 extracts character features (step S1035). Specifically, the control unit 70 inputs the character image to be evaluated into the font recognition model, and obtains font feature information output from the font recognition model. Steps S1034 and S1035 may be performed simultaneously.

[0090] Next, the control unit 70 determines whether the font recognized for the character to be evaluated is a font that can be used in the image forming device 200 (step S1036). Specifically, the control unit 70 determines whether the font is a font that can be used to form an image on paper in the image forming unit 60 of the image forming device 200.

[0091] If the recognized font is available (Yes in step S1036), the control unit 70 replaces the font of the character image with the available font (step S1039). That is, the character image to be evaluated is replaced with the available font.

[0092] On the other hand, if the recognized font is not available (No in step S1036), it is determined whether a similar font is available (step S1037).

[0093] If it is determined that a font similar to the recognized font is available in image forming device 200 (Yes in step S1037), the font of the character image is replaced with the available similar font (step S1038). That is, the character image to be evaluated is replaced with the available similar font.

[0094] On the other hand, if it is determined that a font similar to the recognized font is not available in the image forming device 200 (No in step S1037), the control unit 70 returns to the process of extracting the character region (step S1031). That is, the control unit 70 acquires the next word region after the previously evaluated word region as the evaluation target.

[0095] Then, after steps S1038 and S1039, the character image data whose font has been replaced is acquired, thereby completing the first half of the process.

[0096] On the other hand, in step S1032, if the character to be evaluated is not the first character in the extraction region (No in step S1032), it is determined whether the character to be evaluated is the last character.

[0097] If the character to be evaluated is not the last character, the control unit 70 skips the processes from font recognition (step S1033) to font substitution (steps S1038 and S1039) and acquires a character image (step S1040). That is, since the second and subsequent characters in a single character area generally have the same font as the first character, font recognition processing and the like can be omitted for the second and subsequent characters.

[0098] Furthermore, if the character to be evaluated is the last character (Yes in step S1034), the control unit 70 ends the series of processes for one character region.

[0099] (2-3) The latter half of the translation manuscript data generation process Next, with reference to Fig. 7, the second half of the process of generating translation manuscript data, which corresponds to step 103 in Fig. 4, will be described. As shown in Fig. 7, in the second half of the process of generating translation manuscript data, first, the control unit 70 determines whether the character to be evaluated is the same as the previous character (step S1041).

[0100] If the character to be evaluated is not identical to the previous character, a translation character image for the character to be processed is generated (step S1042). Specifically, the generation unit generates a translation character image by rasterizing font data corresponding to the translation character string based on the font characteristics recognized for the character image representing the pre-translation character. The generated translation character image is stored in storage unit 80.

[0101] On the other hand, if the character to be evaluated is the same as the previous character in step S1041, control unit 70 uses the saved translated character image without generating a translated character image (step S1043). That is, for a character for which a translated character image has already been created, control unit 70 reuses the translated character image of the same character stored in storage unit 80 without generating a translated character image again.

[0102] In this way, if the characters in a character image match the characters in an already saved translation character image, the control unit 70 does not generate a translation character image, but instead uses the already saved translation character image. Therefore, by reusing an already generated translation character image, the processing load for generating a translation character image can be reduced.

[0103] Next, the control unit 70 determines whether the character to be evaluated corresponds to halftone (step S1044). Specifically, the control unit 70 refers to the extracted feature information and determines whether the character to be evaluated is expressed in halftone in the document image data.

[0104] If the control unit 70 determines that the character to be evaluated is expressed in halftone in the document image data (Yes in step S1044), it performs halftone processing on the translated character image (step S1045). As a result, the translated character image is in a halftone processed state, and a translated character image can be generated in a display mode similar to that of the document image.

[0105] On the other hand, if the control unit 70 determines that the character to be evaluated is not expressed by halftone processing in the document image data (Yes in step S1044), it does not perform halftone processing on the translation character image.

[0106] The control unit 70 then generates a translation character image in bitmap format and stores it in the storage unit 80. This prepares a translation character image for the extracted character region in a state ready for rendering. The control unit 70 repeats this series of processes for all character regions. This completes the process of generating translation manuscript data.

[0107] (3) Example Next, we will explain the translation manuscript data generated by the image reading device 100. Fig. 8 is a diagram showing manuscript images before and after translation according to the present invention. In the illustrated example, a manuscript containing English characters is translated into Japanese, and translation manuscript data displaying Japanese, shown on the right side of Fig. 8, is generated from manuscript image data displaying English, shown on the left side of Fig. 8.

[0108] As shown in FIG. 8, a first character area B1 in English is replaced with a second character area B2 in Japanese. Here, the first character area B1 and the second character area B2 have the same area size. However, the font size of the second character area B2 is larger than the font size of the first character area B1. In this case, because it was possible to increase the font size in the same character area by translating into Japanese, the font size after translation is increased in step S319 shown in FIG. 6.

[0109] Next, the third character area B3 in English shown in Figure 8 is replaced with the fourth character area B4 in Japanese. As in the previous example, the third character area B3 and the fourth character area B4 have the same area size. The third character area B3 and the fourth character area B4 also have the same font size. In this case, the font size of the translation character string matched the character area before translation in step S318 shown in Figure 6, so the size of the translation character string was not increased.

[0110] The fifth character area B5 in English shown in FIG. 8 is replaced with a sixth character area B6 in Japanese. As in the previous example, the fifth character area B5 and the sixth character area B6 have the same area size. However, the font size of the sixth character area B6 is slightly smaller than the font size of the fifth character area B5. In this case, the font size must be reduced by translating into Japanese to fit within the same character area, so the font size is reduced from before translation in step S317 shown in FIG. 6.

[0111] In this way, in the image reading device 100 of the present invention, the control unit 70 compares the size of each extracted character region before and after translation, and enlarges or reduces the font size to be applied to the translated character string. This allows the translated characters to fit within the page frame of the document when the characters contained in the document are translated, regardless of the language.

[0112] (4) Variations In the above embodiment, an example in which a character extraction region is set for each word block has been described, but this is not limitative. For example, a character extraction region may be set for each paragraph block or each line block.

[0113] (5) Other variations The image forming apparatus 200 may be a copier, a printer, a facsimile, a scanner, or a multifunction device that combines the functions of these.

[0114] 1, the image reading device 100 includes the document transport unit 90. However, the image reading device 100 does not necessarily have to include the document transport unit 90.

[0115] The image forming apparatus 200 may include an inkjet image forming unit. The inkjet image forming unit divides an image to be printed into pixels, charges ink particles with a voltage proportional to the position information of each pixel, and deflects them in an electrostatic field to make them reach the document, thereby forming an image.

[0116] The embodiments of the present invention have been described above with reference to the drawings (FIGS. 1 to 8). However, the present invention is not limited to the above embodiments and can be embodied in various forms without departing from the spirit and scope of the present invention. Furthermore, various inventions can be formed by appropriately combining multiple components disclosed in the above embodiments. For example, some components may be omitted from all components shown in the embodiments. The drawings mainly show each component in a schematic manner for ease of understanding, and the thickness, length, number, spacing, etc. of each component shown may differ from the actual components due to the convenience of drawing. Furthermore, the materials, shapes, dimensions, etc. of each component shown in the above embodiments are merely examples and are not particularly limited, and various modifications are possible within a scope that does not substantially deviate from the effects of the present invention. [Industrial Applicability]

[0117] The present invention provides an image reading device and an image forming device, and has industrial applicability. [Explanation of symbols]

[0118] 1. Information Processing Systems 20 Reading unit 70 Control Unit 80 Storage section 100 Image reader 200 Image forming device

Claims

1. a reading unit that reads an original and generates original image data; an extraction unit that performs character recognition processing on the document image data and extracts character strings for each preset extraction area; a translation unit that translates the extracted character string into a pre-specified translation language to generate a translated character string; a generating unit that generates translation manuscript data by replacing the character string with the translation character string; Equipped with When generating the translation manuscript data, the generation unit adjusts a font size of the translation character string so that the translation character string fits within the extraction area.

2. The image reading device according to claim 1 , further comprising a receiving unit that receives a setting of the translation language from a user.

3. a recognition unit that recognizes font characteristics of characters included in the extracted character string; the document image data includes a character image representing the character string, 3. The image reading device according to claim 1, wherein the generation unit rasterizes font data of characters included in the translation character string based on the translation character string generated by the translation unit and the font characteristics recognized by the recognition unit to generate a translation character image, and replaces the character image with the translation character image to generate the translation manuscript data.

4. The image reading device according to claim 1 , further comprising an output unit that outputs the translation manuscript data.

5. The image reading device according to claim 4 , wherein the output unit includes at least one of a transmission unit that transmits the translation manuscript data and a storage unit that stores the translation manuscript data.

6. The image reading device according to claim 5 ; an image forming unit that forms an image indicated by the translation manuscript data on a paper; An image forming apparatus having the same.

Images