JP6458764B2 - Image processing device - Google Patents

Description

  The present invention relates to a technique for extracting original text from image data and transmitting the original image data together with the text.

  In Patent Document 1, a document is read, a marker marked on the document is detected, a region of the document surrounded by the marker is recognized, and the inside of the region is printed, or The outside is printed.

JP 2005-167875 A

  By the way, as another application of the technique for recognizing the area of the document surrounded by the markers as in Patent Document 1, the recognized area is subjected to OCR (Optical Character Recognition) processing, and the text in this area is extracted. It is possible to do. As a result, for example, image data of a document can be stored and transmitted together with text in the area, and subsequent document processing is facilitated.

  Further, when extracting the text of the marker portion, it is desirable that the page of the document on which this marker is marked can be designated. For example, when a destination is described on the first page of a plurality of documents, the image data of the first page of the document is not necessary, and the destination (text) described in the first page of the document. Therefore, if the first page can be designated by marking the first page, the destination (text) of the first page can be reliably extracted and used. It is possible to improve convenience.

  Furthermore, it is more desirable to warn when a marker is not marked on the document of the designated page. As a result, it is possible to prevent only the image data of the original from being saved or transmitted without being able to extract the text at the marker portion.

  The present invention has been made in view of the above circumstances, and can specify a page of a document on which a marker is marked, and warn when a marker is not set on a document on the specified page. An object of the present invention is to provide an image processing apparatus capable of performing the above.

  An image processing apparatus according to an aspect of the present invention includes an acquisition unit that acquires image data indicating an image of a document, a marker detection unit that detects a marker portion marked on the document based on the image data, A reception unit that receives a page of a document to be detected by a marker detection unit, a text extraction unit that analyzes the image data and extracts the text of the marker portion in the document, and transmits the image data and the text Informing that the marker is not marked when the marker detection unit does not detect the document on the page of the document to be detected by the transmission unit and the marker detection unit received by the reception unit. An image processing device.

  According to the present invention, it is possible to designate a page of a document on which a marker is marked, and to warn when a marker is not set on a document on a designated page.

1 is a perspective view showing an image forming apparatus to which an image processing apparatus according to an embodiment of the present invention is applied. 1 is a block diagram illustrating an internal configuration of an image forming apparatus to which an image processing apparatus according to an embodiment of the present invention is applied. It is explanatory drawing which shows the procedure for processing and transmitting the image of the document by the image processing apparatus of this embodiment. It is explanatory drawing which shows the other procedure for processing and transmitting the image of the original document by the image processing apparatus of this embodiment. It is explanatory drawing which shows another procedure for processing and transmitting the image of the original document by the image processing apparatus of this embodiment. 6 is a flowchart illustrating a control process for processing and transmitting an image of a document by the image processing apparatus of the present embodiment. It is a flowchart which shows the control process following FIG. 6A. FIG. 3 is a plan view showing an operation unit and a display unit of the image forming apparatus. (A) is a figure which shows the 1st page key and all page keys which are displayed on the screen of the display part of an image forming apparatus, (b) is the OK key and NG which are displayed on the screen of the display part of an image forming apparatus. It is a figure which shows a key. (A) And (b) is a figure which shows the message displayed on the screen of the display part of an image forming apparatus.

  An image processing apparatus according to an embodiment of the present invention will be described below with reference to the drawings.

  FIG. 1 is a perspective view showing an image forming apparatus to which an image processing apparatus according to an embodiment of the present invention is applied. FIG. 2 is a block diagram illustrating an internal configuration of the image forming apparatus. The image forming apparatus 10 is a multi-function machine having a plurality of functions such as a copy function, a printer function, a scanner function, and a facsimile function. The image forming apparatus 10 is generally configured by an apparatus main body 11, an image reading unit 110 disposed above the apparatus main body 11, and a connecting unit 12 provided between the image reading unit 110 and the apparatus main body 11.

  The apparatus main body 11 includes an image forming unit 120, a paper feeding unit 13, a discharge tray 14, and the like.

  When the image forming apparatus 10 performs an image reading operation, the image reading unit 110 (acquisition unit) reads a document placed on the document placing table 111 and controls an image of the document under the control of an operation control unit 102 described later. The image data shown is generated. This image data is stored (saved) in the storage unit 160. In the image forming apparatus 10, the communication unit 170 receives image data from another information processing apparatus such as a PC (Personal Computer) instead of the image reading unit 110 reading the bundle of documents to acquire image data. The image data indicating the original document may be acquired by.

  When the image forming apparatus 10 performs an image forming operation, the image forming unit 120 is fed from the paper feeding unit 13 under the control of the operation control unit 102 based on the image data stored in the storage unit 160. A toner image is formed on the recording paper. Thereafter, the toner image formed on the recording paper is thermally fixed by a fixing unit (not shown). The recording paper on which the fixing process has been completed is discharged to the discharge tray 14.

  An operation unit 150 and a display unit 130 are arranged on the front surface of the apparatus main body 11. The display unit 130 includes a liquid crystal display (LCD) or an organic EL (Organic Light-Emitting Diode) display.

  A touch panel 140 is disposed on the screen of the display unit 130. The touch panel 140 is a so-called resistive film type or capacitive type touch panel, and detects contact (touch) of the user's finger or the like with the touch position on the touch panel 140.

  The operation unit 150 includes, for example, a menu key for calling a menu, an arrow key for moving the focus of a GUI constituting the menu, a determination key for performing a confirmation operation on the GUI constituting the menu, a start key, and the like.

  The storage unit 160 is a large-capacity storage device such as an HDD.

  The communication unit 170 is a network interface composed of a communication module such as a wireless LAN board.

  The image forming apparatus 10 further includes a control unit 100. The control unit 100 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and the like. The control unit 100 is configured such that the control unit 101, the operation control unit 102, the operation receiving unit 103, the communication control unit 104, the marker detection unit are executed by executing the program stored in the ROM or the storage unit 160 on the CPU. 105, functions as an OCR processing unit 106 and a notification unit 107. Note that each of the above-described configurations of the control unit 100 may be configured by a hardware circuit without depending on an operation based on a program.

  The control unit 101 governs overall operation control of the image forming apparatus 10.

  The operation receiving unit 103 has a function of receiving a user operation on the touch panel 140 based on a detection signal output from the touch panel 140. The operation receiving unit 103 has a function of receiving a user operation on the hard key of the operation unit 150.

  The communication control unit 104 (transmission unit) has a function of controlling communication operations by the communication unit 170. The communication unit 170 transmits / receives data to / from a PC (Personal Computer) or the like under the control of the communication control unit 104.

  The operation control unit 102 has a function of controlling an image reading operation by the image reading unit 110, a display operation by the display unit 130, and the like.

  The marker detection unit 105 analyzes image data indicating an image of a document acquired by the image reading unit 110 and detects a marker portion marked with a marker of a preset color (also referred to as a prescribed color) on the document. Have

  The OCR processing unit 106 (text extraction unit) has a function of extracting text included in the marker location detected by the marker detection unit 105.

  The notification unit 107 has a function of notifying the user of information by displaying a message or the like on the display unit 130.

  Here, in this embodiment, a plurality of originals are read and images of these originals are transmitted. Also, under any conditions set by the user, a marker of a specified color marked on the document is detected, and the text at the marker is recognized and extracted (also referred to as zone OCR), and the image of the document is detected. Is sent with the text.

  As the above-mentioned arbitrary conditions, there are a condition as to which of the first page document and all page documents is a marker detection target and a condition as to whether or not the first page document is transmitted.

  For example, as shown in FIG. 3, when all the pages of the document are set as the marker detection targets, at least one document marked with the marker is read from all the pages of the document. An image of the document is acquired, and the text at the marker portion of the at least one document is extracted, and the image of the at least one document is transmitted together with the text of the at least one document. Therefore, the image of the original and the text of the marker portion are transmitted only for the original on which the marker is marked among the plurality of originals.

  Also, as shown in FIG. 4, when the first page document is set as a marker detection target and the first page document is set to be transmitted, all page documents are read and all pages are read. Is obtained, the text of the marker portion of the first page of the document is extracted, and the image of the original document of all pages is transmitted together with the text of the marker portion of the first page of the document. For example, when the file name or catalog (text) described in the first page of the document is necessary, if the marker is attached to the file name or catalog, the file name or catalog is extracted and transmitted.

  Further, as shown in FIG. 5, when the first page document is set as a marker detection target and the first page document is set not to be transmitted, all page documents are read and all pages are read. The image of the original of the first page is acquired, the text of the marker portion of the original of the first page is extracted, and the image of the original of the second and subsequent pages is transmitted together with the text of the original of the first page. For example, when the address and the title are described in the first page of the document and the image data of the first page of the document is not necessary, and only the destination and the title (text) of the first page of the document are necessary, If a marker is attached to the subject, the destination and the subject text are extracted and transmitted. In particular, for contracts, etc., a marker cannot be marked. Therefore, add the first page of the manuscript to the contract, write the address and title on the cover, and place the marker on the address or title. If attached, the destination and the subject (text) are extracted and transmitted, and the destination and the subject can be easily used.

  In addition, if either the first page document or all pages document is set as the marker detection target, but the marker is not set on the detection target page document, this is warned. For example, when the marker is not marked or the color of the marker is different from the specified color, this is warned. Accordingly, it is possible to prevent an error in processing a document on which a marker of a specified color is marked.

  Next, the operation of the image forming apparatus 10 having the above configuration will be described. 6A and 6B are flowcharts showing a control process for reading a document by the image forming apparatus 10, extracting text from the document image, and transmitting the document image and text.

  First, it is assumed that a plurality of touch keys 21a to 21h associated with each function are displayed on the screen of the display unit 130 of the image forming apparatus 10 as illustrated in FIG. In this state, when the user touches the touch key 21h corresponding to the transmission of the document, the touch operation on the touch key 21h is detected by the touch panel 140, and this touch operation is received by the operation receiving unit 103. Then, a function (application program) for transmitting a document is activated (step S101).

  Subsequently, the user operates the operation unit 150 to input destination information indicating a document transmission partner, for example, a telephone number, a mail address, and the like (step S102). At this time, an input screen such as a telephone number and an e-mail address may be displayed on the display unit 130 so that the user performs an input operation on the input screen.

  Further, the user sets a plurality of documents on the image reading unit 110 and operates the start key of the operation unit 150. When the operation of the start key is accepted by the operation accepting unit 103 (step S103), the control unit 101, as shown in FIG. 8A, detects the first page of the original and all pages as detection targets by the marker detecting unit 105. A first page key 22a and an all page key 22b for designating one of the documents are displayed (step S104).

  For example, when the user performs a touch operation on the all-page key 22b, the touch operation on the all-page key 22b is detected by the touch panel 140, and this touch operation is received by the operation receiving unit 103 (“all-page key” in step S105). At this time, the operation control unit 102 activates the image reading unit 110, the image reading unit 110 sequentially reads the plurality of originals, and each image data indicating the images of the originals of all pages is sequentially stored in the storage unit 160. (Step S106).

  In addition, the marker detection unit 105 sequentially analyzes each image data in the storage unit 160, detects a marker of a specified color marked on the document (“Yes” in step S107), and detects a marker of the specified color. Each time the OCR processing unit 106 is instructed, the marker portion of the specified color in the document is designated. The OCR processing unit 106 analyzes the image data indicating the original with the marker of the specified color, performs OCR processing on the marker position of the specified color, extracts the text of the marker position of the specified color, and indicates this text Text data is generated and stored in the storage unit 160 (step S108).

  Then, based on the destination information input in step S102, the communication control unit 104 obtains image data indicating the original for all of the originals with the marker of the predetermined color, at the marker portion of the predetermined color extracted from the image data. The text data indicating the text is transmitted to the transmission partner (step S109).

  When the image data and the text data are transmitted for all the originals with the marker of the specified color, the control unit 101 ends the processes of FIGS. 6A and 6B.

  If the marker detection unit 105 does not detect the marker of the predetermined color (“No” in step S107) and the marker of the predetermined color is not marked on any of the document images on all pages, the notification unit 107 Without performing the processes of steps S108 and S109, for example, as shown in FIG. 9A, a message indicating that the marker of the specified color is not marked on any of the original images on all pages is displayed on the display unit 103. (Step S110), and the processing of FIGS. 6A and 6B is terminated. For this reason, the user can recognize the situation that the original is not transmitted because the marker of the specified color is not marked on any of the originals on all pages by looking at the message.

  That is, when the all-page key 22b for designating a document of all pages as a detection target by the marker detection unit 105 is selected by touch operation, markers of a plurality of documents are marked as shown in FIG. For the original only, the image of the original and the text of the marker location are transmitted.

  If the marker of the specified color is not detected, a message indicating that the marker of the specified color is not marked on any of the document images on all pages is displayed on the display unit 103.

  Next, when the user performs a touch operation on the first page key 22a, the touch operation on the first page key 22a is detected by the touch panel 140, and this touch operation is received by the operation receiving unit 103 ("Step 1" Key"). At this time, as shown in FIG. 8B, the control unit 101 displays an OK key 23a and an NG key 23b on the screen of the display unit 130 for designating whether or not to transmit the first page of the document. Step S111).

  For example, when the user touches the OK key 23a, the touch operation on the OK key 23a is detected by the touch panel 140, and this touch operation is received by the operation receiving unit 103 ("OK" in step S112). In response to this, the operation control unit 102 activates the image reading unit 110, the image reading unit 110 sequentially reads the plurality of originals, and each image data indicating the original image of all pages is sequentially stored in the storage unit 160. Stored (step S113).

  Further, the marker detection unit 105 analyzes only the image data indicating the image of the first page of the document in the storage unit 160 and detects the marker of the specified color marked on the first page of the document (step S114). “Yes”), the OCR processing unit 106 is instructed to specify the marker portion of the specified color in the document on the first page. The OCR processing unit 106 analyzes the image data indicating the image of the first page of the document, applies OCR processing to the marker portion of the specified color, extracts the text of the marker portion of the specified color, and indicates this text. Text data is generated and stored in the storage unit 160 (step S115).

  Based on the destination information input in step S102, the communication control unit 104 converts each image data indicating the original of all pages into text indicating the text of the marker portion of the specified color extracted from the image data of the original of the first page. The data is transmitted to the transmission partner together with the data (step S116). Then, the processes in FIGS. 6A and 6B are terminated.

  Further, when the marker of the specified color is not detected by the marker detection unit 105 (“No” in step S114), and the marker of the specified color is not marked on the first page of the document, the notification unit 107 Without performing the processing of steps S115 and S116, for example, a message indicating that the marker of the specified color is not marked on the image of the first page of the document as shown in FIG. 9B is displayed on the display unit 103. (Step S117), the processing in FIGS. 6A and 6B is terminated. For this reason, the user can know the situation that the document is not transmitted because the marker is not marked on the image of the document on the first page by looking at the message.

  That is, the first page key 22a for designating the first page document as a detection target by the marker detection unit 105 is touch-operated, and the OK key 23a for designating transmission of the first page document is subsequently displayed. When the touch operation is performed, as shown in FIG. 4, the image of the document on all pages is transmitted together with the text of the marker portion of the document on the first page. For this reason, if a marker is attached to the file name or catalog described in the first page of the document, text such as the file name or catalog is extracted and transmitted.

  When the specified color marker is not detected, a message indicating that the specified color marker is not marked on the first page of the document image is displayed on the display unit 103.

  On the other hand, when the user touches the NG key 23b, the touch operation on the NG key 23b is detected by the touch panel 140, and this touch operation is received by the operation receiving unit 103 (“NG” in step S112). In response to this, the image reading unit 110 sequentially reads the plurality of documents, and each image data indicating the image of the document of all pages is sequentially stored in the storage unit 160 (step S118).

  Further, the marker detection unit 105 analyzes only the image data indicating the image of the first page of the document in the storage unit 160, and detects the marker of the prescribed color marked on the first page of the document (step S119). “Yes”), the OCR processing unit 106 is instructed to specify the marker portion of the specified color in the document on the first page. The OCR processing unit 106 analyzes the image data indicating the image of the first page of the document, applies OCR processing to the marker portion of the specified color, extracts the text of the marker portion of the specified color, and indicates this text. Text data is generated and stored in the storage unit 160 (step S120).

  Based on the destination information input in step S102, the communication control unit 104 uses the image data indicating the second and subsequent pages of the document, and the text of the marker portion of the specified color extracted from the image data of the first page of the document. It transmits to the other party of transmission with the text data shown (step S121). Then, the processes in FIGS. 6A and 6B are terminated.

  Further, when the marker of the specified color is not detected by the marker detection unit 105 (“No” in Step S119), and the marker of the specified color is not marked on the first page of the document, the notification unit 107 Without performing the processes of steps S120 and S121, a message as shown in FIG. 9B is displayed on the display unit 103 (step S117), and the processes of FIGS. 6A and 6B are terminated. For this reason, the user can know that the document has not been transmitted because the marker is not marked on the image of the document on the first page.

  That is, the first page key 22a for designating the first page document as a detection target by the marker detection unit 105 is touch-operated, and subsequently, the NG key 23b for designating that the first page document is not transmitted. When the touch operation is performed, as shown in FIG. 5, the images of the second and subsequent pages are transmitted together with the text of the marker portion of the first page of the document. Therefore, if you add the first page of the original cover page to the contract, write the address and title on this cover, and add a marker to the address and title, the image of the contract will be sent to the address and title. (Text) will be sent.

  When the specified color marker is not detected, a message indicating that the specified color marker is not marked on the first page of the document image is displayed on the display unit 103.

  The present invention is not limited to the configuration of the above embodiment, and various modifications can be made. For example, various color samples of the marker are displayed on the screen of the display unit 130, and one of these color samples is selected through the touch panel 140, and the color of the selected color sample is set as the default color of the marker. May be.

  In the above-described embodiment, the case has been described in which the receiving unit 103 selectively receives either the first page document or the entire page document as a detection target by the marker detection unit 105. However, the present invention is not necessarily limited to this case. It is not limited to. The accepting unit 103 may accept a part of the pages of the original as a detection target of the marker detecting unit 105 from all the originals.

  In this case, the marker detection unit 105 detects a marker part from the document on the page received by the reception unit 103. Then, the OCR processing unit 106 extracts the text included in the marker location detected by the marker detection unit 105. The communication control unit 104 transmits the detected text, that is, the text of the marker portion in the document of the page received by the receiving unit 103, together with the image data indicating the document of the page received by the receiving unit 103. When the marker detection unit 105 fails to detect the marker portion of the document of the page received by the reception unit 103, the notification unit 107 notifies that the marker is not marked as in the above embodiment.

  In the above embodiment, the marker of the first page is designated as a detection target by the marker detection unit 105, but the marker of the specified color marked on the first page of the document is not detected by the marker detection unit 105. In this case, a warning message is displayed and the processing is finished without transmitting the image data and the text data. After displaying the warning message, the first page of the original is displayed on the display unit 130. Also good. Then, when the user checks the first page of the document and operates the start key or the like, the image data and text data may be transmitted.

  In the above-described embodiment, the case has been described in which the marker detection unit 105 detects a spot marked with a predetermined designated color marker as a marker spot, but the present invention is not necessarily limited to this case. The marker detection unit 105 may detect the marker location based on at least one element of the marker color, the marker line type, and the marker thickness.

DESCRIPTION OF SYMBOLS 10 Image forming apparatus 100 Control unit 101 Control part 102 Operation control part 103 Operation reception part 104 Communication control part 105 Marker detection part 106 OCR process part 110 Image reading part 120 Image formation part 130 Display part 140 Touch panel 150 Operation part 160 Storage part 170 Communication department

Claims (9)

An acquisition unit that acquires image data indicating an image of a document;
Based on the image data, a marker detection unit for detecting a marker portion marked on the document;
A reception unit that receives a page of a document to be detected by the marker detection unit;
A text extraction unit that analyzes the image data and extracts the text of the marker portion in the document;
A transmission unit for transmitting the image data and the text;
A notifying unit for notifying that a marker has not been marked when the marker detecting unit has not detected the marker portion of the document on the page of the document to be detected by the marker detecting unit received by the receiving unit; An image processing apparatus comprising:   The image processing apparatus according to claim 1, wherein the reception unit selectively receives one of a first page document and all page documents as a detection target by the marker detection unit.   The transmission unit receives an original of all pages as a detection target of the marker detection unit by the reception unit, and the marker portion is detected when the marker part is detected in at least one of the originals of all pages by the marker detection unit. The image processing apparatus according to claim 2, wherein the image data indicating the document on which the location is marked is transmitted together with the text of the marker location on the document.   The image processing apparatus according to claim 2, wherein the reception unit receives designation as to whether or not to transmit the first page of the document.   When the receiving unit receives the first page of the original as the detection target of the marker detection unit and receives the transmission of the first page of the original, the image data indicating the originals of all pages is received. The image processing apparatus according to claim 4, wherein the image is transmitted together with the text of the marker portion in the first page of the document.   When the receiving unit receives the first page of the original as a detection target of the marker detection unit and does not transmit the first page of the original, image data indicating the second and subsequent pages is received. The image processing apparatus according to claim 4, wherein the image is transmitted together with the text of the marker portion in the first page of the document.   The transmission unit receives a page of a part of the original as a detection target of the marker detection unit by the reception unit, and receives the image data indicating the original of the received page as a document of the received page The image processing apparatus according to claim 1, wherein the image processing apparatus transmits the text together with the text of the marker portion.   8. The marker detection unit according to claim 1, wherein the marker detection unit detects, as the marker location, a location marked with a predetermined color among the locations marked in the image data. 9. Image processing device.   The notifying unit does not detect the marker portion marked on the first page document by the marker detecting unit when the receiving unit receives the first page document as a detection target of the marker detecting unit. The image processing apparatus according to any one of claims 1 to 8, wherein a notification that a marker is not marked is provided when the image is recorded.