JPH0554075A - Translation device - Google Patents

Abstract

(57) [Summary] [Purpose] Stable character recognition and translation processing is performed even for text manuscripts that include tables in the text. [Structure] A front portion and a portion other than the front portion are detected from image information stored in a page memory 401, and image information in character units is extracted separately, and character recognition processing and translation processing are performed. Then, the character image information of the translated word is combined with the original image or the recognition image in the front portion, and the size of the table is changed so that the combined image information falls within the block surrounded by the ruled lines of the table. Thereafter, it is determined whether the changed table portion can be incorporated in a portion other than the edited table. If it can be incorporated, the image information in which the table portion is incorporated in the portion other than the table is output.
If the data cannot be written in and embedded in the second image data, the image information of the portion other than the table and the image information of the front portion are separately output.
, And the printer 200 outputs this character image information.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a translation device, and more particularly, to a translation device for optically reading a document containing a table marked with markers in a sentence, performing image processing on the document, and outputting the image.

[0002]

2. Description of the Related Art In a translation apparatus for optically reading a text manuscript consisting of, for example, an alphabet, recognizing characters, translating the recognized characters word by word and outputting the words, an image stored in a memory is first read by a scanner. A process of cutting out an image in character units from the information is performed. In this character cutout, a histogram of the number of black pixels in the cutout direction (row direction, column direction) is calculated, and a certain threshold value is determined to determine the line or character delimiter and the character image is cut out.

[0003]

However, when a text manuscript consisting of alphabets or the like includes a table, the table often includes ruled lines, and the lines and character spacing in the table are often different from other places. The conventional method of counting the number of black pixels in the row direction and the column direction and recognizing the line or character delimiter from the histogram to cut out the character does not work well, causing a problem in translation.

Therefore, an object of the present invention is to provide a translation apparatus which performs stable character recognition / translation processing even for a text original containing a table in a sentence.

[0005]

According to the invention of the present application, an image reading means (100) for reading an original image; an image reading means (1)
Image storage means (401) for storing the image information read by (00); table detection means (1541 a, 15) for detecting a front portion from the image information stored in the image storage means (401).
41b); ruled line detecting means (1541c) for detecting ruled lines from information indicating a table portion; image information in character units is extracted from image information for each block in a block surrounded by the ruled lines detected by the ruled line detecting means (1541c) Front part character cut-out means (1541d, 1542, 1543); character cut-out means (1542, 1543) for extracting image information in character units from image information outside the block surrounded by the ruled lines detected by the ruled line detection means (1541c) A word portion detecting means (1544) for extracting image information in word units from the line direction interval of the image information cut out by the character cutting means (1541d, 1542, 1543) and the character cutting means (1542, 1543); Character cutout means (1541d, 1542, 1543) and character cutout means (1 42,1543) character recognition means (1545) for recognizing the characters of the image information cut out; words composed of a sequence of characters recognized by the character recognition means (1545) in word units detected by the word area detection means (1544) Translating means (1546) for translating the original image in the front portion and the character image recognized by the character recognizing means (1545) to the translating means (1
546) Character image information of the translated word is combined, and a table editing unit (1547a) is configured to change the size of the table so that the combined image information falls within the block; a document image and a character recognition unit in a portion other than the table. Other than the table editing means (1547b) for combining the character image information of the translated word of the translation means (1546) in the portion other than the table with one of the character images recognized by (1545); the table editing means (1547).
It is determined whether or not the table portion whose size is changed in a) can be embedded in the portion other than the table synthesized by the editing means (1547b) other than the table. If it can be incorporated, the image information including the table portion in the portion other than the table is output Write to memory (402),
If it cannot be incorporated, output image creating means (1547c) for writing the image information of the portion other than the table and the image information of the surface portion separately to the output image memory (402); and the image information stored in the output image memory (402). An output means (200) for outputting is provided. Symbols in parentheses indicate corresponding elements or corresponding matters in the embodiments shown in the drawings and described later.

Further, as a preferred embodiment of the present application,
The table detecting means is a designated area detecting means (1541a) for detecting the area of the document image designated by the marker; and a designated area separating means (1541b) for separating the inside and the outside of the area detected by the designated area detecting means. , And the inside of the separated area is the front portion.

[0007]

According to the invention of the present application, the table detecting means (1541)
a, 1541b) detects the front portion from the image information stored in the image storage means (401), and the ruled line detection means (1541c) detects the ruled line from the detected information. Then, the front portion character cutting means (1541d, 1542,
1543) extracts the image information in character units from the image information for each block in the block surrounded by the ruled lines, and the character cutting means (1542, 1543) extracts from the image information outside the block surrounded by the ruled lines. Extract image information in character units.

That is, since the character is cut out separately for the front portion and the portion other than the table, the character can be surely cut out even if the line and the character spacing of the front portion and the portion other than the table are different.

A word area detecting means (1544)
Is a front part character cutting means (1541d, 1542,
1543) and character cutting means (1542, 154)
3) The image information is extracted word by word from the line direction interval of the image information cut out by 3), and the character recognition means (1545) is also the front part character cutout means (1541d, 1542, 1).
543) and character cutting means (1542, 154)
3) Recognize the characters of the image information cut out. Next, the translation means (1546) is the word area detection means (1544).
Translates a word composed of a sequence of characters recognized by the character recognition means (1545) for each word detected by.

Therefore, the character recognition and the translation performed after the character segmentation are stably performed without being affected by the table.

The table editing means (1547a) is a document image and character recognition means (1545) in the front part.
The character image information of the translated word of the translating means (1546) in the table portion is combined with either one of the character images recognized by the user, and the size of the table is changed so that the combined image information falls within the block. Edit means other than table (1547b)
Combines the character image information of the translated word of the translation means (1546) in the portion other than the table with one of the document image in the portion other than the table and the character image recognized by the character recognition means (1545). After that, in the output image creating means (1547c), the table portion whose size is changed by the table editing means (1547a) is other than the table editing means (1547b).
Determines whether it can be embedded in a part other than the combined table. If it can be embedded, the image information in which the table part is embedded in the part other than the table is written in the output image memory (402). The image information of the part is separately written in the output image memory (402), and the character image information is output by the output means (200).

Therefore, when the image of the original document is left as much as possible and it is impossible, that is, when the translation result cannot be output on one sheet of recording paper, the table and the others are output separately. It does not reduce the amount of information.

Further, according to a preferred embodiment of the present invention, the designated area separating means (1541b) separates the inside and the outside of the area of the original image designated by the marker detected by the designated area detecting means (1541a). However, the table detection means
Since the inside of the separated area is detected as the front portion, the operator marks the front portion with the marker so that the front portion and the portion other than the front portion can be easily recognized. Other objects and features of the present invention will become apparent from the following description of embodiments with reference to the drawings.

[0014]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 shows an outline of a mechanical portion of a digital copying machine having a translation function which is an embodiment of the present invention. The mechanical unit mainly includes an image reading unit (scanner) 100 and an image recording unit (laser printer) 200.

The contact glass 1 of the scanner 100 on which a document (not shown) is placed is illuminated by the light sources 2a and 2b, and the reflected light (document image) from the read document is mirrors 3, 4, 5 and. CC through 6, 7 and lens 8
An image is formed on the light receiving surface of the D image sensor 9. Light source 2 (2
a, 2b) and the mirror 3 are mounted on a traveling body 10 that moves the lower surface of the contact glass 1 in parallel with the contact glass 1 in the sub-scanning direction (left-right direction in FIG. 1), and the mirrors 4 and 5 are mounted on the traveling body 10. It is mounted on the traveling body 11 that moves in the sub-scanning direction at a speed of 1/2 in conjunction with. The main scanning direction is performed by solid-state scanning of the CCD image sensor 9, the original image is read by the CCD image sensor 9, and the entire surface of the original is scanned by moving the optical system as described above. In the figure, 39 is
A pressure plate for pressing the document.

The laser printer 200 comprises a laser writing system, an image reproducing system and a paper feeding system. The laser writing system includes a laser output unit 21 and an imaging lens 2
2 and a mirror 23. Inside the laser output unit 21, there is provided a laser diode, which is a laser light source, and a polygon mirror (polygon mirror) that rotates at a high speed and a constant speed by an electric motor. The laser light output from the laser writing system is applied to the photosensitive drum 24 of the image reproducing system. Around the photosensitive drum 24, a charging charger 25, an eraser 26, a developing unit 27,
Transfer charger 28, separation charger 29, separation claw 3
0, a cleaning unit 31, and the like. A beam sensor (not shown) that generates a main scanning synchronization signal (MSSYNC) is arranged near the one end of the photosensitive drum 24 at a position where the laser beam is emitted.

The image reproducing process in the laser printer 200 will be briefly described. The peripheral surface of the photosensitive drum 24 is uniformly charged to a high potential by the charging charger 25. When the peripheral surface is irradiated with laser light, the potential of the irradiated portion is lowered. Since the laser light is controlled to be turned on / off in accordance with black / white for recording / reproduction, the potential distribution corresponding to the recorded image, that is, an electrostatic latent image is formed on the peripheral surface of the photosensitive drum 24 by the irradiation of the laser light. It When the portion on which the electrostatic latent image is formed passes through the developing unit 27, toner adheres according to the level of the potential, and the electrostatic latent image becomes a visualized toner image. The recording sheet 32 is fed from the cassette to the portion where the toner image is formed at a predetermined timing and overlaps the toner image. This toner image is transferred to the recording sheet 32 by the transfer charger 28, and then separated from the photosensitive drum 24 by the separation charger 29 and the separation claw 30. The separated recording sheet 32 is conveyed by a conveyor belt 34, heated and fixed by a fixing roller 35 having a built-in heater, and then ejected to an ejection tray 36.

In this embodiment, the laser printer 200 has two paper feeding systems. One paper feed system is provided with an upper paper feed cassette 33a and a manual paper feed tray 33c. The upper paper feed cassette 33a or the manual paper feed tray 33c is provided.
The recording sheet 32a set in the
Fed by. The other sheet feeding system is provided with a lower sheet feeding cassette 33b, and the recording sheet 32b in the lower sheet feeding cassette 33b is fed by a sheet feeding roller 37b. Then, the recording sheet 32 fed from any one of the sheet feeding rollers is temporarily stopped while being in contact with the registration roller 38, and is fed to the photosensitive drum 24 at a timing synchronized with the progress of the recording process.

FIG. 2 shows an outline of the electrical equipment section of the copying machine shown in FIG. The electrical component section mainly reads an original and outputs an image data signal, an image reading section 100, an image processing section 150 that processes the image data signal, an image recording section 200 that performs recording based on the image data signal, a memory circuit 400, A control unit 3 for controlling the operation board 500 and these units, etc.
It is composed of 00.

In the image reading section 100, the image signal read by the CCD image sensor 9 is output to the amplifier 10
It is amplified to a predetermined voltage amplitude of 1, converted into digital data by the A / D conversion circuit 102, and input to the shading correction circuit 103. The shading correction circuit 103 is a circuit for performing correction for uneven illuminance of the light sources 2a and 2b, uneven sensitivity of a light receiving element inside the CCD image sensor 9 and dark current. In addition, the image reading unit 10
Reference numeral 0 has a carriage drive motor M and a motor control circuit 104 for controlling the rotation of the motor M.

The image data signal output from the shading correction circuit 103 is input to the spatial filter circuit 151 of the image processing section 150. The spatial filter circuit 151 performs MTF correction for increasing the resolution of characters and line characters, smoothing processing for removing noise such as photographs, and the like.

The image data signal output from the spatial filter circuit 151 is input to the output modulation circuit 152, where it is converted into a halftone expression process in consideration of the correction considering the characteristics of the printer and a write signal created in the image recording unit 40. The corresponding code data is converted and output from the output circuit 153 to the image recording unit 200. The editing circuit 154 is a circuit that performs various types of processing and editing on the code data and outputs the code data.

In the image recording unit 200, the LD drive circuit 201 energizes and modulates the LD 202 in accordance with the image data signal output from the image processing unit 150, while correcting the output fluctuation of the laser light due to temperature or the like. The emitted laser light is emitted to the LD 202. The control unit 300 includes a CPU 301 that performs various controls according to a program, a ROM 302 that stores the control program, a RAM 303 that is temporarily used by the control program, and an I / O port 30.
A microcomputer including 4 and the like controls the entire copying machine.

The memory circuit 400 is composed of a page memory 401 for temporarily storing the read image, an output image memory 402 for storing the output image, and a dictionary memory 403 for storing a dictionary necessary for translation.

FIG. 3 shows the configuration of the editing circuit 154 shown in FIG. Reference numeral 1541 is a front portion determination cutout circuit for cutting out the front portion from the original image. This circuit 1541 is a mark detection circuit 1541a for detecting a marker portion subjected to marker processing for distinguishing the front portion, inside the detected marker portion. A table part separation circuit 1541b for separating the (table image) from the document image of the page memory 401, a ruled line detection circuit 1541c for recognizing ruled lines from the obtained table image and storing them as ruled line information, and a table obtained by the table part separation circuit 1541b. It has a block cutout circuit 1541d for cutting out the character portion in the table from the image. Further, reference numeral 1542 is a line cutout circuit for cutting out a character image for each line, 1543 is a cutout circuit for each character for cutting out one character from the character image cut out for each line, and reference numeral 1544 is a cutout character image. A word extraction circuit for extracting a word from the reference numeral 15
Reference numeral 45 is a character recognition circuit for recognizing characters in word units, reference numeral 1
Reference numeral 546 is a translation circuit for translating a recognized character, reference numeral 154.
7 is an output image memory 40 for outputting character images of translated words
2 is an output image creating circuit to be written in 2. The output image creation circuit 1547 changes the size of the table to add the translation result and edits the output image of the table.
a, a non-table editing circuit 1547b for editing the output image of the part other than the table by adding the translation result, and whether or not the table can be built based on the size of the table editing result and the editing result of the part other than the table. It has a table embedding circuit 1547c that creates an output image in which a table is incorporated in a portion other than the table and creates a separate output image if it cannot be incorporated.

FIG. 4 shows the processing operation of the CPU 301 for translation, and FIG. 5 shows its subroutine.

When a manuscript directly marked with a color felt pen or the like is set on the contact glass 1 and a translation instruction is given by the operator, the manuscript is optically read by the scanner section 100 (step 1: hereinafter in parentheses, step or The word "subroutine" is omitted), and the read original image is stored in the page memory 401 (1).
Then, the front part is cut off from the stored original image (2).

Referring to FIG. In the front portion cutting process (2), first, the front portion marked with a marker is recognized (21). In order to recognize the front portion, the mark detection circuit 1541a is composed of a circuit for detecting the size of the document in the main scanning direction and a circuit for detecting the mark area, as proposed by the present applicant in Japanese Patent Laid-Open No. 1-204192. To do.
That is, in the example shown in FIG. 6A, the original size is detected from the original image, and as shown in FIG. 6B, the density is checked for each main scan to detect the background density. ,
The black level (maximum density) is divided according to the number of gradations (for example, 64 gradations), and a certain level or higher (for example, 62) is detected as a mark.

Then, as shown in FIG. 7, the portion sandwiched between the markers recognized on each main scanning line is recognized as a part of the table area, and the continuous scanning lines detect the area between the markers. Examine the connection of a part and decide as the area.
That is, if the coordinate sections in the sub-scanning line direction of the area portions existing on the continuous main scanning line overlap, it is determined that these two partial areas are the same area. Therefore, FIG.
In the above example, it is divided into a region 1 and a region 2, which indicate that they are different from each other.

For this area recognition, the original image once read is displayed on a display device such as a CRT,
Using the cursor, light pen, mouse, etc., on the displayed display, you can make a mark for specifying the area, or put a document on the digitizer attached to the copier and use the touch pen to make a mark for specifying the area. Good.

Next, the recognized table portion and the other portion are separated (22). In this separation, the partial area recognized in real time in the recognition processing (21) of the front portion is written into the front image storage portion for storing the front image provided in the page memory 401. At that time, if it is determined that the partial area is not connected to the partial area on the previous scanning line, that is, it is in another area, the partial area is written to another table image storage area and the table count is performed. Increase one. Simultaneously with writing, the partial area determined to be within the mark area in the original image is cleared to have the density of zero. As a result, in the original image shown in FIG. 8A, after separation, partial areas are written in the front image storage area for each area as shown in FIG. As shown in (c), the partial area is stored in a removed form.

The boundary between the front portion and the other portion may be stored in the memory, and the subsequent processing may be performed separately inside and outside the area.

Next, the ruled line of the part separated as the front part is recognized and the pattern is recorded (23). And
The character portion surrounded by the ruled lines is separated for each area (block) in each column of the table (24). As for this block-by-block separation, as known from Japanese Patent Laid-Open No. 1-119885, first, vertical and horizontal ruled lines of a table portion are extracted, a block area surrounded by the extracted ruled lines is calculated, and the block area is calculated. Is cut out from the front image. As shown in FIG. 9, the ruled line pattern information obtained at the time of ruled line extraction is stored in the page memory 401 until the output editing is completed.
Store it inside. Again, it returns to the main flow of FIG.
When the front part cutting process (2) is completed, the original character cutting process for each line is performed for the separated block of the character part in the table and the part other than the table (3). Then, a word extraction process is performed to cut out each word from the cut line (4). The cutout for each word is performed based on the character spacing obtained by the cutout for each character. Next, the extracted words are recognized word by word (5), and Japanese corresponding to each word is searched from the translation dictionary and translated (6). Next, based on the ruled line pattern information of the table stored in the page memory 401, the table is edited so that the original image (which may be replaced by the recognized character image) and the translation result are included in the table, and the result is output as an image. Write to the memory 402 (7).

The table editing will be specifically described. When an image of the front portion is to be output in a table format, the amount of information contained in the table increases, so that it becomes necessary to rewrite the ruled lines of the table. That is, since the characters are recognized and translated for each block in the table, the edits are performed by embedding the block outputs in the corresponding positions of the stored ruled line pattern.

For example, let us consider a case where the original image characters and the translation result are arranged side by side in the table of the original image shown in FIG. It is to be noted that FIG.
0 shows the ruled line pattern information of the table shown in FIG. Since the translation result is added to the manuscript image characters, the original sentence for one line is output for two lines. Therefore, as shown in (a) of FIG. 11, first, the interval of the stored ruled line pattern in the vertical direction (column direction) is doubled, and then the blocks (A) and (B) located at the left end. , (C), (D) output image memory 4
The original image and the translation result are output to 02, and when all of the vertically arranged blocks have been written, the right side of the block is aligned with the one with the largest width (block (D)). Draw a border line with the block. However, if the horizontal lengths of the blocks differ according to the stored ruled line pattern as in this example, the block group having the shortest horizontal length (block (A),
(B) and (C)), the boundary ruled line (first
Draw a border line). Next, as shown in FIG. 11B, the blocks (E), which are vertically arranged along the drawn boundary,
The writing of (F) and (G) is performed, the ruled line pattern is referred to when the writing is completed, and the rightmost boundary ruled line (second boundary ruled line) which has not been drawn is repeatedly drawn. Next, as shown in (c) of FIG. 11, when writing is completed for all blocks including the remaining blocks (H), (I), (J), and (K), the right frame of the table Draw a ruled line and draw a horizontal ruled line.

As a result, the finally obtained ruled line information is stored by updating the ruled line pattern information, and the original ruled line pattern information shown in FIG. 10B is the ruled line information as shown in FIG. The pattern information is changed. That is,
Each interval of the horizontal ruled line y coordinate is doubled, and the vertical ruled line x coordinate becomes larger as the translation result protrudes from the original image.

Next, in the portions other than the table, the translation result is edited together with the original character image and the result is written in the output image memory 402 (8). After that, output allocation is performed by incorporating the table edit result and the edit result other than the table by judging the size thereof (9).

The output allocation will be specifically described. Figure 1
The difference (horizontal width of the table) between the largest x-coordinate (12.3) and the smallest x-coordinate (5.2) is calculated from the ruled line pattern information of the output table shown in FIG. 2, and the calculated value (7.1 = 12. 3-
5.2) is compared with the cut-out lateral width of the image portion cut out as the front portion of the original character document shown in FIG. If the calculated value is equal to or smaller than the cutout width, the table portion fits within the cutout boundary line, so that the table is edited by incorporating it into an image other than the table as shown in FIG. On the other hand, if the calculated value is larger than the cutout width, the table cannot be embedded in an image other than the table, and therefore the table and the portion other than the table are separately output as shown in FIG. Further, a calculated value (15.50) of a difference (vertical width of the table) between the largest y coordinate (25.2) and the smallest y coordinate (9.6) obtained from the ruled line pattern information of the output table shown in FIG.
6 = 25.2-9.6) is larger than the vertical length (adjacent vertical width of the table cutout portion shown in FIG. 14) of the edited result of the portion other than the table adjacent to the side of the portion where the table is cut out. Even when the cut-out portion of the table or the cut-out portion is caught at the end of the paper, the table cannot be embedded in the image other than the table. Therefore, as shown in FIG. 15, the table and the portion other than the table are separately output.

Next, the output image created in the output image memory 402 is output (10), transferred to the recording paper by the printer 200 and discharged (11).

As described above, as shown in FIG. 16, when the table can be incorporated in an image other than the table, the marked input document is translated on one recording sheet including the table and the table. The output image is changed.

[0041]

As described above, according to the invention of the present application, the characters are cut out separately in the table portion and the portion other than the table. Therefore, for example, even when the line and the character spacing of the table portion and the portion other than the table are different. The characters are reliably cut out, and the subsequent character recognition and translation are performed stably without being affected by the table.

Further, the image of the original document is left as much as possible, and when it is impossible, that is, when the translation result cannot be output on one recording sheet, the table and the others are output separately. There is no particular reduction in the amount of information.

Further, according to a preferred embodiment of the present invention, the operator marks the front portion with the marker so that the front portion and the portion other than the front portion can be easily recognized.

[Brief description of drawings]

FIG. 1 is a block diagram showing an outline of a mechanical unit of a digital copying machine having a translation function according to an embodiment of the present invention.

FIG. 2 is a block diagram showing an outline of an electric component section of the digital copying machine shown in FIG.

3 is a block diagram showing a schematic configuration of an editing circuit 154 shown in FIG.

FIG. 4 is a flowchart showing a part of the content of the processing operation of CPU 301 shown in FIG.

FIG. 5 is a flowchart showing the contents of a front part cutting process (2) shown in FIG.

6A and 6B show recognition of a front portion, FIG. 6A is a plan view showing a marked original image, and FIG. 6B is a block diagram showing density detection.

FIG. 7 is a plan view showing a front area of a document image for each main scanning line.

FIG. 8 shows how a front image is separated from a document image,
(A) is a plan view showing an original image read into a memory by specifying an area, (b) shows a specified area in (a),
The plan view showing the front image in the memory and (c) are
It is a top view which shows the image in memory which the front image was isolate | separated from the original image of (a).

FIG. 9 is a block diagram showing extraction of ruled lines from a designated area and ruled line pattern information obtained thereby.

10A is a plan view showing an example of a table in a document image, and FIG. 10B is a block diagram showing ruled line pattern information in FIG. 10A.

FIG. 11 shows table editing, (a) of FIG.
2 is a plan view showing a state in which the table shown in FIG. 2 is doubled in the vertical direction (column direction) and a first boundary ruled line is drawn, (b) is a plan view showing a state in which a second boundary ruled line is drawn, and (c) [Fig. 6] is a plan view showing a state in which a right frame ruled line and a horizontal direction ruled line are drawn.

FIG. 12 is a block diagram showing ruled line pattern information of an output table after table editing.

FIG. 13 is a plan view showing an original document image showing a cutout boundary line and a cutout horizontal width of a table.

FIG. 14 is a plan view showing an output image when the cutout width shown in FIG. 13 is equal to or larger than a calculated value.

FIG. 15 is a plan view showing an output image when the cutout width shown in FIG. 13 is smaller than the calculated value.

FIG. 16: When a table can be incorporated in an image other than the table, the marked input manuscript is changed to a translated output image including the table and the table other than one sheet of recording paper. FIG.

[Explanation of symbols]

Reference numeral 100: image reading unit (image reading unit) 150: image processing unit 154: editing circuit 1541: front portion determination cutout circuit 1541a: mark detection circuit (front detection unit, designated area detection unit) 1541b: front portion separation circuit (front detection) 1541c: Ruled line detection circuit (ruled line detection means) 1541d: Block cutout circuit (front portion character cutout means) 1542: Line cutout circuit (front portion character cutout means, character cutout means) 1543: In each line Cutout circuit for each character (front part character cutout means, character cutout means) 1544: word extraction circuit (word area detection means) 1545: character recognition circuit (character recognition means) 1546: translation circuit (translation means) 1547: output image creation Circuit 1547a: Table editing circuit (table editing means) 1547b: Other than table Circuit (editing means other than table) 1547c: Table built-in circuit (output image creating means) 200: Image recording section (output means) 300: Control section 301: CPU 302: ROM 303: RAM 304: I / O port 400: Memory circuit 401: page memory (image storage means) 402: output image memory (output image memory) 403: dictionary memory 500: operation board

 ─────────────────────────────────────────────────── --- Continuation of the front page (72) Inventor Masato Yokoyama 1-3-6 Nakamagome, Ota-ku, Tokyo Inside Ricoh Co., Ltd. (72) Inventor Tomonori Tanaka 1-3-3 Nakamagome, Ota-ku, Tokyo No. 6 in Ricoh Co., Ltd. (72) Inventor Takaaki Tada 1-3-6 Nakamagome, Ota-ku, Tokyo In Ricoh Co., Ltd.

Claims (2)

[Claims] 1. An image reading unit for reading an original image; an image storage unit for storing image information read by the image reading unit;
Table detecting means for detecting a table portion from the image information stored in the image storing means; Ruled line detecting means for detecting a ruled line from information indicating the table portion; Image for each block in a block surrounded by the ruled lines detected by the ruled line detecting means Table portion character cutting means for extracting image information in character units from information; Character cutting means for extracting image information in character units from image information outside a block surrounded by ruled lines detected by the ruled line detection means; table portion character cutting means And a word area detecting means for extracting the image information in word units from the line direction interval of the image information cut out by the character cutting means; a character recognition means for recognizing a character of the image information cut out by the front part character cutting means and the character cutting means; A translation means for translating a word composed of a sequence of characters recognized by the character recognition means for each word detected by the word area detection means; In either one of the character image is an original image and the character recognition means recognized in the branching, synthesizes the character image information translated translation means in Table moiety,
Table editing means for changing the size of the table so that the combined image information is contained in the block; one of the document image in the portion other than the table and the character image recognized by the character recognition means in the portion other than the table Editing means other than the table for synthesizing the character image information of the translation word of the translating means: It is judged whether the table portion whose size has been changed by the table editing means can be incorporated into the portion other than the table synthesized by the editing means other than the table. ,
Output image creating means for writing the image information in which the front portion is incorporated in the portion other than the table to the output image memory and writing the image information of the portion other than the table and the image information of the front portion separately in the output image memory; and A translation device comprising: output means for outputting the image information stored in the output image memory. 2. The specified area detecting means for detecting an area of an original image specified by a marker, the table detecting means;
The translation device according to claim 1, further comprising: designated area separating means for separating the inside and the outside of the area detected by the designated area detecting means, wherein the inside of the separated area is a front portion.