JP2003085479A - Image processor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processor capable of preventing erroneous discrimination by enhancing character discrimination accuracy without discriminating only characters the orientations of which are difficult to be discriminated even in the case that time is restricted for discrimination of the orientation. SOLUTION: The image processor to perform an image processing of image data read by a reading means to read an original image, is provided with a character area detecting means to detect character areas in the image data, a discriminating means to discriminate the orientations of the prescribed numbers of characters for characters in the respective character areas detected by the character area detecting means and a document orientation discriminating means to discriminate the document orientation of the image data according to discrimination results of the respective character areas by the discriminating means.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus for performing image processing on image data read by a reading unit for reading a document image such as a digital copying machine.

[0002]

2. Description of the Related Art Conventionally, in this type of image processing apparatus,
A device having a function of detecting the document direction of a read document image and rotating the image data even if the document direction of the document is different to align the document direction has been devised. Further, in the image processing apparatus having such a function, for the characters in one document, the character direction is determined in the order in which the characters are detected, and the document direction of the document is determined.

[0003]

However, in the conventional technique, the character direction is determined in the order in which the characters are detected,
The document direction of the manuscript was determined. Therefore, if there is a time limit for determining the orientation of a document, it may happen that even if there are easily identifiable characters in the same manuscript, only fonts and sizes that are difficult to identify happen to be processed. However, if the determination time ends while the processing is being performed, the document direction of the document may not be detected or the document may be erroneously determined.

The present invention has been made in view of the above problems, and an object of the present invention is to discriminate only characters whose character direction is difficult to discriminate even when the direction discrimination has a time limit. It is another object of the present invention to provide an image processing device capable of improving character discrimination accuracy and preventing erroneous discrimination.

[0005]

In order to achieve the above object, the present invention is an image processing apparatus for image-processing image data read by a reading means for reading an original image, and detects a character area in the image data. The character area detecting means, the determining means for determining the direction of a predetermined number of characters in the characters in each character area detected by the character area detecting means, and the determining means according to the determination result of each character area by the determining means. It is characterized in that a document orientation discriminating means for discriminating the document orientation of the image data is provided.

[0006]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the accompanying drawings.

FIG. 3 is a sectional view for explaining the structure of an image processing apparatus showing an embodiment of the present invention. In FIG.
Reference numeral 1 denotes a platen glass on which the documents fed from the automatic document feeder 142 are sequentially placed at predetermined positions. Reference numeral 102 denotes a document illumination lamp composed of, for example, a halogen lamp, which exposes a document placed on the platen glass 101.

Scanning mirrors 103, 104, 105 are housed in an optical scanning unit (not shown), and the CCD unit 106 receives reflected light from the original while reciprocating.
Lead to. The CCD unit 106 is composed of an image forming lens 107 for forming an image of reflected light from a document on the CCD, an image pickup element 108 including, for example, a CCD, a CCD driver 109 driving the image pickup element 108, and the like. The image signal output from the image sensor 108 is converted into, for example, 8-bit digital data, and then manually input to the controller unit 139.

Further, 110 is a photosensitive drum, which is precharged by a pre-exposure lamp 112 to prepare for image formation. 1
13 is a primary charger, which uniformly charges the photosensitive drum 110. Reference numeral 117 denotes an exposure unit, which is composed of, for example, a semiconductor laser, and exposes the photosensitive drum 110 on the basis of image data processed by a controller unit 139 that controls image formation and the entire apparatus to form an electrostatic latent image. Form.

Reference numeral 118 denotes a developing device, which contains a black developer (toner). A pre-transfer charger 119 applies a high voltage before transferring the toner image developed on the photosensitive drum 110 to a sheet. 120, 12
Reference numerals 2 and 124 denote paper feeding units, and each paper feeding roller 12
The transfer paper is fed into the apparatus by driving 1, 123, and 125, and the transfer paper is temporarily stopped at the position where the registration roller 126 is provided, and the transfer timing with the image formed on the photosensitive drum 110 is taken and re-transferred. Be delivered.

Reference numeral 127 denotes a transfer charger, which transfers the toner image developed on the photosensitive drum 110 onto a transfer sheet to be fed. Reference numeral 128 denotes a separation charger, which separates the transfer sheet after the transfer operation from the photosensitive drum 110. The toner remaining on the photosensitive drum 110 without being transferred is collected by the cleaner 111.

A conveyor belt 129 conveys the transfer sheet after the transfer process to the fixing device 130. For example, the transfer sheet receives a toner image by heat. Thirteen
A flapper 1 controls the conveyance path of the transfer sheet for which the fixing process has been completed to either the staple sorter 132 or the arrangement direction of the intermediate tray 137. The sheets discharged to the staple sorter 132 are sorted into bins, and the stapling unit 141 performs stapling according to an instruction from the controller unit 139.

Further, 133 to 136 are feeding rollers,
In these, the transfer paper after the fixing process is once inverted (multiplexed) or non-inverted (double-sided) and fed to the intermediate tray 137. Reference numeral 138 denotes a re-feeding roller that re-transfers the transfer sheet placed on the intermediate tray 137 to the registration roller 12 again.
It is conveyed to the position of 6. The controller section 139 is provided with a microcomputer, an image processing section, and the like, which will be described later, and performs the above-mentioned image forming operation according to an instruction from the operation panel 140.

FIG. 2 is a block diagram showing the configuration of the controller unit 139 in the image processing apparatus according to the present invention.

In FIG. 2, reference numeral 201 denotes a CPU for controlling the entire image processing apparatus, which is a read-only memory 20 storing a control procedure (control program) for the apparatus main body.
3 (ROM) to sequentially read and execute the program. The address bus and data bus of the CPU 201 are connected to each load via a bus driver circuit 202 and an address decoder circuit. Reference numeral 204 denotes a random access memory (RAM) which is a main storage device used as a storage area for input data, a work storage area, and the like.

205 is an I / O interface,
The operator performs key input and displays the status of the device such as liquid crystal, LED
The operation panel 140, the paper feed system, the transport system,
Motors 207 and clutches 20 for driving the optical system
8, solenoids 209, and paper detection sensors 210 for detecting the conveyed paper, etc. are connected to respective loads of the apparatus. In the developing device 118, a toner remaining detection sensor 211 for detecting the amount of toner in the developing device 118 is arranged,
The output signal is input to the I / O port 205.

215 is a high-voltage unit, which is a CP
According to the instruction of U, the primary charger 113, the developing device 11
8. High voltage is output to the pre-transfer charger 119, the transfer charger 127, and the separation charger 128.

An image processing unit 206 receives the image signal output from the CCD unit 106, performs image processing described later, and outputs a control signal for the laser unit 117 according to the image data. Laser unit 117
The laser light output from the device irradiates and exposes the photosensitive drum 110, and the light emission state is detected by the beam detection sensor 213 which is a light receiving sensor in the non-image area, and the output signal is input to the I / O port 205. .
In addition, the I / O port 205 is connected to the image processing unit 20 described later.
The select signal of the selector 312 in 6 is output.

FIG. 1 is a block diagram of the image processing unit 206 in the controller unit 139 in the image processing apparatus according to the present invention.

The image signal converted into the electric signal by the CCD 108 is first corrected by the shading circuit 301 for the pixel-to-pixel variation, and then the scaling circuit 302 performs the data thinning process during the reduction copy to enlarge the image. Data is interpolated during copying.

Next, in the edge emphasizing circuit 303, for example, a second-order differentiation is performed in a 5 × 5 window to emphasize the edge of the image. Since this image data is luminance data, the γ conversion circuit 304 performs data conversion by table search in order to convert it to density data to be output to the printer. The image data converted into the density data is input to the binarization processing unit 305. Here, multivalued data is converted into binary data by the ED method, for example. The binary-converted image data is input to the combining circuit 307. The synthesizing circuit 307 selectively outputs the input image data and the image data in the image memory 310 configured by, for example, a DRAM, or outputs an ORed result. The read / write control for the image memory 310 is performed by the memory control unit 309. These image data are input to the PWM circuit 308 for conversion into a signal of laser emission intensity, and a pulse width according to the image density is output to the laser unit. Further, the image output from the shading circuit 301 is input to the document direction discriminating unit 306, and the document direction discriminating process described later is performed.

Next, the document direction discriminating operation according to the present invention will be described with reference to FIGS. FIG. 4 is a block diagram of the inside of the document orientation discriminating unit 306.

The image data output from the shading circuit 301 is input to the CPU / memory section 401 to temporarily store the image data and perform various controls. The CPU 201 in the controller unit 139 is bus-connected by, for example, a dual port RAM (not shown), and transmits / receives data. Note that serial communication may be used.

The character recognizing / orienting discriminating unit 402 pays attention to the fact that it is the character that most accurately represents the orientation of the document, and it recognizes several kinds of character areas in the document at 0 °, 90 °, 180 °.
Character recognition is performed from the directions of 270 ° and 270 °, and the direction with the highest accuracy among the character recognition accuracies in each direction (confidence of character recognition: distance with respect to character feature distribution) is the document direction.

The area separation unit 403 makes a character portion, a graphic portion, a natural surface portion, a front surface portion, etc. of the document image data into a rectangular shape as a preprocessing for performing the character recognition / direction determination processing by the character recognition / direction determination unit 402. This is a block for performing a process of separating an area and adding an attribute (character portion or the like) of each area.

The storage device 404 is composed of, for example, a hard disk or a magneto-optical disk, and is used to store various processing results (image data, area separation result, character recognition result, etc.). The I / F unit 405 uses SCSI or RS.
232C or the like, and is provided for transmitting data to the outside. The computer 406 obtains information via the I / F unit 405 or obtains data from a movable storage device such as a magneto-optical disk for use.

Next, the outline of the document direction automatic discrimination / correction and character recognition processing in this embodiment will be described with reference to the flowchart shown in FIG.

The input image data (multi-valued image) is first separated by the area separating unit 403 into rectangular areas according to attributes such as a character portion, a graphic portion, a natural image portion, and a front portion (steps S1 and S2). ). Here, the area information enclosed by the rectangle is actually created.

Next, the rectangle information of the character area is extracted from each attribute (step S3). Here, the character area is a text part, a title part, characters in a table, a caption part of a figure, or the like. For example, in the case of the documents shown in FIGS. 6A and 6C, the rectangular information of the character area as shown in FIGS. 6B and 6D is extracted. Then, the document direction is discriminated using several blocks among these blocks (step S4).
As a result, if the document direction is the forward direction, the character recognition process is continuously performed on the character block in the image (step S7).

On the other hand, if the document direction is incorrect, the image data is rotated in the correct direction (step S5). Then, the rotation image is subjected to region separation, and the region separation information is corrected (step S6). This is to correct the difference in area separation information due to image rotation, and one method is to perform area separation processing again on all rotated image data. The other method is to apply address translation to the area separation result. In the area separation processing, the image is generally assumed to be in the forward direction, and therefore the area separation processing performed in the initial stage and the area separation processing performed on the rotated image data often have different results. Therefore, it is desirable to adopt the former method.

Next, in step S7, the character area block in the rotated image data is recognized by the character recognition processing system. As a result, the area separation information and the character recognition information are finally obtained in both cases of no rotation / with rotation (step S8). This processing result is the I / F unit 405.
Is transmitted to the computer 406 via the computer and used by filing application software on the computer 406. In addition, the CPU 20 in the controller unit 139
1 is transmitted for each image.

Next, a method of discriminating the document direction using the character recognition processing will be described.

[Region Separation Processing] The black pixels of the document image data are detected, and the rectangular frame of the black pixel block is created by the contour tracking or labeling method. Next, character areas (titles, text, captions, etc.), graphic areas, natural image areas, table areas, etc., based on the black pixel density in the rectangle, the presence or absence of adjacent rectangular blocks, the aspect ratio of the rectangle, etc. To determine. The rectangular area of the character area is discriminated from the processing result.

[Character Recognition Processing] One method of character recognition processing is the feature vector extraction and comparison method. For example, as shown in FIG. 7A, it is assumed that a character area including the character "book" is identified. As the first step, character cutting processing is performed on this character area (see FIG. 7B). This is the process of cutting out the rectangle of one character. First, the image data of 8 bits is converted into binary of white and black,
It is required if the state of black pixel continuity is detected. The background data of the image created by the bistogram creating unit 312 in FIG. 3 is used as the binary conversion threshold value at this time.
In the second stage, one character is m × n (eg 64 × 64)
The pixel block is cut out (see FIG. 7C). Then, the distribution direction of the black pixels is extracted from that using a window of 3 × 3 pixels (direction vector information: FIG. 7).
(See (d)).

Incidentally, FIG. 7 (d) shows an example of a part of the direction vector information, and the window of 3 × 3 pixels is shifted to obtain several ten pieces of direction vector information. This vector information becomes a character feature. By comparing this feature vector with the contents of the character recognition dictionary stored in advance, characters are extracted in order from the character having the feature closest to the feature vector. In this case, the features are first in the order in which the features are closer to the feature vector.
Candidate, second candidate ... The closeness of the feature to the feature vector is the closeness of the distance to the character, that is, the confidence level (accuracy) of character recognition.

[Character Orientation Discrimination Processing] In this way, the degree of confidence in character recognition is obtained. The character orientation discrimination processing based on the degree of confidence is performed by using the sentence example "name of the present invention" shown in FIG. explain.

FIG. 8 (a) is a forward sentence, and FIG. 8 (b) is 2
It is a sentence rotated by 70 °. Focusing on the “book” here,
When determining the character direction, as shown in FIG. 8C, 0 °, 90 °, 180 for one character “book”
Let's try character recognition from 4 directions of ° and 270 °. For each rotation angle, the reading method of the character rectangular area may be changed, and the original need not be rotated.

The character recognition result at each rotation angle is shown in FIG.
As shown in (c), they are different from each other. Note that FIG.
In (c), the temporary character recognition result and the confidence level for the purpose of explanation are shown, and it is not always the case.

In FIG. 8C, when the character recognition is performed from the forward direction (0 °), the character is correctly recognized as "book", and the confidence is a high value of 0.90. When the character recognition is performed from the direction rotated by 90 °, it is erroneously recognized as “town” and the confidence level is also reduced to 0.40. False recognition occurs like this,
The reason for the decrease in confidence is that the character recognition is performed based on the feature vector when viewed from the rotated direction. Similarly, when character recognition is performed from a direction rotated by 180 ° or 270 °, erroneous recognition occurs and confidence is also reduced. still,
The difference in the degree of confidence in character recognition by direction becomes more remarkable as the character is more complicated.

The result shown in FIG. 8C has the highest degree of confidence in the case of the forward direction, and therefore it is judged that the document is highly likely to be in the normal direction. In order to improve the accuracy of character direction discrimination, character recognition is similarly performed from four directions for a plurality of characters in the same block. Furthermore, if the character direction is determined only by one block, the character direction may be erroneously determined for a special character string, so the same character recognition will be performed for a plurality of blocks. Then, for each block, the average value of the confidence levels of the respective recognition target characters in each block in each of the four directions is calculated, and the average value of the confidence values of each block in each of the four directions is calculated. The direction with the highest value is recognized as the character direction (document direction).

As described above, the character direction is not recognized by the confidence level of only one character, but the character direction is recognized by the confidence levels of a plurality of characters in the same block, and further, a plurality of characters in the same block. It is possible to determine the (document) direction with high accuracy. However, it goes without saying that the character direction can be determined with higher accuracy than before even if the character direction is determined based on the confidence level of only one character, or the character direction is determined based on the confidence levels of multiple characters in the same block. .

Next, when the result of discrimination of the character direction (document direction) is a direction other than the positive direction, the original image is rotated so that the character direction becomes the positive direction. This rotation is C shown in FIG.
This can be easily performed by a known technique using the PU / memory 401, and the description thereof will be omitted.

By the above processing, the original image data shown in FIG. 9A, the area separation data shown in FIG. 9B, and the character recognition information shown in FIG. 9C can be obtained. . As described above, this information is stored in the controller unit 139.
Is sent to the CPU 201 and used for various image processing and various controls.

The format of the area separation data is, as shown in FIG. 9B, "head" indicating that it is area separation data.
er "and the identifiers" rect1 "to" r "of the separated areas
The information of each area (block) that is configured by "ect4" and distinguished by this identifier is the block number "orde".
r ", block attribute (character part, graphic part, etc.)" ar
t ”, the coordinate values“ x1 ”and“ y1 ”at the upper left of the block,
The block width “w”, the block height “h”, the vertical or horizontal writing “direction”, the block ID “selfID”, the parent block ID including the block “upperID”, Parent block attribute "upperAtt", spare area "rese"
rve ”.

As shown in FIG. 9C, the character recognition information is "header" indicating that it is the character recognition information.
Character recognition information “OCR1” or the like regarding a single character such as “book” and “blkh” corresponding to the above “rect1” or the like indicating a block in which the character is merged.
“Eader” and combination information.

Each character recognition information such as "OCR1" is "type" indicating whether it is a character or a blank.
e ”, the first to fifth candidate characters“ character 1 ”to“ character 5 ”according to the confidence level of the character recognition, the cutout positions“ x1 ”and“ y1 ”of the character, and the width“ w ”of the character. , The height of the character “h”, and the spare area “reserve”. If the characters cannot be recognized, for example, if the characters are not included in all the image data, the reserved area "res"
Data representing "unknown (undetectable)" is returned to "erve".

Next, the operation panel 140 of the image processing apparatus of the present invention will be described with reference to FIGS.

FIG. 10 is a basic screen displayed on the operation panel 140 of the image processing apparatus according to the present invention. 1001
Is an extended function key, and by pressing this key, a mode such as double-sided copying, multiple copying, moving, setting of binding margin, setting of frame erasing, etc. is entered. 1002 is an image mode key,
Enter the setting mode for shading, shadowing, trimming and masking the copied image. A user mode key 1003 can be used to register a mode memory and set a standard mode screen for each user.

An applied zoom key 1004 enters a mode for independently changing the magnification in the X and Y directions of a document, and a mode for a zoom program for calculating the magnification from the size of the document and the copy size. Reference numerals 1005, 1006 and 1007 denote M1 key, M2 key and M3 key, which are pressed when calling the respective mode memories. 1008 is a call key,
Press to call the previously set copy mode. 1
An option key 009 is used to set an optional function such as a film projector for directly copying from a film.

A sorter key 1010 is used to sort sorters and set modes such as groups. Reference numeral 1011 denotes a document mixed loading key, which has A4 size and A
Press to set 3 size or B5 size and B4 size documents together. Reference numeral 1012 denotes an equal magnification key, which is pressed when the copy magnification is 100%. Reference numerals 1014 and 1015 are a reduction key and an enlargement key, respectively, which are pressed when performing a fixed size reduction and enlargement. Reference numeral 1016 denotes a zoom key, which is pressed when performing non-standard size reduction / enlargement in 1% steps. A paper selection key 1013 is pressed when selecting a copy paper.

Reference numerals 1018 and 1020 denote density keys. Each time the density key 1018 is pressed, a dark copy is made.
Each time you press 20, a light copy is made. Reference numeral 1017 denotes a density display, and when the density keys 1018 and 1020 are pressed, the display changes to the left and right. Reference numeral 1019 denotes an AE key, which is pressed when a document with a dark background such as a newspaper is copied for automatic density adjustment. 1
Reference numeral 021 denotes a HiFi key, which is pressed when a document such as a photographic document having a high halftone density is copied.

Reference numeral 1022 denotes a character emphasizing key, which is pressed when a character is desired to be highlighted in copying a character original. Reference numeral 1023 denotes a guide key, which is displayed when the key is pressed when the function of the key is unknown. Reference numeral 1024 denotes a copy mode key, which is pressed when copying. Reference numeral 1025 denotes a fax key, which is pressed when performing a fax. Reference numeral 1026 denotes a file key, which is pressed to output file data. Reference numeral 1027 denotes a printer key, which is pressed to print out image data from an external device such as a computer. A document orientation detection key 1028 is pressed to detect the document direction of the document set in the document feeder. Reference numeral 1029 denotes a document orientation detection detailed setting key, which is pressed to make detailed settings relating to document orientation detection.

FIG. 11 is a screen displayed on the operation panel 140 when the document orientation detection detail setting key 1029 in FIG. 10 is pressed.

When the document orientation detection detailed setting key 1029 is pressed in the state of the basic screen of FIG. 10, the document orientation detection detailed setting screen is displayed as shown in FIG. On this screen, the number of characters to be detected for one character area detected in the document is set. For example, if a number from 1 to 50 is input using a ten-key pad (not shown)
Displayed at 0. Also, for example, 10 is input in advance as a default value. Reference numeral 1031 denotes a return key, which is pressed to end the setting here and return to the screen in the figure.

Next, the operation for determining the document direction of the conventional apparatus will be described with reference to the explanatory view of FIG.

For example, in the case of a manuscript as shown in FIG. 12, the character area 1 is 120 characters in the numerical string, the character area 2 is 12 characters in the diagonal character string "CONFIDENTIAL", and the character area 3 is " 13 characters in the character string "contents described in this specification", and 1 in the character string "・ Problems to be solved by the present invention, ・ Effect of the present invention"
It is assumed that each character area of 6 characters is detected.

Further, the time given to the character discrimination of the present embodiment is, for example, one second, and the number of discriminable characters within this time is 30. In the conventional art, when a certain character area is detected, all the characters in the character area are tried to be discriminated in order. In the example of FIG. 12, when the character area 1 is detected, the direction of the characters in the character area 1 is sequentially determined within a predetermined time. There are 120 characters in the character area 1, and there is a character in which all the characters are the same even if they are turned upside down. Therefore, it is possible to detect 0 ° or 180 ° in the direction determination of the character in the character area 1.

Further, since there are 120 characters in the character area 1 and only 30 characters can be discriminated within a predetermined time, even if there is a character area that can be surely discriminated in the character areas 3 and 4,
The document direction of this original must be determined by discriminating only the characters in the character area 1. Originally, the original shown in FIG. 12 had to be judged to be in the direction of 0 °, but there was a possibility of misjudging to be 180 °. The same applies to the case where the characters are inclined as in the character area 2.

Next, the detailed operation of the image processing apparatus of the present invention will be described with reference to the explanatory view of FIG. 12 and the flowchart of FIG.

First, in step S1, it is determined whether or not the copy key on the operation panel 140 is turned on. If turned on, the original on the original table is read in step S2, and in step S3, the character area in the original is cut out by the method described above, and the direction of the character in a certain character area is determined.

For example, in the case of a manuscript as shown in FIG.
The character area 1 is 120 characters in a numerical string, and the character area 2 is 1 in a diagonal character string "CONFIDENTIAL".
Two characters, 13 characters in the character string "contents described in this specification" in the character area 3, and 1 in the character string "・ Problems to be solved by the present invention-Effects of the present invention" in the character area 4.
It is assumed that each character area of 6 characters is detected.

Further, the time given to the character discrimination of the present embodiment is, for example, 1 second, and the number of characters that can be discriminated within this time is 30 characters, and the number of characters discriminated in one character area is shown in FIG. It is assumed that 8 characters are set on the document orientation detection detail setting screen. In step 3, the character direction is first determined for the character area 1, and in step S4, 8 is determined.
It is determined whether or not the character discrimination is completed. If the determination of 8 characters has not been completed, the process returns to step S3 to determine the character direction. If the determination of the predetermined number of characters (8 characters) is completed in step S4, the process proceeds to step S5 for a predetermined time (1
Second) is finished. If the predetermined time has not ended, the process proceeds to step S6, and it is determined whether the character direction determination has ended for all the character areas in the document.

If the character direction determination is not completed for all the character areas, the process proceeds to step S7, and the character direction determination is performed for another character area. Since the previous operation was performed for the character in the character area 1, the character direction determination operation is performed for the character in the character area 2 this time. Then, in step S8, it is determined whether or not the predetermined number of characters (8 characters) has been determined. If not, the process returns to step S7 to perform the character direction determination operation, but in step S8, the predetermined number of characters is determined to have ended. When judged, it returns to step S5 and judges whether or not the predetermined time has ended. If the predetermined time has not ended, the operations from step S6 to step S8 described above are repeated, and the character direction determination of 8 characters is similarly performed for the character areas 3 and 4.

When it is determined in step S5 that the predetermined time has ended, the process proceeds to step S9, and the majority of the character direction determination results from the character areas 1 to 4 is taken. For example,
If the determination result is 180 ° in the character area 1, 90 ° in the character area 2, 0 ° in the character area 3, and 0 ° in the character area 4, the majority decision is taken to be 0 °, and the document direction of this document is determined in step S10. Is determined to be 0 °.

[0065]

As is apparent from the above description, according to the present invention, in the image processing apparatus for image-processing the image data read by the reading means for reading the original,
A character area detecting unit that detects a character area in the image data, a determining unit that determines the direction of a predetermined number of characters in each character area detected by the character area detecting unit, and each of the determining means. Since the document direction determining means for determining the document direction of the image data according to the result of the determination of the character area is provided, even if there is a time limit in the direction determination, it is difficult to determine the character direction and only the characters are determined. It is possible to obtain the effect that the accuracy of character discrimination can be improved and erroneous discrimination can be prevented without causing a mistake.

[Brief description of drawings]

FIG. 1 is a block diagram showing a configuration of an image processing unit in a controller unit in an image processing apparatus according to the present invention.

FIG. 2 is a block diagram showing a configuration of a controller unit in the image processing apparatus according to the present invention.

FIG. 3 is a sectional view showing a configuration of an image processing apparatus according to the present invention.

FIG. 4 is a block diagram showing a configuration of a document orientation determination unit shown in FIG.

FIG. 5 is a flowchart showing automatic document orientation determination and character recognition processing of the present invention.

FIG. 6 is a diagram showing a region separation state in automatic document orientation determination according to the present invention.

FIG. 7 is a diagram illustrating a process of character recognition processing.

FIG. 8 is a diagram for explaining a document (character) direction automatic determination process of the present invention.

FIG. 9 is a diagram showing a data format of area separation and character recognition information.

FIG. 10 is a diagram showing a display example of an operation panel in the image processing apparatus according to the present invention.

FIG. 11 is a diagram showing a display example of an operation panel in the image processing apparatus according to the present invention.

FIG. 12 is a diagram showing an example of a document for explaining the present invention and a conventional example.

FIG. 13 is a flowchart showing an operation of the image processing apparatus according to the present invention.

[Explanation of symbols]

101 Platen glass 102 Original illumination lamp 103-105 Scanning mirror 106 CCD unit 107 Imaging lens 108 image sensor 109 CCD driver 110 photosensitive drum 112 Pre-exposure lamp 113 Primary charger 117 exposure means 118 developing device 127 Transfer charger 139 Controller section 201 CPU 203 ROM 204 RAM 206 Image processing unit 301 Shading circuit 302 scaling circuit 303 Edge enhancement circuit 304 γ conversion circuit 305 Binarization processing unit 306 Document direction determination unit 307 Synthesis circuit 308 PWM circuit 309 memory control unit 310 Image memory

Claims (4)

[Claims] 1. An image processing apparatus for image-processing image data read by reading means for reading an original image, wherein the character area detecting means detects a character area in the image data, and the character area detecting means detects the character area. Further, a discriminating means for discriminating the direction of a predetermined number of characters in each character area and a document direction discriminating means for discriminating the document direction of the image data according to the discrimination result of each character area of the discriminating means are provided. An image processing device characterized by the above. 2. The image processing apparatus according to claim 1, further comprising setting means for setting the predetermined number of characters. 3. The image processing apparatus according to claim 1, wherein the document orientation discriminating means discriminates the document orientation of the original image by a majority decision of the discrimination results of the respective character areas. 4. The image processing apparatus according to claim 1, wherein the determination unit sequentially performs each character area within a predetermined time.