JPH11331549A - Device and method for processing image - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processing method, with which the directions of all images can be completely and exactly discriminated, and an image processor using that method. SOLUTION: When there is the instruction of an operator, input image data through a shading circuit 301 and a magnification circuit 302 are inputted to an image direction discriminating part 306 and image direction discriminating processing is performed. When the image direction is discriminated, these data are passed through an edge emphasis circuit 303, γ transforming circuit 304, binarizing processing part 305 and synthesizing circuit 307 and afterwards, according to the instruction of the operator, image direction information discriminated by the image direction discriminating part 306 is added to the image data at an image direction information adding part 311. The image data, to which the image direction information is added by at the image direction information adding part 311, are inputted to a PWM circuit 308 in order to transform them to signals showing the emission intensity of a laser and pulse width according to the density of the image is outputted to a laser unit.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing method for determining a character direction in an image, an image processing apparatus using the method, and a storage medium for realizing the method. The present invention relates to a processing device.

[0002]

2. Description of the Related Art Heretofore, as this type of image processing method, there has been known a method of determining whether the image is written vertically or horizontally.

[0003]

However, when reading a plurality of original images successively and recognizing characters on the original images or outputting the read images aligned in a certain direction, it is necessary to read the original image vertically. It is necessary to determine the direction of the character itself, not the distinction between writing and horizontal writing.

Accordingly, the present applicant has filed Japanese Patent Application No. 9-2604.
79, etc., a device has been proposed which determines the direction of characters in an image, recognizes characters based on the direction, and outputs a plurality of images in a fixed direction. For example, it has an image reading unit, detects the document direction of the document image read by the image reading unit, and rotates the image data if the document directions of some of the plurality of documents are different. There is disclosed a digital copying machine having a function of aligning and printing in a predetermined direction.

However, in practice, it is very difficult to completely and accurately determine the direction of the image recorded on the original for all the originals. If there is a document whose image direction is erroneously determined, even if the document is recognized in advance by the operator, it is not possible to designate and read the correct image direction before the determination. .

Therefore, a document whose image direction is erroneously determined cannot be corrected no matter how many times it is read. Furthermore, since the direction of the document image is determined based on the direction of the characters on the image, it is difficult to determine the direction when no characters exist on the image.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems of the prior art. It is an object of the present invention to provide an image processing method and a method capable of completely and accurately determining the direction of any image. It is an object of the present invention to provide an image processing device and a storage medium storing a program code capable of realizing the method.

[0008]

In order to achieve the above object, in an image processing apparatus according to the present invention, there is provided an image input means for inputting image data, and an image direction based on the image data input by the image input means. Image direction determining means for determining, image direction information adding means for adding image direction information determined by the image direction determining means to image data, and output means capable of outputting image data to which the image direction information has been added, And image direction information recognizing means for detecting and recognizing image direction information added to the input image data.

Here, the image direction information recognizing means is capable of recognizing designated image direction information added to an image input by an operator in advance.

The image direction information recognizing means preferentially recognizes the designated image direction information, and when the operator does not add the designated image direction information to the image, the image direction information adding means recognizes the designated image direction information. It is characterized in that the added image direction information is recognized.

On the other hand, in the image processing method according to the present invention, an image direction information detecting step for detecting whether image direction information is added to image data, and an image direction information detected in the image direction information detecting step. Image direction information recognizing step of recognizing the image direction, an image direction determining step of determining an image direction from character data in image data when image direction information is not detected in the image direction information detecting step, and the image direction information recognizing step. Or an image direction information adding step of adding image direction information obtained in the image direction determining step to image data.

Further, in the computer readable memory according to the present invention, a program module of an image direction information detecting step for detecting whether image direction information is added to the image data, and a program module for detecting the image direction information in the image direction information detecting step. A program module for an image direction information recognizing step for recognizing the obtained image direction information, and an image direction determining step for determining an image direction from character data in the image data when the image direction information is not detected in the image direction information detecting step. A program module and a program module for an image direction information adding step of adding image direction information obtained in the image direction information recognizing step or the image direction determining step to image data are stored.

[0013]

Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, unless otherwise specified, the relative arrangement of components, program modules, and the like described in this embodiment, and numerical values such as resolutions are intended to limit the scope of the present invention to them only. Not something.

[Preferred Embodiment] A preferred embodiment of the present invention will be described with reference to FIGS.

FIG. 1 is a cross-sectional view illustrating a schematic configuration of an image processing apparatus according to the present embodiment. Reference numeral 101 denotes an original platen glass on which originals fed from the automatic original 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 document table glass 101. 103,10
Reference numerals 4 and 105 denote scanning mirrors which are housed in an optical scanning unit (not shown) and guide reflected light from the document to the CCD unit 106 while reciprocating. CCD unit 106
Is an imaging lens 1 for imaging the reflected light from the original on the CCD
07, for example, an image sensor 108 including a CCD, a CCD driver 109 for driving the image sensor 108, and the like. The image signal output from the image sensor 108 is converted into, for example, 8-bit digital data and then input to the controller unit 139.

Reference numeral 110 denotes a photosensitive drum;
Is discharged by the pre-exposure lamp in preparation for image formation.
A primary charger 113 charges the photosensitive drum 110 uniformly. Reference numeral 117 denotes an exposure unit which is configured by, for example, a semiconductor laser or the like, and exposes the photosensitive drum 110 based on image data processed by a controller unit 139 which performs image processing and control of the entire apparatus to form an electrostatic latent image. . 11
Reference numeral 8 denotes a developing device which contains a black developer (toner). Reference numeral 119 denotes a pre-transfer charger, which is a photosensitive drum 11
A high pressure is applied before transferring the developed toner image onto the sheet. Reference numerals 120, 122, and 124 denote paper feed units. The transfer paper is fed into the apparatus by driving the paper feed rollers 121, 123, and 125, and temporarily stops at the position where the registration rollers 126 are provided. The writing timing with the formed image is set, and the image is re-fed. 1
A transfer charger 27 transfers the toner image developed on the photosensitive drum 110 to a fed transfer sheet.

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. Reference numeral 129 denotes a transport belt which transports the transfer sheet after the transfer process to the fixing device 130, where the transfer sheet is fixed by, for example, heat. Reference numeral 131 denotes a flapper, which controls the conveyance path of the transfer sheet having undergone the fixing process in one of the directions in which the staple sorter 132 or the intermediate tray 137 is arranged. The paper discharged to the staple sorter 132 is sorted into each bin, and the controller unit 1
The stapling unit 141 performs stapling according to the instruction from 39. Reference numerals 133 to 136 denote feed rollers, which transfer the transfer paper once the fixing process has been completed to the intermediate tray 137.
The sheet is fed inverted (multiple) or non-inverted (both sides). 1
Reference numeral 38 denotes a re-feed roller, which conveys the transfer sheet placed on the intermediate tray 137 again to the position where the registration roller 126 is provided.

The controller unit 139 includes a microcomputer, an image processing unit, and the like, which will be described later. According to an instruction from the operation panel 140, the controller 139 controls the entire apparatus and performs an image forming operation as described above.

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

Reference numeral 201 denotes C for controlling the entire image processing apparatus.
It is a PU, and sequentially reads and executes programs from a read-only memory 203 (ROM) that stores a control procedure (control program) of the apparatus main body. An address bus and a data bus of the CPU 201 are a bus driver circuit of the CPU 202,
It is connected to each load via an address decoder circuit.
Reference numeral 204 denotes a random access memory (RAM) which is a main storage device used as storage for input data, a work storage area, and the like. Reference numeral 205 denotes an I / O interface, which is an operation panel for displaying the status of the apparatus using liquid crystal and LEDs by performing key input by an operator, and an operation panel 140 and motors for driving a paper feed system, a transport system, and an optical system. 207, clutches 208, solenoids 209, and paper load sensors 210 for detecting the paper being conveyed. The developing device 118 is provided with a residual toner detection sensor 211 for detecting the amount of toner in the developing device, and an output signal thereof is input to the I / O port 205. A high-voltage unit 215 outputs a high voltage to the primary charger 113, the developing unit 118, the pre-transfer charger 119, the transfer charger 127, and the separation charger 128 according to an instruction from the CPU.

An image processing unit 206 receives an image signal output from the CCD unit 106, performs image processing described later, and outputs a control signal for the laser unit 117 in accordance with image data. The laser beam output from the laser unit 117 irradiates and exposes the photosensitive drum 110, and at the same time, the light emission state is detected by a beam detection sensor 213 which is a light receiving sensor in a non-image area. 205.

FIG. 3 is a block diagram of the image processing section 206 in the controller section 139 in the image processing apparatus according to the present embodiment.

The image signal converted into an electric signal by the CCD 108 is first corrected for variations between pixels by a shading circuit 301, and then subjected to a data thinning process at the time of reduction copying at a magnification circuit 302 to enlarge the data. During copying, data interpolation is performed. Next, in the edge enhancement circuit 303, second differentiation is performed in, for example, a 5 × 5 window to enhance the edges 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 the image data into density data to be output to a printer. The image data converted into the density data is input to a binarization processing unit 305. Here, for example, the multi-value data is converted into 2
Convert to value data. The image data converted to binary is 3
07 is input to the combining circuit. The synthesizing circuit 307 selectively outputs the input image data and the image data in the image memory 310 including, for example, a DRAM or a hard disk. The read / write control for the image memory 310 is performed by the memory control unit 309, and when the image is rotated, the read address of the image data in the memory is controlled.

Next, in the image direction information adding section 311, the image direction information is added to the image data in accordance with the instruction of the operator. The image data to which the image direction information has been added by the image direction information adding unit 311 is input to the PWM circuit 308 for conversion into a signal of the laser emission intensity, and the pulse width according to the image density is output to the laser unit. Is done.

On the other hand, the image output from the scaling circuit 302 is
When there is an instruction from the operator, the instruction is input to the image direction determination unit 306, and an image direction determination process described later is performed.

FIG. 4 is a block diagram of the image direction judging section 306.

When the operator gives an instruction to determine the image direction, the image data output from the scaling unit 302 is
The data is input to the PU / memory unit 401. The CPU / memory unit 401 temporarily stores image data and performs various controls. CPU 201 in controller unit 139
Are connected by a bus, for example, via a dual port RAM (not shown), and transmit and receive data. Of course, serial communication may be used.

The character recognition / direction determination unit 402 focuses on the fact that the direction of an image is most accurately represented by a character, and identifies several types of character areas in the image as 0 °, 90 °, and 180 °.
The character recognition is performed from the directions of 270 ° and 270 °, and the direction with the highest accuracy among the character recognition accuracy (the reliability of character recognition: the distance to the characteristic distribution of the character) in each direction is set as the image direction.

As a pre-process for performing character recognition / direction determination processing and the like by the character recognition / direction determination unit 402, a region separation unit 403 converts a character portion, a graphic portion, a natural image portion, a table portion, and the like into a rectangular shape from image data. This is a block for performing a process of loading the attributes (such as a character portion) of each area by dividing the area into areas.

The image direction information reading unit 407 determines whether information indicating the image direction, such as the image direction information added by the image direction information adding unit 311 in FIG. 3, is added to the document, and the information is added. In this case, the block is for reading the image direction information.

Detailed processing in each of the character recognition / direction determination section 402, the area separation section 403, and the image direction information reading section 407 will be described later.

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 results, character recognition results, etc.). The I / F unit 405 is
It is composed of SCSI, RS232C, etc., and is provided for transmitting data to the outside. Computer 4
Reference numeral 06 is used to read information stored in the storage device 404 via the I / F unit 405 or to process image data obtained by reading data from a storage medium such as a magneto-optical disk. .

Next, the outline of the automatic image direction determination processing in the image processing apparatus according to the present embodiment will be described with reference to the flowcharts of FIGS.

When the copy key is pressed (S51), the original on the original platen 101 or the original fed from the automatic original feeder 142 is read and scanned by the CCD (S5).
2) The read image data is stored in the memory (S)
53). At this time, the image direction data of 0 ° is stored in association with the image data. At the same time, it is determined whether or not the image direction needs to be determined (S54). If the image direction needs to be determined, the image data is searched (S55) to determine whether or not the image direction information has been added. A determination is made (S56). If the image direction information is not added, the direction of the image is determined by normal character recognition (S
57). When the image Otorioka information is added to the original image, the direction of the image is determined from the image direction information (S5).
8). When the image direction is determined in step S57 or step S58, the image direction data is rewritten according to the determined result (S59). Here, it is assumed that the direction of the input image is one of 0 °, 90 °, 180 °, and 270 °, and data indicating which direction the input image corresponds to is written.

Next, image data is read from the memory for printing (S60). If it is determined in S54 that it is not necessary to determine the image direction, steps S55 to S59 are cut, and the process proceeds to the image data reading step (S60).

Further, it is determined whether or not to print the image direction determination result on a copy (recording paper) (S62). If the print mode is a mode in which the image direction information is added, the image direction information is added to the bitmap image data (print data) for printing (S63), and the laser unit 117 is operated based on the added print data. Is driven, and the image with the image direction information is transferred to the recording paper (S64). On the other hand, when the determination result of the image direction is not printed on the copy,
The print data is directly transferred to recording paper.

FIG. 7 is a flowchart showing in detail the image direction determining process based on the character recognition performed in step S57 of FIG.

First, when it is determined in step S56 of FIG. 5 that the image direction information does not exist in the image data, the shading circuit 301 converts the multi-valued image data in step S1.
Enter from. In step S2, the image represented by the input image data is converted into a character part,
Separates into rectangular areas according to the type such as graphic part, natural image part, and table part, and adds attributes (information indicating image types such as character part, graphic part, natural image part, and table part) to the separated area. I do. In practice, this is done by creating attribute information for the area enclosed by the rectangle.

The area separation processing by the area separation unit 403 is executed as follows. First, black pixels are detected while scanning image data, and a rectangular area including the black pixels is created based on the continuity or discontinuity of the black pixels using a contour tracing or labeling method. I do. Next, based on the black pixel density included in the rectangular area, the presence or absence of an adjacent rectangular area, the aspect ratio of the rectangle, and the like, the area is a character part (title, body, caption, etc.) or a graphic part. It is determined whether the image is a natural image part, a front part, or the like. The rectangular area of the character area is determined based on the processing result.

Next, in step S3, rectangle information of a region having an attribute as a character portion is extracted based on the added attribute. Here, the character part is a text part, a title part,
Includes characters in tables, captions in figures, etc.

FIG. 8 is a view showing a document image placed and read on the document table glass 101 in various directions. For example, in the case of a document image read in the directions shown in FIGS. 8A and 8C, FIGS.
Rectangular information including a character portion as shown in (d) is extracted. Then, in step S4, using a block of a rectangular area having attributes of some character portions in these,
Perform character recognition processing.

In this embodiment, a feature vector extraction and comparison method are used for character recognition processing. In the following description, FIG.
It is assumed that a rectangular area including a character portion as shown in (d) is extracted.

FIG. 9 is a diagram showing each step of the character recognition process according to this method.

For example, as shown in FIG.
It is assumed that the character area 71 including the character is determined. As a first stage, a character segmentation process is performed on the character area 71 as shown in FIG. This is a process of cutting out a rectangle including one character and detecting and obtaining a state of black pixel continuity. Next, as a second stage, as shown in FIG. 9C, one character is cut out as a pixel block of m × n (for example, 64 × 64 pixels). And among them, Figure 9
Using a 3 × 3 pixel window as shown in (d),
The distribution direction of black pixels is extracted. The distribution direction extracted by this is called direction vector information. FIG. 9 (d)
Exemplifies a part of the direction vector information.

A window of 3.times.3 pixels is placed on a pixel block, and the window is shifted vertically and horizontally to obtain several tens of direction vector information from characters included in the pixel block. This vector information is a character feature. By comparing this feature vector with the contents of a character recognition dictionary stored in advance, characters are extracted in order from the character whose feature is closest to the feature vector. In this case, the first candidate, the second candidate,... The closeness of the feature to this feature vector indicates the closeness of the distance to the character,
That is, it is a quantified numerical value of the character recognition reliability.

In this way, the reliability of each character by character recognition is obtained.

Next, the process proceeds to step S5, and the rectangular area including the character portion is rotated clockwise by 90 ° based on a known technique. Further, in step S6, the character recognition processing is performed from four directions, that is, the direction in which the character recognition is first performed is set to 0 °, and 90 °, 180 °,
It is rotated by 70 °, and it is checked whether the character recognition processing has been performed in each direction. If it is determined that the processing from the four directions has not been completed, the process returns to step S4 to continue the character recognition processing, but determines that the character recognition processing from the four directions has been completed. For example, the process proceeds to step S7, and determines the character (document) direction based on the reliability obtained from the character recognition process.

FIG. 10 is a diagram for explaining the character direction determination process. Here, description will be made using a sentence example of “name of the present invention” described in the rectangular area 71 shown in FIG.

FIG. 10A shows a character string when character recognition is first performed, and FIG. 10B shows a character string obtained by rotating the character string shown in FIG. Is shown. Focusing on the character "book" in such a character string, when determining the character direction, as shown in FIG.
Consider the results of character recognition performed from four directions of °, 180 °, and 270 °. The character recognition result in each direction is
As shown in FIG. 10C, they are different from each other. Note that the character recognition result and the reliability shown in FIG. 10C are provisional results and values for explanation, and are not necessarily the same as actually.

As shown in FIG. 10C, when character recognition is performed from the direction of 0 °, the recognized character is "book" and the reliability is also a high value of "0.90". Next, when character recognition is performed from the direction in which the character string is rotated by 90 °,
The recognition character is "town", and its reliability is also reduced to "0.40". The reason why the erroneous recognition occurs and the reliability decreases is that character recognition is performed based on a feature vector obtained from a rotated character string. Similarly, when character recognition is performed from directions in which the character string is rotated by 180 ° and 270 °, the recognized characters are “「 ”and“ expression ”, and their reliability is“ 0.30 ”and“ 0.50 ”. ", Erroneous recognition occurs and its reliability is low. In addition, regarding such character recognition processing, the difference in the degree of reliability for each direction becomes more noticeable as the characters are more complicated.

As is clear from the results shown in FIG. 10C, the reliability obtained from the first character recognition result is the highest, so that the read image is oriented in the direction shown in FIG. It is determined that it is likely to be suitable. In addition,
In this embodiment, in order to improve the accuracy of character direction determination, character recognition is performed from four directions for a plurality of characters in the same rectangular area, and the direction of the image is comprehensively determined from the character recognition results.

Further, when the character direction is determined from one rectangular area, the character direction may be erroneously determined for a special character string. Therefore, similar character recognition is performed for a plurality of rectangular areas, and for each rectangular area. , The average value of the reliability in each of the four directions for each character is calculated, and the average value of the reliability in each of the four directions in each rectangular area is calculated. Direction). Alternatively, a threshold value of the reliability may be determined, and when a certain threshold value (for example, 0.9) is exceeded, character recognition from the Tano direction may not be performed.

As described above, a character (image) is determined by determining a plurality of characters in the same rectangular area and a character direction based on the degree of confidence of the plurality of rectangular areas without determining the character direction based on the reliability of only one character. ) It is possible to determine the direction with high accuracy. However, the character direction may be determined based on the reliability of only one character, or the character direction may be determined based on the reliability of a plurality of characters in the same rectangular area. Edit information on the determined image direction and character recognition result.

FIG. 11 is a diagram showing edit data obtained from the image direction determination processing described above.

Here, FIG. 11A shows the original image data, FIG. 11B shows the segmentation data, and FIG.
(C) shows character recognition information.

As shown in FIG. 11B, the area separation data is "head" indicating that the area separation data is area separation data.
r ”and the identifiers of the separated areas“ rect1 ”to“ re
ctn4 ”, and information of each area (block) distinguished by this identifier includes a block number“ orde
r ", block attributes (character part, figure part, etc.)" ar
t ", coordinate values" x1 "and" y "at the upper left of the block
1, "width" of the block, "h" of the block, "direction" indicating vertical writing or horizontal writing, "selfID" which is the ID of the block, and ID of a parent block including the block. "UpperI
D ", an attribute" upperArt "of the parent block, and a reserved area" reserve ".

As shown in FIG. 11 (c), the character recognition information is "head" indicating that the character recognition information is character recognition information.
r ", for example, character recognition information" OCR1 "relating to a single character such as" book ", and" b1k head "corresponding to" rect "indicating a block including the character.
r ".

Then, "OCR1", "OCR2" ...
The character recognition information of “OCRn” includes “type” indicating whether the character is a character or a blank, and first to fifth candidate characters “character 1” to “character 1” according to the reliability obtained from the character recognition result.
It is composed of “character 5”, the cut-out positions “x1” and “y1” of the character, the width “w” of the character, the height “h” of the character, and the reserve area “reserve”.

This processing result is output to the interface (I /
F) transmitted to the computer 406 via the unit 405,
It can also be used with filing application software on the computer 406.

FIGS. 12 and 13 are diagrams showing a judgment block as an example of specific image direction information.

At the time of output, the image direction information is printed on the lower right portion of the recording paper.

The image direction information is composed of eight blocks, and the four on the left side show the results of the image direction determination performed when the image direction information was output.

The four blocks on the right side are used to make corrections when the operator is dissatisfied with the determination result of the image direction.

FIG. 13 is an enlarged view of the judgment block. The four blocks on the left indicate the result of document detection, and the four blocks on the right are correction blocks. 0 ° from above, 90
°, 180 °, and 270 ° blocks, and the black blocks are the determination results. That is, this is the determination direction when the document is viewed such that the determination block is located at the lower right of the sheet.

Therefore, in the example of FIG. 13A, the uppermost block on the left is painted black, so that the judgment result of this document is 0 °. When the operator corrects the determination result, the determination angle of the right adaptive block is painted black. In the example of FIG. 13B, since the lower right block is painted, it is determined to be 270 °.

Next, referring to FIG. 14, step S5 in FIG.
4, a method of searching and recognizing image direction information performed in S55 will be described.

In the determination block as shown in FIG. 13, the upper left coordinates “x1, y1”, the block width “w”, the block height “h”, and the like are determined in advance. It is recognized whether the block indicates the determination result.

If it is set in advance that such a determination block is recorded at the lower right of the sheet, the relationship between the determination block and the sheet is determined when the document is read and the image direction information is searched. As shown in (a), (b), (c), and (d), there are four types, and it is only necessary to recognize a determination block when the positional relationship, the size, and the like are satisfied.

Next, regarding the determination of the image direction, if the upper left coordinates "x1" and "y1" of the block, the block width "w", and the block height "h" are known, eight blocks are determined. The range of (the block indicating the four determination results and the four correction blocks) is naturally determined. Then, it is first determined from the data of the four correction blocks whether the determination result has been corrected. When the correction is detected, the data is set in the image direction information adding unit 311.

When it is determined that no correction has been made, the data of the block indicating the determination result is read in the same manner. Then, the result is set in the image direction information adding unit 311.

In the case of judging the image direction from the judgment block, the point to be referred to when judging which block of the eight blocks is filled is not one point in the block but each block. It is only necessary to refer to whether or not black dots exist at a plurality of points within. And
Blocks with black dots at more points
If it is determined that the block is the block to which the determination information is added, it is possible to avoid a reading error in the image direction from the determination block.

FIG. 15 is a flowchart showing in detail the image direction judging process by reading the image direction information, which is performed in step S58 of FIG. Here, as an example, a process for reading a document to which image direction information is added as shown in FIG. 12 is shown.

When the determination block as shown in FIG. 13 is extracted from the image data, first, whether any of the four blocks on the right is not painted black, that is, whether or not the image direction is specified by the operator. It is determined (S150
1). If there is a designation, the image direction is determined according to the designation (S1502), and the image direction data as specified is output (S1503). If not specified,
Since the previous determination is correct, the previous determination result is used as the determination for the document (S1504). And
The same image direction data as the previous determination result is output (S
1503).

The data thus determined is set in the image direction information adding section 311 and is added to the read document image as a result of the determination to form an image on an output sheet.

FIG. 16 is a block diagram showing the configuration of the image direction information adding section 311 in the present embodiment.

First, based on the image direction data, the CPU
Generates print data of the determination block. When “0” is input as a data switching signal, the memory 161 enters the write mode, and at the same time, the selector 162
Selects the CPU address and the gate 163 is opened, so that the data bus and address bus of the CPU become valid, and the determination block print data (bitmap data)
Is written to the memory 161.

The data to be written into the memory has, for example, the contents shown in FIG. That is, it is composed of two-dimensional coordinates of lower address coordinates and upper address coordinates. In this configuration, 0 to 96 of the lower 8 bits and 0 of the upper 8 bits are set.
To 128 are output. Data "1" is written in a portion output in black, and data "0" is written in a portion output in white. Data “1” is always written in the frame portion. According to the determination result, lower addresses 1 to 47 and upper addresses 1 to 31, 33
To 63, 65 to 95, or 97 to 127, “1” is written.

Next, when "1" is input as a data switching signal and the memory 161 enters the read mode, the selector 162 inputs an address from the address controller 164, and the determination block from the memory 161 according to the address from the address controller 164. Read the print data. The determination block print data read from the memory 161 is input to the selector 165. The image data output from the synthesizing circuit 307 in FIG. 3 is also input to the selector 165 according to the address from the address controller 164. By selecting the print data or the image data of the determination block by the selector 165 based on the address of the address controller 164, the determination block is preferentially printed on a part of the recording paper (here, the lower right).

In this way, if the determined image direction is added to the copy and output, the operator can immediately recognize the determination result just by looking at the copy.

When the operator wants to correct the determined result, the determination correction column corresponding to the direction in which the determination is desired may be painted black as described above.

Further, before the operator performs the document detection function, the judgment is made by writing eight blocks in the designated place with a pen or the like, and painting the blocks in the designated direction.
From the beginning, copying, recognition, and the like of an image can be performed according to the designated image direction.

In the present embodiment, the judgment block composed of eight blocks has been described as the image direction information. However, this judgment block is merely an example, and indicates the judged image direction and the designated image direction. Any other form may be used.

Further, in the present embodiment, the image direction is determined from the four directions of 0 °, 90 °, 180 °, and 270 °.
Also, by changing the form of the image direction information, it is possible to easily determine another angle (such as 45 °).

(Other Embodiments) Even if the present invention is applied to a system including a plurality of devices (for example, a host computer, an interface device, a reader, a printer, etc.), an apparatus (one device) For example, the present invention may be applied to a copying machine, a facsimile machine, and the like.

Further, an object of the present invention is to supply a storage medium storing a program code of software for realizing the functions of the above-described embodiments to a system or an apparatus, and to provide a computer (or CPU) of the system or the apparatus.
And MPU) read and execute the program code stored in the storage medium.

In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiment, and the storage medium storing the program code constitutes the present invention.

As a storage medium for supplying the program code, for example, a floppy disk, hard disk, optical disk, magneto-optical disk, CD-ROM, CD
-R, a magnetic tape, a nonvolatile memory card, a ROM, or the like can be used.

When the computer executes the readout program code, not only the functions of the above-described embodiment are realized, but also the OS (Operating System) running on the computer based on the instruction of the program code. ) May perform some or all of the actual processing, and the processing may realize the functions of the above-described embodiments.

Further, after the program code read from the storage medium is written into a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer, based on the instructions of the program code, It goes without saying that the CPU included in the function expansion board or the function expansion unit performs part or all of the actual processing, and the processing realizes the functions of the above-described embodiments.

When the present invention is applied to the storage medium, the storage medium stores program codes corresponding to the flowcharts described above. Among them, at least, an "image direction information detection module" that detects whether image direction information is added to image data, and an "image direction information recognition module" that recognizes image direction information detected in the image direction information detection step. An image direction determining module that determines the direction of an image from character data in image data when image direction information is not detected in the image direction information detecting step; and the image direction information recognizing step or the image direction determining step. It is sufficient to store the program code of each module of “image direction information adding module” for adding the image direction information obtained by the above to the image data in the storage medium.

When the present invention is realized by such a program code, the above-described modules are stored in the storage device 404 of FIG. You can add

[0092]

As described above, according to the present invention, since the image direction information can be added to the output image, the operator can immediately recognize the determined direction. Further, by adding image direction information different from the image direction automatically determined by the apparatus, the image input can be performed by designating the image direction. Accordingly, it is possible to provide an image processing method capable of completely accurately determining the direction of any image, an image processing apparatus using the method, and a storage medium storing a program code capable of realizing the method.

[0093]

[Brief description of the drawings]

FIG. 1 is a cross-sectional view illustrating a schematic configuration of an image processing apparatus according to a preferred embodiment of the present invention.

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

FIG. 3 is a block diagram of an image processing unit 206 in a controller unit 139 in the image processing device according to the preferred embodiment of the present invention.

FIG. 4 is a block diagram of an image direction determination unit 306 in the image processing apparatus according to the preferred embodiment of the present invention.

FIG. 5 is a flowchart illustrating an outline of an image direction automatic determination process in the image processing apparatus according to the preferred embodiment of the present invention.

FIG. 6 is a flowchart illustrating an outline of an image direction automatic determination process in the image processing apparatus according to the preferred embodiment of the present invention.

FIG. 7 is a flowchart showing in detail an image direction determination process based on character recognition, which is performed in step S57 of FIG.

FIG. 8 is a diagram illustrating an image document placed on a document table glass 101 in various directions and read.

FIG. 9 is a diagram showing each process of a character recognition process.

FIG. 10 is a diagram illustrating a character direction determination process.

FIG. 11 is a diagram showing edit data obtained from the image direction determination processing.

FIG. 12 is a diagram illustrating a determination block as an example of image direction information according to a preferred embodiment of the present invention.

FIG. 13 is an enlarged view of a determination block as an example of image direction information according to the preferred embodiment of the present invention.

FIG. 14 is a diagram illustrating recognition of a determination block as an example of image direction information according to a preferred embodiment of the present invention.

FIG. 15 is a flowchart showing in detail an image direction determination process by reading image direction information, which is performed in step S58 of FIG. 5;

FIG. 16 is a block diagram showing a configuration of an image direction information adding unit according to a preferred embodiment of the present invention.

17 is a diagram showing a relationship between addresses and data in a memory 161 in FIG.

Claims (5)

[Claims] An image input unit for inputting image data; an image direction determining unit for determining an image direction from the image data input by the image input unit; and an image direction information determined by the image direction determining unit. Image direction information adding means for adding image direction information; output means capable of outputting image data to which the image direction information is added; image direction information recognition for detecting and recognizing image direction information added to input image data Means, and an image processing apparatus comprising: 2. An image processing apparatus according to claim 1, wherein said image direction information recognizing means is capable of recognizing designated image direction information added to an image input by an operator in advance. . 3. The image direction information recognizing means preferentially recognizes the designated image direction information, and when the operator does not add the designated image direction information to an image, the image direction information adding means recognizes the designated image direction information. The image processing apparatus according to claim 2, wherein the added image direction information is recognized. 4. An image direction information detecting step for detecting whether image direction information is added to the image data; an image direction information recognizing step for recognizing the image direction information detected in the image direction information detecting step; An image direction determining step of determining an image direction from character data in the image data when image direction information is not detected in the image direction information detecting step; and an image obtained by the image direction information recognizing step or the image direction determining step. An image direction information adding step of adding direction information to image data. 5. A program module for an image direction information detecting step for detecting whether image direction information is added to image data, and an image direction information recognizing step for recognizing the image direction information detected in the image direction information detecting step. A program module of an image direction determining step of determining an image direction from character data in the image data when image direction information is not detected in the image direction information detecting step; and And a program module for an image direction information adding step of adding image direction information obtained in the image direction determining step to image data.