JPH10117281A - Image-forming method and device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To form a necessary image by detecting the direction of an original image, based on the confidence degree of character recognition when the original image is inputted and an image is formed on a recording member and then deciding the image direction based on the decision degree of the direction of the original image. SOLUTION: An original is scanned on the platen glass, and the original image data are inputted to an electronic sorter part 203 and an image direction detection part 210. The part 203 binarizes the image data and stores them in a memory. Then the part 210 decides and stores the direction of the original image and the degree of confidence. When the confidence degree can be decided for the direction of the original image, a status flag is set and an image is formed after the image rotation processing, etc. If the confidence degree cannot be decided, it is decided whether or not the read original is the final one. If the original is not final, the same operation is repeated until the final original is read. If it is the final one, the operation returns to the next original image.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to an image forming method and apparatus for inputting a document image and forming an image on a recording material.

[0002]

2. Description of the Related Art Conventionally, in an image forming apparatus such as a copying machine, an image is formed on a recording sheet in a direction in which an original image is read. For this reason, if the document bundle contains a mixture of horizontally or vertically written documents, or if the image direction of the document bundle is not aligned, the output bundle also has a non-uniform direction. This, especially with the development of post-processing mechanisms such as bookbinding,
It is becoming an important issue.

[0003] Therefore, it has been proposed to use a character recognition technique to recognize the original image direction and to align the directions of the output images. The technique of recognizing the original image direction is an application of the technique used in the information processing apparatus. But,
In the information processing apparatus, character recognition is performed by selecting character candidates based on a feature when the character is oriented in the forward direction. Therefore, when image data rotated by 90 ° or 180 ° is read, character recognition is correctly performed. In some cases, completely different character codes were output. For example,
In the case of the character "high" shown in FIG. 14, when the character is oriented in the positive direction, as shown in FIG.
However, as shown in FIG.
It is erroneously recognized as “strike” at 0 ° rotation, and as shown in FIG.
It is erroneously recognized as a “character” by 180 ° rotation, and further becomes unrecognizable by 90 ° rotation as shown in FIG.
This recognition result is merely for convenience of explanation and differs from the actual result.)

Therefore, in order to correctly perform character recognition, if the direction of the document is not correct, the direction of the document is manually adjusted, and the document is read again and character recognition is performed again. However, since the processing speed of the scanner has been improved and an automatic document feeder function called an auto feeder has begun to be attached, the processing of a large number of documents has been increasing, and it is difficult to manually correct the direction of the document one by one. It has become The format of the manuscript document is expressed by various patterns such as vertical writing and horizontal writing. That is, an A4 portrait document is written horizontally (see (a) in FIG. 11: often used in a Japanese horizontally written document or an English document), and an A4 landscape document is written horizontally ((b) shown in FIG. 11). Reference: A document having a long sentence, a document for OHP, a document such as A3 or B4 is often used in a reduced copy mode, or a horizontally written document in which A4 is placed horizontally and the column is switched in the middle (see FIG. 11). (See (c) shown: Often used when two A4 documents are successively reduced and copied), and various patterns such as a vertically written A4 document (see (d) shown in FIG. 11).

On the other hand, the direction of the image displayed on the monitor is
It depends on the scanning direction (image reading direction) of the scanner when inputting an image. For this reason, when the document is read in a posture in which the scanning direction of the scanner and the direction of the character string of the document match, the document is displayed in the original posture as shown in FIG. However, in the case of the A4 scanner, since the direction of the document is uniquely determined, the scanning direction of the scanner does not match the direction of the character string of the document.
For example, as shown in FIG. 12B, the character string of the document is displayed in a state rotated by 90 ° from the original posture, and there are cases where it becomes very difficult to read.

In order to eliminate the erroneous recognition of characters and the difficulty of reading on a monitor as described above, information processing apparatuses having a document image direction automatic discrimination / rotation function have been conventionally proposed.
As shown in FIG. 13, a typical conventional automatic document image direction determination method is to look at the directionality of a line having a table based on the result of area separation and to use a long line in the horizontal direction to write a character. A method of determining the direction in which the area is divided (see “a” in FIG. 13A) as the direction of the document image, detecting the projection (histogram) in the vertical and horizontal directions of the document, Judgment can be made by checking the degree of delimitation (see “b” in (b) of FIG. 13), or a feature such as a horizontal or vertical length of a rectangular area that is separated from the area and matches the characteristic of the character area (see FIG. b) "c"). Then, the document image is rotated based on the document image direction determined by these methods, and character recognition is performed on the rotated image. In particular, the expectation of correct character recognition based on the document direction has been increasing in recent years with the application of electronic filing for organizing a large number of documents, the development of DTP, and the development of devices for processing a large amount of documents such as copying machines. There is a growing trend and more accurate recognition techniques have been proposed.

[0007]

However, in the above-described conventional example, the information processing apparatus detects the direction of the original image using character recognition, and automatically rotates the image to adjust the image direction or change the staple direction. Although it is controlled, for example, if there is a document such as a column or figure, character recognition can not be performed accurately, false detection of the document image direction is caused by various documents, and copying that is not intended by the operator is performed There was a problem.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and is to set a predetermined image forming process for a direction detection result of a document image to form an image intended by an operator. It is an object to provide a method and an apparatus.

[0009]

In order to achieve the above object, the present invention relates to an image forming apparatus for inputting a document image and forming an image on a recording material, wherein the image direction of the document image is detected. The image processing apparatus further includes a detection unit, and a control unit that performs control to perform a predetermined image forming process according to a detection result of the image direction detection unit.

According to another aspect of the present invention, there is provided an image forming method for inputting a document image and forming an image on a recording material, the method comprising: detecting an image direction of the document image; A control step of performing control so as to perform a predetermined image forming process in accordance with a detection result in the image direction detecting step.

[0011]

Embodiments of the present invention will be described below in detail with reference to the drawings.

FIG. 1 is a sectional view showing the structure of the image forming apparatus according to the present embodiment. In the figure, reference numeral 100 denotes a copying machine main body, and 180 denotes a circulating automatic document feeder (RD).
F). Reference numeral 101 denotes a platen glass as a document mounting table; 102, a scanner; a document illumination lamp 103;
It is constituted by a scanning mirror 104 and the like. Scanner 102
Is reciprocally scanned in a predetermined direction by a motor (not shown), whereby the reflected light of the original is transmitted through the lens 108 via the scanning mirrors 104 to 106 to form an image on the CCD sensor 109. An exposure control unit 120 includes a laser, a polygon scanner, and the like. The exposure control unit 120 converts the laser light 129 converted into an electric signal by the image sensor unit 109 and modulated based on an image signal subjected to predetermined image processing described later. Irradiates the photosensitive drum 110. Around the photosensitive drum 110, a primary charger 112, a developing device 121, a transfer charger 11
8. Cleaning device 116 and pre-exposure lamp 114
Is arranged. In the image forming unit 126, the photoconductor drum 110 is rotated in a direction indicated by an arrow by a motor (not shown), and is charged to a desired potential by the primary charger 112. Light 12
9 is irradiated to form an electrostatic latent image. Photoconductor drum 1
The electrostatic latent image formed on the developing device 10 is developed by the developing device 121 and is visualized as a toner image.

On the other hand, the transfer paper fed from the upper cassette 131 or the lower cassette 132 by the pickup rollers 133 and 134 is sent to the main body by the feed rollers 135 and 136, and is fed to the transfer belt by the registration rollers 137. The visualized toner image is transferred to the transfer charger 11.
The image is transferred to the transfer paper by 8. Photoreceptor drum 1 after transfer
In 10, residual toner is cleaned by a cleaner device 116 and residual charges are erased by a pre-exposure lamp 114.
The transfer paper after the transfer is separated from the transfer belt 130, the toner image is recharged by the pre-fixing chargers 139 and 140, sent to the fixing device 141, and fixed by pressurizing and heating.
The sheet is discharged out of the main body 100 by the discharge roller 142.

Reference numeral 119 denotes an attraction charger for attracting the transfer paper sent from the registration roller 137 to the transfer belt 130. Reference numeral 138 is used to rotate the transfer belt 130 and, at the same time, forms a pair with the attraction charger 119. Transfer belt 13
This is a transfer belt roller that attracts and charges the transfer paper to zero.
Further, the main body 100 is provided with a deck 150 capable of storing, for example, 4000 transfer papers. Deck 150
Lifter 151 rises according to the amount of transfer paper so that the transfer paper always contacts the paper feed roller 152. In addition, 100
A multi-bypass 153 is provided, which can hold a sheet of transfer paper.

On the other hand, reference numeral 154 denotes a paper discharge flapper, which switches the path between the double-side recording side or the multiple recording side and the paper discharge side.
The transfer paper fed from the paper discharge roller 142 is switched by the paper discharge flapper 154 to a double-sided recording side or a multiple recording side. A lower conveyance path 158 turns the transfer sheet sent out from the sheet discharge roller 142 through the reversing path 155 and guides the transfer sheet to the re-feed tray 156. 1
Numeral 57 denotes a multiplex flapper for switching the path between double-sided recording and multiplex recording. By inverting the flapper to the left, the transfer paper is guided directly to the lower transport path 158 without passing through the reversing path 155. Reference numeral 159 denotes a transfer sheet through the path 160 to the image forming unit 1.
A paper feed roller for feeding paper to the 26 side.

A discharge roller 161 is disposed near the discharge flapper 154 and discharges the transfer paper switched to the discharge side by the discharge flapper 154 outside the apparatus. During double-sided recording (double-sided copying) or multiple recording (multiple copying), the discharge flapper 154 is raised upward, and the copied transfer paper is stored in the re-feed tray 156 via the transport paths 155 and 158. At this time, the multiplex flapper 157 is tilted to the right during double-sided recording, and the multiplex flapper 15
Tilt 7 to the left. The transfer paper stored in the re-feed tray 156 is guided to the registration roller 137 of the main body via the path 160 by the paper feed roller 159 one by one from below.

When the transfer paper is to be inverted and discharged from the main body, the discharge flapper 154 is raised upward, and the flapper 1 is discharged.
57 to the right and transport the copied transfer paper to transport path 15
5 and the rear end of the transfer paper is
, The sheet is conveyed to the second feed roller side by the reversing roller 163, and the transfer sheet is turned over by the discharge roller 161 and discharged out of the apparatus.

FIG. 16 is a diagram showing the configuration of the operation unit according to this embodiment. In the figure, reference numeral 451 denotes a numeric keypad, which is used for inputting the number of sheets and numerical value for mode setting during image formation. A clear / stop key 452 is used to clear the set number of images to be formed and to stop the image forming operation. Reference numeral 453 denotes a reset key for returning the set number of image formations and the operation mode to the specified values. A start key 454 starts an image forming operation when the key is pressed. Reference numeral 469 denotes a display panel composed of a liquid crystal or the like, and the display content changes according to the setting mode in order to facilitate detailed mode setting. In the present embodiment, the display panel 4 is operated by using the cursor keys 465 to 468.
The cursor 69 is moved, and the setting is determined by the OK key 464. Note that the setting method is not limited to this. For example, the touch panel may be configured by a touch panel and set.

Reference numeral 471 denotes a paper type setting key which is set when an image is formed on a recording material thicker than the standard. When the thick paper mode is set by the paper type setting key 471, the LED 47
Control is performed so that 0 lights up. In the present embodiment, only the thick paper mode can be set. However, the function can be extended so that a mode for OHP or other special paper can be set as necessary. A double-sided mode setting key 475 is, for example, a “single-sided mode” for performing single-sided output from a single-sided original, a “single-sided mode” for performing double-sided output from a single-sided original, and a “double-sided mode” for performing double-sided output from a double-sided original. "
It is possible to set four types of two-sided modes, that is, a "two-sided mode" for outputting two single-sided originals from a two-sided original. LED472
To 474 are turned on in accordance with the set double-sided mode, and in the “single-single mode”, all the LEDs 472 to 474 are turned off,
In the “single-both mode”, only the LED 472 is turned on, and the “both-both mode”
In the “both mode”, only the LED 473 is turned on, and in the “both-single mode”, only the LED 474 is turned on.

FIG. 2 is a block diagram showing a control system of the image forming apparatus according to this embodiment. In FIG.
Reference numeral 1 denotes an image reading unit, which includes a CCD sensor 109, an analog signal processing unit 202, and the like. CCD sensor 109 via lens 108 in image reading unit 201
Is converted into an analog electric signal by the CCD sensor 109. Then, the converted image information is input to the analog signal processing unit 202 and subjected to analog-to-digital conversion (A / D conversion) after performing sample-and-hold, dark level correction and the like. The digitized signal is subjected to shading correction (variation of the sensor for reading the original and correction of the light distribution characteristic of the original illumination lamp) and scaling processing, and then input to the electronic sorter unit 203 and the image direction detecting unit 210. Is done. Image direction detector 210
Will be further described later.

209 is an external interface (I / F)
The processing unit develops image information input from an external computer and inputs the image information to the electronic sorter unit 203 as image data. The electronic sorter unit 203 performs necessary correction processing in an output system such as gamma (γ) correction, smoothing processing, edge enhancement, other processing and processing, and outputs the result to the printer unit 204. The printer unit 204 includes an exposure control unit 120 composed of a laser or the like described with reference to the cross-sectional view of FIG. 1, an image forming unit 126, a transfer paper transfer control unit, and the like, and records an image on the transfer paper based on an input image signal. I do. Further, the CPU circuit unit 205 includes the CPU 206 and the RO
An M207, a RAM 208, and the like control the image reading unit 201, the electronic sorter unit 203, the printer unit 204, and the like, and totally control the sequence of the present apparatus.

FIG. 3 is a block diagram showing a detailed configuration of the electronic sorter unit 203. The image sent from the image reading unit 201 is input as black luminance data,
The log is sent to a log converter 301. The log conversion unit 301 stores an LUT for converting input luminance data to density data, and converts the luminance data to density data by outputting a table value corresponding to the input data. . Thereafter, the density data is sent to the binarization unit 302. The binarization unit 302 binarizes the multi-valued density data and sets the density value to “0” or “2”.
55 ". The input 8-bit image data is binarized and converted into 1-bit image data of “0” or “1”, and the amount of image data stored in the memory is reduced.

However, when an image is binarized, the number of gradations of the image is changed from 256 to two. Therefore, when image data having a large number of halftones such as a photographic image is binarized, image deterioration generally occurs. Remarkable. Therefore, it is necessary to perform pseudo halftone expression using binary data.

Here, an error diffusion method is used as a technique for pseudo-halftone expression using binary data. This method uses “25” when the density of a certain image is larger than a certain threshold.
If the density data is not more than a certain threshold value, the data is binarized as being the density data of “0”, and the difference between the actual density data and the binarized data is used as an error signal as a surrounding error signal. This is a method of allocating to pixels. Here, the distribution of the error is performed by multiplying a weight coefficient on a matrix prepared in advance by the error generated by the binarization, and adding the result to the surrounding pixels. As a result, the average density value of the entire image is stored, and the halftone can be represented in a pseudo binary manner.

The binarized image data is supplied to the control unit 303.
Sent to The image data from the external computer input from the external I / F processing unit 209 is stored in the external I / F
Since the image is processed as binary image data by the processing unit 209, the image data is sent to the control unit 303 as it is. The control unit 303 temporarily stores all the images of the original to be copied in the image storage unit 304,
The image data is sequentially read from the image data 04 and output. The image storage unit 304 has a SCSI controller (not shown) and a hard disk (memory), and writes image data to the hard disk according to a command from the SCSI controller.
The plurality of image data stored on the hard disk are output in an order according to the editing mode specified by the operation unit of the copying machine. For example, in the case of sorting, the document is read from the DF in order from the last page to the first page of the document bundle, and temporarily stored in the hard disk. Then, the image data of the document once stored is read from the hard disk in order from the last page to the first page, and this is repeated a plurality of times and output. Thereby, it can play the same role as a sorter having a plurality of bins.

The image data called from the image storage unit 304 is sent to the smoothing unit 305. The smoothing unit 305 first converts 1-bit data into 8-bit data, and sets the image data signal to “0” or “255”. The converted image data is replaced with a weighted average value obtained by summing the values obtained by multiplying the coefficients on the predetermined matrix by the density values of the neighboring pixels. As a result, the binary data is converted into multi-valued data according to the density value of the neighboring pixels, and an image quality closer to the read image can be reproduced. The smoothed image data is input to the gamma correction unit 306. γ correction unit 30
In step 6, when the density data is output, conversion is performed using an LUT in consideration of the characteristics of the printer, and the output is adjusted in accordance with the density value set by the operation unit.

Next, a detection method of the image direction detection unit 210 will be described with reference to FIGS. FIG. 6 is a block diagram illustrating a configuration of the image direction detection unit 210 according to the present embodiment. In the figure, reference numeral 401 denotes an image input unit, which inputs image data subjected to scaling processing by the analog signal processing unit 202 in FIG. Reference numeral 402 denotes a CPU / memory unit, which includes a memory that performs image direction detection processing, converts the image data into a resolution of image data necessary for determining the image direction, and temporarily stores the resolution. Reference numeral 403 denotes a character recognition / direction discriminating unit. It is noted that characters most accurately represent the direction of a document.
Several types of character areas in a document are defined as 0 °, 90 °, 180 °,
Character recognition is performed from the direction of 270 °, and the direction with the highest accuracy among the character recognition accuracy (the degree of confidence in character recognition: the distance to the characteristic distribution of the character) in each direction is set as the document direction. Reference numeral 404 denotes an area separating unit, which performs a character recognition and a direction determination process by the character recognition / direction determination unit 403 from the document image data as a pre-process.
This is a block for performing processing of separating a graphic part, a natural image part, a table part, and the like into rectangular areas and adding an attribute (character part or the like) of each area.

Next, the outline of the automatic document direction determination / correction and character recognition processing will be described. FIG. 7 is a flowchart illustrating the image direction detection processing according to the present embodiment. Image data (multi-valued image) input by the image input unit 401
Is first separated by the region separating unit 404 into rectangular regions for each attribute such as a character portion, a graphic portion, a natural image portion, and a front portion (steps S1 and S2). Actually, area information surrounded by a rectangle is created. Next, rectangle information of the character area is extracted from each attribute (step S3). Here, the character area includes a text portion, a title portion, characters in a table, a caption portion of a figure, and the like. For example, in the case of the documents (a) and (c) shown in FIG. 8, the rectangular information of the character area is extracted as shown in (b) and (d) of FIG. 8, respectively. Then, the document direction is determined using several blocks among them (step S4). As a result, if the document direction is the forward direction, character recognition processing is continuously performed on character blocks in the image (step S7).

On the other hand, if the document direction is not the forward direction, the image data is rotated in the correct direction (step S5). Then, region separation is performed on the rotated image, and correction processing of region separation information is performed (step S6). This method corrects the phase of the region separation information accompanying the image rotation. As a method, there are a method of performing a region separation process again on all rotated image data and a method of applying an address conversion to a region separation result. Since the area separation processing generally assumes that the image is in the forward direction, the results of the area separation processing performed in the initial stage and the area separation processing performed on the rotated image data often differ. Therefore, it is desirable that the former method be used. Next, a character area block in the rotated image data is recognized by a character recognition processing system (step S7). And
Finally, in the case of the direction without rotation / with rotation, the area separation information and the character recognition information are obtained (step S8). This processing result is notified to the CPU circuit unit 205 shown in FIG. The CPU circuit unit 205 performs image rotation and the like using the result of the character recognition information, and controls the binding position of the paper discharge processing unit.

Next, a description will be given of a method of determining the document direction using the character recognition processing. The region separation process detects black pixels of the document image data, and creates a rectangular frame of black pixel blocks by contour tracing or labeling.
Next, a character area (title, body, caption, etc.), a graphic area, a natural image area, a table area, and the like are determined based on the black pixel density in the rectangle, the presence / absence of an adjacent rectangular block, the aspect ratio of the rectangle, and the like. Is determined. From this processing result, the rectangle information of the character area is determined. The character recognition processing includes a feature vector extraction method, a comparison method, and the like. For example, as shown in FIG. 4A, when a character area including the character "book" is determined, as a first step, a character cutout process is performed on this character area (FIG. 4B) reference). This is a process of cutting out a rectangle of one character, and is obtained by detecting the state of black pixel continuity. As a second step, one character is cut into m × n (for example, 64 × 64) pixel blocks (see (c) shown in FIG. 4). Then, the distribution direction of the black pixels is extracted from among them using a 3 × 3 pixel window (direction vector information: (d) shown in FIG. 4).
reference).

FIG. 4 (d) illustrates a part of the direction vector information. The window of 3 × 3 pixels is shifted to obtain several tens of direction vector information.
This vector information is a character feature. The feature vector is compared with the contents of the character recognition dictionary stored in advance, and 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 third candidate,... The closeness of the feature to this feature vector is a numerical value called the closeness of the distance to the character, that is, the degree of confidence (accuracy) of character recognition. In the character direction determination processing, the degree of confidence in character recognition is obtained in this manner. The character direction determination processing based on the degree of confidence will be described with reference to a sentence example of “Name of the present invention” shown in FIG.

FIG. 5A shows a sentence in the forward direction, and FIG. 5B shows a sentence rotated by 270 °. here,
When paying attention to “book” and determining the character direction, as shown in (c) of FIG. 5, 0 is set for one character “book”.
Let's try character recognition from four directions of °, 90 °, 180 ° and 270 °. For each rotation angle, the method of reading the character rectangular area may be changed, and it is not particularly necessary to rotate the document. The character recognition results at each rotation angle are different from each other as shown in FIG. Note that FIG. 5C shows the provisional character recognition result and the degree of confidence for explanation, and this is not always the case.

In FIG. 5C, in the positive direction (0
When character recognition is performed from (°), “book” is correctly recognized, and the degree of confidence is as high as 0.90. When character recognition is performed from a direction rotated by 90 °, the character is erroneously recognized as “town”, and the confidence level is reduced to 0.40. The reason why the erroneous recognition occurs and the confidence level is reduced is that the character recognition is performed based on the feature vector when viewed from the rotating direction. Similarly, when character recognition is performed from a direction rotated by 180 ° or 270 °, erroneous recognition occurs and the degree of confidence is reduced. It should be noted that the difference in the degree of confidence in the direction of character recognition becomes more pronounced as the character becomes more complex.

In the result (c) shown in FIG. 5, since the confidence is highest in the forward direction, it is determined that the document is highly likely to be oriented in the forward direction. In order to improve the accuracy of character direction discrimination, character recognition is performed for a plurality of characters in the same block from four directions in the same manner. Furthermore, when the character direction is determined only by one block, the character direction may be erroneously determined for a special character string. Therefore, similar character recognition is performed on a plurality of blocks. And
For each block, the average value of the confidence in each direction of each recognition target character in the block is determined, and further, the average value of the confidence values in each direction in each block is determined.
The direction with the highest average value is recognized as the character direction (document direction). As described above, the character (document) can be determined by determining the character direction based on the confidence level of a plurality of characters in the same block, and further, the plurality of characters in the same block without determining the character direction based on the degree of one character itself. The direction can be determined with high accuracy. However, needless to say, even if the character direction is determined based on the degree of confidence of only one character, or the character direction is determined based on the degree of confidence of a plurality of characters in the same block, the character direction can be determined with higher accuracy than before.

Next, an example of processing for detecting a document orientation and outputting a copy according to the present embodiment will be described. FIG. 17 is a diagram showing various patterns of document contents on a document. In the figure, 3-1 indicates upper original horizontal writing, 3-2 indicates upper original vertical writing, 3
-3 is a lower original horizontal writing, 3-4 is a lower original vertical writing, 3-5 is a right original horizontal writing, 3-6 is a right original vertical writing, 3-7 is a left original horizontal writing, 3-8 is a left original vertical writing. is there. Here, depending on the direction of each document and the horizontal and vertical directions, if the normal stapling position is stapled in ST1 to ST8 in FIG. 17, no problem occurs when viewing the copied document.

However, the stapling apparatus shown in FIG. 1 can only staple the sheet in the sheet conveying direction before the rear end. Therefore, the direction of the image output is controlled by detecting the document orientation shown in FIG.

FIG. 18 is a flowchart showing copy rotation control in this embodiment. First, one original is optically read (step S701), and image data is input (step S702). Thereafter, the document direction (up / down / left / right) of the original is determined from the input image data (step S703). From the determination result, it is determined whether the image data of the document should be rotated (step S7).
04), if it is determined to rotate, that is, FIG.
When the original is placed in a direction other than 3-1 and 3-8 shown in FIG. 7, the rotation angle of the image data is obtained from the determination result and the designated direction or the reference direction (step S705), and the image is rotated by the rotation angle. Rotate the data (step S706),
Copying is performed (step S707), and the sheet is discharged (step S708). On the other hand, if it is determined that the document is not to be rotated, that is, if the document is placed in the direction of 3-1 and 3-8 shown in FIG. 17, the image is not rotated and copying is performed (step S707). (Step S708).

Next, the determination process for the rotation angle of the image will be described. When the original is placed in the direction shown in FIG. 17, the image is read, and when the image is not rotated, the paper on which the image has been formed is the left side of FIG. An image is formed on the front side. If it is determined from the document orientation determination result that the document is in the direction of 3-1 in FIG. 17, the rotation angle is 0 because there is no need to rotate the image.
°. If the original is determined to be 3-2 in FIG. 17, the image is formed by rotating the image 90 ° clockwise to the right so that the upper side of FIG.
If the original is determined to be 3-3 in FIG. 17, the right side of FIG.
The image is formed by rotating the image by 0 °. The original is 3 in FIG.
When it is determined to be −4, the image is formed by rotating the image 90 ° to the left so that the lower side of FIG. 17 is the rear end of the discharge and the left side is the front of the discharge. Similarly, if the original is 3-5 in FIG.
If it is determined that the image is to be formed, the image is rotated 90 ° to the right so that the upper side in FIG. When the original is determined to be 3-6 in FIG. 17, the image is formed by rotating the 180 ° image so that the right side of FIG. 17 is at the rear end of the discharge and the lower side is before the discharge.
When the original is determined to be 3-7 in FIG. 17, the image is formed by rotating the image 90 ° to the left so that the lower side of FIG. 17 is at the rear end of the discharge and the left side is before the discharge. If the original is determined to be 3-8 in FIG. 17, it is 0 ° because there is no need to perform image rotation. By rotating the image using the result of detection of the direction of the document, the staple direction can be adjusted to the direction of the image.

In this embodiment, the stapling process has been described as an example of determining the direction of the document and changing the control. However, the present invention may be used in a mode in which a plurality of document images are laid out on one sheet.

Next, a copy process according to this embodiment will be described. FIG. 9 is a flowchart illustrating a copy process according to the present embodiment. This process is called at regular time intervals or as needed from the main process.

First, in step S1001, it is determined whether the copy key has been pressed by the operator. If the button has not been pressed, the process returns to step S1001 and waits until the button is pressed. Thereafter, if the copy key is pressed by the operator in step S1001, step S1002
To determine whether or not pressing the copy key is the start of the previous interruption / resumption. Here, in the case of resumption from interruption, since the document image has already been read, step S1010
Then, the output direction and the layout direction of the image are controlled in accordance with the direction of the original image specified by the operator before the start key is pressed, and the process proceeds to step S1011 to form the image.

If it is determined in step S1002 that the operation is not a restart from the interruption, the flow advances to step S1003, and the RDF 18
From 0, the original is conveyed onto the platen glass 101. Thereafter, the process proceeds to step S1004, where the platen glass 101
The upper document is scanned, and document image data is input to the electronic sorter unit 203 and the image direction detection unit 210. In the electronic sorter unit 203, as described above, the image data is binarized and stored in the memory. Then, in step S1005, the image direction detection unit 210 determines the direction of the document image and the degree of confidence thereof. In step S1006, step S100
It is determined whether or not the degree of confidence in the document image direction determined in step 5 is greater than an operator set level 1 described later. here,
If the confidence is greater than level 1, step S1010
Proceed to. If not, the process proceeds to step S1007, and it is determined whether or not the degree of confidence is greater than an operator setting level 2 described later. If it is higher than level 2, the process advances to step S1008 to determine whether the document image direction is the same as the document image direction of the previous page. as a result,
If the image direction is the same as the original image of the previous page, the process advances to step S1010. If it is not larger than level 2 in step S1007, or if it is not in the same image direction as the original image of the previous page in step S1008, the process advances to step S1009 to execute the interruption process. More specifically, since the orientation of the original image could not be determined, the image forming operation was interrupted and a part of the original image reduced to an extent that the operator could not recognize was displayed on the display panel 469 of the operation unit. Then, a message urging the operator to instruct the direction of the document image is displayed, and the image forming operation is interrupted. Here, although not described in detail, in the printer operation, the driving is stopped after the fed paper is discharged.

Next, in step S1010, the image is rotated according to the copy mode specified by the operation unit, and the layout is determined according to the direction of the original image. Then, in step S1011 image formation is performed. Although not described here, paper is fed from the above-described paper feed cassette in a processing flow different from this control flow,
Image formation is performed so as to match the image to the sheet.
Thereafter, in step S1012, it is determined whether or not image formation has been performed for the number set in the operation unit. If image formation has not been performed for the number of copies, step S1
Returning to step 011, the above-described image formation is repeated. If image formation has been completed for the number of copies, the process advances to step S1013 to determine whether the document bundle stacked on the document transport device 180 has been transported to the last document. If the document is not the last document, the process returns to step S1003 and repeats from drawing in the document. If it is the last document, the image forming operation is terminated.

Next, the setting of levels 1 and 2 by the operator will be described. FIG. 10 shows a display panel 469 of the operation unit.
FIG. 7 is a diagram showing a setting screen displayed in FIG. In the figure,
Reference numeral 501 denotes a display for setting the level of switching of the degree of confidence in the image direction determination. The confidence level of the judgment is changed from “0” to “1”.
0 "to 11 levels. Here, “0” is the stage where the image direction could not be determined at all, and “10” is the case where the degree of confidence in the determination of the image direction is the maximum. It is divided and displayed with a confidence level of 10 during that time. 505,506
Are the self-designation levels 1 and 2 of the image direction determination shown in FIG.
Are respectively shown. The level indicated by the cursor key of the operation unit can be set from "0" to "10". Reference numerals 502, 503, and 504 denote operation content setting items, which are used to set what processing is to be performed when the level is higher than level 1, not higher than level 1 but higher than level 2, and not higher than level 2. Indicates the content.

These processing contents can be selected from several processing contents by selecting each item and using a cursor key. The processing settings at each level are configured so that the same processing contents can be set and processing can be performed. An arrow is displayed on each selected display in a direction in which another processing content can be selected with the cursor key.

In FIG. 10, the selection item 502 can be changed to another processing content by using the down cursor key, and the up cursor key indicates that there is no more processing content. In addition, 503 indicates that it is both up and down. 504
Indicates that it can only be changed with the up cursor key. Further, the processing contents shown in FIG. 10 indicate the items of the control flow shown in FIG. 9, and the control flow depends on the contents of the setting items in steps S1006 and S1006 in FIG.
The processing after the determination in step 1007 will change.

In this embodiment, the degree of confidence in the direction determination of the original image is divided into three levels, and the operator designates the processing at each level. Can be similarly performed. Conversely, it may be performed at the confidence level of “0” and at two other levels. In this case, the designation is made in a case where the document image direction cannot be determined and in other cases.

Further, instead of selecting the processing content at the determination level of the document image direction from the menu item, the processing content may be specified more minutely.

As another embodiment, a case will be described in which the image forming operation is not interrupted when the original image direction cannot be determined. The setting method is the same as in the present embodiment. FIG. 15 is a flowchart illustrating a copy process according to another embodiment. This process is called at regular time intervals or as needed from the main process.

First, in step S1101, it is determined whether the copy key has been pressed by the operator. If the button has not been pressed, the process returns to step S1101 and waits until the button is pressed. Thereafter, if the copy key is pressed by the operator in step S1011, step S1102
The document is conveyed onto the platen glass 101 from the RDF 180. Then, the process proceeds to step S1103, where the original on the platen glass 101 is scanned, and the electronic sorter unit 2 is scanned.
03, and input the original image data to the image direction detection unit 210. In the electronic sorter unit 203, as described above, the image data is binarized and stored in the memory. Then, step S1
In step 104, the image direction detecting unit 210 determines the direction of the original image and its confidence, and stores the original image direction and the confidence in association with the original image data stored in the electronic sorter unit 203.

Next, in step S1105, it is determined whether or not the degree of confidence in the document image direction determined in step S1104 is such that the document can be determined. This corresponds to the case where both the level 1 and the level 2 are set to the confidence level 0 in the above-described embodiment. If the direction of the document image has been determined, the process advances to step S1106 to set a status flag indicating that there was a document whose document image direction could be determined. If the direction of the document image cannot be determined, the process advances to step S1107 to determine whether the read document is the final document. If it is not the final document, the process returns to step S1102, and the above processing is repeated until the final document is read.

On the other hand, if it is the final document,
Proceeding to 1108, it is determined whether the above status flag is set. Here, the case where the status flag is not set means that the directions of all the original images cannot be determined, and the step is performed in the original image reading direction without rotating the image or changing the layout. S111
Proceeding to 0, image formation is performed. If the status flag is set, the flow advances to step S1109 to rotate the image according to the copy mode specified by the operation unit, or to determine the layout according to the direction of the document image determined in step S1104. . If the original image direction cannot be determined in step S1104, control is performed using the original image directions before and after the original image. Although not described here, in a processing flow different from this control flow, paper is fed from the above-described paper feed cassette, and image formation is performed so as to match an image to the paper.

Next, in step S1111, it is determined whether image formation has been performed for the number set in the operation unit. If image formation has not been performed for the set number, the process returns to step S1110, and image formation is repeated. If the image formation for the number of copies has been completed, the process proceeds to step S1112, and it is determined whether the image forming operation for all the originals has been performed. If all document image forming operations have not been performed, the process returns to step S1108 and repeats for the next document image. If the image forming operation for all the original images has been performed, the image forming operation is terminated.

It is needless to say that the same effect can be obtained in the present process even when the document image direction is close to a level where it cannot be determined.

Further, as another embodiment, when the original image direction cannot be determined, it is possible to set so that the image is formed in the output direction set in advance by the operator according to the original size.

As described above, according to the embodiment,
Recognizing the original image direction and rotating or laying out the image to prepare an image forming bundle for the original bundle, or setting image forming processing for controlling the stapling direction to the recognition confidence of the original image direction detecting means. Thus, even if erroneous detection of the image direction is caused by various originals, the control specified by the operator can be performed with the confidence, and a copy intended by the operator can be obtained.

The present invention can be applied to a system including a plurality of devices (for example, a host computer, an interface device, a reader, a printer, etc.), but it can be applied to a single device (for example, a copier, a facsimile). Device).

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 (CPU or MP) of the system or apparatus.
It goes without saying that U) can also be achieved by reading and executing 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 instruction 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 functions of the above-described embodiments are realized by the processing.

[0063]

As described above, according to the present invention,
By setting a predetermined image forming process for the direction detection result of the document image, an image intended by the operator can be formed.

[0064]

[Brief description of the drawings]

FIG. 1 is a cross-sectional view illustrating a structure of an image forming apparatus according to an embodiment.

FIG. 2 is a block diagram illustrating a control system of the image forming apparatus according to the exemplary embodiment.

FIG. 3 is a block diagram illustrating a detailed configuration of an electronic sorter unit 203.

FIG. 4 is a diagram illustrating a character recognition process according to the embodiment.

FIG. 5 is a diagram illustrating a character direction determination process according to the embodiment.

FIG. 6 is a block diagram illustrating a configuration of an image direction detection unit 210 according to the present embodiment.

FIG. 7 is a flowchart illustrating an image direction detection process according to the embodiment.

FIG. 8 is a diagram showing a correspondence between a document and rectangular information of a character area to be extracted.

FIG. 9 is a flowchart illustrating a copy process according to the embodiment.

FIG. 10 is a diagram showing a setting screen displayed on a display panel 469 of an operation unit.

FIG. 11 is a diagram showing a format of an original document (various patterns such as vertical writing and horizontal writing).

FIG. 12 is a diagram illustrating a direction of an image displayed on a monitor.

FIG. 13 is a diagram for explaining a method of automatically determining a document image direction.

FIG. 14 is a diagram illustrating a character direction and a recognition result in the character recognition processing.

FIG. 15 is a flowchart illustrating a copy process according to another embodiment.

FIG. 16 is a diagram illustrating a configuration of an operation unit according to the present embodiment.

FIG. 17 is a diagram showing various patterns of document contents on a document.

FIG. 18 is a flowchart illustrating copy rotation control according to the present embodiment.

Claims (10)

[Claims] 1. An image forming apparatus for inputting a document image and forming an image on a recording material, comprising: an image direction detecting means for detecting an image direction of the document image; A control unit for performing control so as to perform a predetermined image forming process. 2. The image forming apparatus according to claim 1, wherein the image direction detecting unit outputs a determination degree as a result of detecting the image direction. 3. The image forming apparatus according to claim 2, further comprising a setting unit configured to set a level at which a predetermined image forming process is performed for the determination level, wherein the control unit performs the image forming process at the level set for the determination level. 3. The image forming apparatus according to claim 2, wherein the control is performed in such a manner. 4. The image forming apparatus according to claim 3, wherein when the determination degree is equal to or less than a predetermined level, the image forming process is interrupted, and a display indicating that the direction of the document image is designated is displayed. 5. The image forming apparatus according to claim 3, wherein when the determination degree is equal to or less than a predetermined level, image forming processing is performed based on directions of original images before and after the original image. 6. An image forming method for inputting a document image and forming an image on a recording material, comprising: an image direction detecting step of detecting an image direction of the document image; A control step of performing control so as to perform a predetermined image forming process. 7. The image forming method according to claim 6, wherein in the image direction detecting step, a determination degree is output as a detection result of the image direction. 8. A setting step of setting a level at which a predetermined image forming process is performed for the determination level, wherein the control step performs the image forming process at a level set for the determination level. 8. The image forming method according to claim 7, wherein the control is performed as follows. 9. The image forming method according to claim 8, wherein when the determination level is equal to or less than a predetermined level, the image forming process is interrupted and a display indicating that the direction of the document image is designated is displayed. 10. When the degree of determination is equal to or less than a predetermined level,
9. The image forming method according to claim 8, wherein the image forming process is performed based on the directions of the original image before and after the original image.