JP4931897B2 - Image processing apparatus, image forming apparatus, image processing method, computer program, and recording medium - Google Patents

Description

  The present invention relates to an image processing method for detecting and correcting an original of an acquired original image and an image, an image processing apparatus, an image forming apparatus including the image processing apparatus, and a computer program for realizing the image processing apparatus And a recording medium on which the computer program is recorded.

  When a document image processed by a copier, multifunction device, scanner, or the like is generated as image data, image processing such as correction of document and image tilt, image shaping, and noise removal is performed when the document is read. There are many. Among these image processes, correction of document and image tilt is positioned as a particularly important process, and various processing methods and apparatuses have already been realized.

For example, in Patent Document 1, in an image processing apparatus that reads an original image, when the original to be read or an image formed on the original (hereinafter referred to as content) is tilted, or when the orientation of the original is incorrect, etc. Obtaining a plurality of tilt angle candidates, presenting a display image representing each tilt angle to the user, determining the tilt angle based on the display image selected by the user, and determining the tilt of the document and the image. Techniques for correcting are disclosed.
JP 2006-87027 A

However, in the technique disclosed in Patent Document 1, a tilt angle candidate is obtained based on feature amounts of plural types of information such as document edge information and character string information, so that it is not necessary to correct the tilt. The display image is presented to the user even when the performance is high.
For example, when the document is not tilted and the content is tilted, or when the document is tilted but the content is not tilted, the display image is presented to the user and the user is required to select. In some cases, work efficiency may be reduced.

  The present invention has been made in view of such circumstances, and an object of the present invention is to change the inclination of an original and an image by switching generation or non-generation of a display image according to the detected original and the inclination of the image. Image processing apparatus, image forming apparatus, image processing method, and image processing apparatus capable of preventing a display image from being displayed when there is a high possibility that correction of the image is not required, and suppressing a reduction in work efficiency A computer program for realizing the above and a recording medium on which the computer program is recorded are provided.

  An image processing apparatus according to the present invention acquires a document image obtained by scanning and reading a document on which an image is formed, and the document and the inclination of the image with respect to the scanning direction from the document image acquired by the unit. Detection means for detecting, generation means for generating a plurality of display images expressing the respective inclinations detected by the detection means, and the inclination expressed in one of the display images generated by the generation means And a correction unit that corrects the inclination of the original and the image of the original image, and a first determination unit that determines whether each of the inclination of the original and the image detected by the detection unit is greater than a first threshold value. And a second determination unit that determines whether or not the difference between the inclinations of the original and the image is smaller than a second threshold when both the first determination unit and the first determination unit are determined to be large. Is small If you, or when the first determination means determines that at least one is not large, the generation unit is characterized in that that is not to generate the display image.

  In the image processing apparatus according to the present invention, when the second determination unit determines that the second determination unit is small, the correction unit determines the document image and the image inclination of the document image based on the document or image inclination detected by the detection unit. It is characterized by being corrected.

  The image processing apparatus according to the present invention comprises means for displaying a plurality of display images generated by the generating means, and means for receiving selection of display images displayed by the means.

  The image processing apparatus according to the present invention includes means for accepting a setting relating to inclination correction, and when the means accepts the setting, when the first judging means judges that at least one is larger, the generating means Is configured to generate the plurality of display images.

  An image forming apparatus according to the present invention includes the image processing apparatus according to any one of the above-described inventions, and an image forming unit that forms an output image based on a document image whose inclination is corrected by the image processing apparatus. It is characterized by providing.

  The image processing method according to the present invention acquires a document image obtained by scanning and reading a document on which an image is formed, and detects and detects the document and the inclination of the image with respect to the scanning direction from the acquired document image. A plurality of display images expressing respective inclinations are generated in the generation step, and the original of the original image and the image inclination are corrected based on the inclination expressed in one of the display images generated in the generation step. In the image processing method to be corrected in steps, when it is determined in the first determination step that determines whether or not each of the detected document and the inclination of the image is larger than the first threshold, and in the first determination step, A second determination step for determining whether or not the difference between the inclinations of the document and the image is smaller than a second threshold value, and when the second determination step determines that the difference is small, or the first determination step If it is determined that at least one is not large, in the generating step, characterized in that you have not to generate the display image.

  In the image processing method according to the present invention, when it is determined in the second determination step that the image processing method is small, the document image and the image inclination of the document image are corrected in the correction step based on the detected document or image inclination. It is characterized by being.

  The image processing method according to the present invention includes a step of displaying a plurality of display images generated in the generation step, and a step of accepting selection of the display image displayed in the step.

  The image processing method according to the present invention includes a step of accepting a setting relating to inclination correction, and when the setting is accepted at the step, when the at least one of the first judging steps is judged to be large, the generating step And a plurality of display images are generated.

  A computer program according to the present invention causes a computer that acquires image data and performs image processing to detect a document and an inclination of the image with respect to the scanning direction from a document image scanned and read from the document on which the image is formed. Generating a plurality of display images expressing the detected inclinations in the generation step, and based on the inclination expressed in one of the display images generated in the generation step, In the computer program for correcting the inclination of the image in the correction step, a first determination step for causing the computer to determine whether each of the detected document and the inclination of the image is larger than a first threshold, and the computer performs the first determination. If it is determined that both are large in the step, the computer determines whether the difference between the inclination of the document and the image is smaller than a second threshold value. A second determination step for determining, and when the computer determines that the second determination step is small, or when it is determined that at least one is not large in the first determination step, the computer displays the display in the generation step. It is characterized by not generating an image for use.

  The computer program according to the present invention, when the computer determines that it is small in the second determination step, based on the detected inclination of the original or image, the inclination of the original and the image of the original image in the correction step. It is characterized in that the correction is made.

  A recording medium according to the present invention records the computer program according to any one of the above-described inventions.

In the present invention, when at least one of the detected original and the image inclination of the original image is not larger than the first threshold, each inclination is larger than the first threshold, and the difference between the inclinations is larger than the second threshold. If it is smaller, the display image to be selected is not generated.
Thereby, when the inclination of the document or the image is not significant enough to exceed the first threshold, and when each inclination is significant and substantially coincides, the necessity of correcting the inclination of the document or the image may be obvious. Therefore, the display image itself is not generated. For this reason, the user is not required to make a selection.

In the present invention, when the display image is not generated because the inclination of the original and the image is larger than the first threshold and the difference between the inclinations is smaller than the second threshold, the original and the image are detected based on the detected inclination. The inclination of the original and the image (that is, the inclination of the entire original including the image) is corrected.
As a result, when the inclinations of the original and the image are significant and the inclinations substantially coincide with each other, the inclination of the original and the image is automatically corrected on the assumption that the reliability of the inclination detection result is high. In this case, the inclination to be corrected is, for example, the detected original inclination, the image inclination, or the average value of the original inclination and the image inclination.

  In the present invention, a plurality of display images to be selected are displayed, and when the user selects one of the display images, the selection is accepted. Thus, for example, the original and the image inclination are corrected with respect to the original original image by an amount corresponding to the inclination of the selected display image.

In the present invention, when a setting related to tilt correction is received in advance, a plurality of display images are generated when at least one of the detected document and image tilt is larger than the first threshold value.
Thereby, for example, when a mode for performing highly accurate correction is set, a plurality of display images are actively displayed when the inclination of the document or the image is significant, and the user is requested to select.

In the present invention, an output image is formed based on the original image whose inclination is corrected by the image processing apparatus according to any one of the above-described inventions.
Thus, an image processing apparatus in which a display image is not displayed when there is a high possibility that the necessity of correcting the inclination of the document and the image is obvious is applied to a printer apparatus, a digital multifunction peripheral, and the like.

  In the present invention, each unit of the image processing apparatus described above is realized by a computer program read from a recording medium.

According to the present invention, the generation or non-generation of the display image is switched according to the inclinations of the document and the image and the difference value between these inclinations.
Thereby, when the inclination of the document or the image is not significant enough to exceed the first threshold, and when each inclination is significant and substantially coincides, the necessity of correcting the inclination of the document or the image may be obvious. Therefore, the display image itself is not generated. For this reason, the user is not required to make a selection. Therefore, when there is a high possibility that the correction of the inclination of the document and the image is not necessary, it is possible to prevent the display efficiency from being displayed and to prevent a reduction in work efficiency.

The image processing apparatus and the image forming apparatus according to the present invention are hereinafter referred to as a digital color multifunction peripheral having functions such as a copier, a printer, a facsimile, and a scan to e-mail, and the image processing apparatus according to the present invention is read as a color image. Embodiments applied to each apparatus will be described in detail.
(Embodiment 1)
FIG. 1 is a block diagram showing a configuration of a digital color multifunction peripheral according to Embodiment 1 of the present invention. In the figure, reference numeral 100 denotes a digital color multifunction peripheral. The digital color multifunction peripheral 100 has a CCD (Charge Coupled Device) line sensor, and RGB (R: red, G) obtained by reading reflected light from a document. : Green, B: blue) image input device 5 that outputs an analog signal as an original image, and CMYK (C: cyan, M: magenta, Y: yellow, K: black) digital color obtained by acquiring the analog signal. An image processing apparatus 2 that outputs a signal is provided.

The digital color multifunction peripheral 100 also includes an image output device 3 that forms an output image on a recording sheet by an output method such as a photographic method or an ink jet method based on a digital color signal given from the image processing device 2, and an LCD (Liquid Crystal). And an image display device 4 including a touch panel and performing various displays, and an operation panel 6 for receiving operations on the above-described devices.
Note that the image output device 3 may be a display device such as a display. Further, the image display device 4 and / or the operation panel 6 may be included in the image processing device 2.

  The image processing device 2 includes an A / D conversion unit 20 that converts an analog document image input from the image input device 5 into a digital document image, and an RGB digital signal output from the A / D conversion unit 20. The image input apparatus 5 includes a shading correction unit 21 that removes various distortions generated in the illumination system, the imaging system, and the imaging system, and an input processing unit 22 that performs gradation correction (hereinafter referred to as gamma correction). The RGB digital signal (original image) output from the input processing unit 22 is temporarily stored in the transmission / reception unit / storage unit 23 having a large-capacity storage device such as a hard disk and read out from the transmission / reception unit / storage unit 23. The document correction unit 25 is supplied via the document detection unit 24. A display control unit 26 that outputs a preview image (display image) to be described later to the image display device 4 is connected to the document detection unit 24 and the document correction unit 25.

  The image processing apparatus 2 also converts the RGB digital signal output from the document correction unit 25 into a CMY signal corresponding to RGB complementary colors and performs a process for improving color reproducibility, and a color correction unit 27. Is provided with a black generation / undercolor removal unit 28 that generates a CMYK digital color signal based on the CMY signal output from the. The CMYK digital color signal output from the black generation / undercolor removal unit 28 is subjected to enhancement processing and smoothing processing in the spatial filter unit 29 and then to a halftone generation unit 30 in which gradation reproduction processing is performed. This is given to the image output device 3.

The RGB digital signals output from the document correction unit 25 are also supplied to the region separation unit 31. The area separation unit 31 is an area identification signal that indicates which area each pixel included in the digital signal belongs to among areas such as black characters, color characters, halftone dots, and photographic paper photographs (continuous tone areas). And is supplied to the black generation / undercolor removal unit 28, the spatial filter unit 29, and the halftone generation unit 30.
Each unit of the image processing apparatus 2 described above is connected to a control unit 40 including a CPU 401, a ROM 402 that stores information such as a program, and a RAM 403 that stores temporarily generated information. The operation of each unit is controlled according to a control program stored in the ROM 402 in advance. The control unit 40 may be configured by an application specific integrated circuit (ASIC) or a digital signal processor (DSP).

  The RGB digital signal output from the document correction unit 25 is supplied to the color correction unit 27 and the region separation unit 31 as described above, and is also converted into the PDF format, and a network interface and a communication line interface (both not shown). To the external connection device and the communication line, respectively. The digital signal may also be compressed into a JPEG code based on a JPEG compression algorithm, stored in the transmission / reception unit / storage unit 23 as filing data, and managed.

When copy output and print output are instructed for the stored data, the target JPEG code is read from the large-capacity storage device of the transmission / reception unit / storage unit 23 and is given to a JPEG decompression unit (not shown) to be combined. And converted into the original RGB digital signal.
On the other hand, when an image transmission is instructed, the target JPEG code is read from the mass storage device of the transmission / reception unit / storage unit 23 and transmitted to the external connection device and the communication line via the network interface and the communication line interface, respectively. Is done.

  FIG. 2 is a schematic front sectional view showing the configuration of the image input device 5. The image input device 5 includes a document conveying unit 51 configured in an upper casing and a scanner unit 56 configured in a lower casing.

  The document transport unit 51 includes a document set sensor 514 that detects a document placed face down on a document tray 511 that is inclined from one side to the other. Above the lower end portion of the document tray 511, an attracting roller 512 is disposed for bringing the documents detected by the document setting sensor 514 one by one downstream. A conveyance path S formed by a guide is provided on the downstream side of the document tray 511, and a document is placed on the upper end and the middle of the conveyance path S up to a reading position R at the other end of the document table 561 described later. Conveying rollers 513a and 513b for conveying are respectively provided. On the other side of the reading position R, a document discharge roller 50 that discharges the read document and a document discharge sensor 567 that detects the discharged document are arranged.

  The conveyance roller (alignment roller) 513b has an electromagnetic clutch (not shown) on the drive shaft, and the transmission of rotational driving force by a drive motor (not shown) is controlled. When the document is not placed on the document tray 511, the drive shaft of the transport roller 513b is restrained and stopped by the electromagnetic clutch.

  A document is placed on the document tray 511, and the leading edge of the document conveyed downstream contacts a feeding timing sensor 515 disposed between the conveyance roller 513a and the conveyance roller 513b. When the signal is issued, the excitation state of the electromagnet built in the electromagnetic clutch is switched at a predetermined timing. As a result, the transport roller 513b releases the restraint of the drive shaft and starts to rotate in the direction of transporting the document downstream. At this time, the leading end portion of the document conveyed from the upstream side has already reached the nip portion of the conveying roller 513b, and the nip portion of the conveying roller 513b is formed so that the leading end portion of the document is formed after a predetermined deflection is formed on the document. It operates so as to be transported to the downstream side with being aligned so as to be substantially perpendicular to the transport direction.

  The scanner unit 56 includes scanning units 562 and 563 that translate in parallel to both sides while reading a document along the lower surface of the mounting table 561 for placing the document horizontally. On one side of the scanning unit 563, an imaging lens 564 is provided for converging the light read by the scanning unit 562. The light converged by the imaging lens 564 is a CCD line sensor. An image is formed on 565. On the other side of the scanner unit 56, a tray 566 is provided so as to project the document transported from the transport path S described above, read at the reading position R and discharged, face-down.

  The scanning unit 562 includes a light source 562a composed of, for example, a halogen lamp for irradiating light on the original conveyed from the original tray 511 and the original placed on the original table 561, and reflects light reflected from the original in the mirror 562a. Is reflected to the other side. The scanning unit 563 includes mirrors 563a and 563b that reflect light reflected by the mirror 562a of the scanning unit 562 downward and to one side, respectively, and the light reflected by the mirror 563b passes through the imaging lens 564 to the CCD line. An image is formed on the sensor 565 as a document image. The CCD line sensor 565 photoelectrically converts the formed original image to generate RGB analog signals.

  FIG. 3 is a block diagram illustrating a configuration of a main part related to document detection and inclination correction. The input processing unit 22 in FIG. 3A temporarily delivers the RGB digital signal (original image) given from the previous shading correction unit 21 to the large-capacity storage device of the transmission / reception unit / storage unit 23, and then the large-capacity storage device. RGB digital signals read from the storage device are supplied to the document detection unit 24. As shown in FIG. 3B, the document detection unit 24 includes a document tilt detection unit 241 and a content tilt detection unit 242 that detect the tilt of the document and the image (content), respectively, and the detected tilt of the document and the content, and each of them. And an inclination determination unit 243 that determines a magnitude relationship between the difference in inclination and a predetermined threshold. Whether or not the user needs to select a preview image is determined according to the determination result of the inclination determination unit 243 and the presence or absence of a predetermined setting by the user.

  When displaying a preview image, the display control unit 26 reads out the RGB digital signals stored in the large-capacity storage device of the transmission / reception unit / storage unit 23, performs resolution conversion and gamma correction as necessary, and performs a plurality of previews. An image is generated and displayed on the image display device 4. At this time, since the document may be reversed in the vertical direction or rotated in the direction of ± 90 degrees, a button for rotating the preview image is provided on the operation panel (for example, an LCD of the image display device 4 described later) A touch panel type operation button is provided on the screen 4a). As a result, the user can determine the direction to be corrected with respect to the vertical direction. The correction information for the vertical direction is given to the document correction unit 25.

Thereafter, when the user selects one of the preview images from the touch panel of the image display device 4 and the selection is accepted, the correction information of the inclination of the selected preview image is given to the document correction unit 25. The document correction unit 25 reads RGB digital signals stored in the large-capacity storage device of the transmission / reception unit / storage unit 23, and based on the correction information, the document and content tilt (that is, the document tilt including the content) and Correct the vertical orientation of the original.
Note that the preview image may be selected from the operation panel 6.

  3 is controlled by the CPU 401 of the control unit 40 in accordance with a control program stored in the ROM 402 in advance.

The resolution conversion performed when the display control unit 26 generates a preview image is such that the entire document image is displayed on the screen of the image display device 4 by thinning out pixels. When thinning out pixels, the following interpolation is performed.
(A) Nearest neighbor: The value of the pixel closest to the pixel to be interpolated or the value of an existing pixel having a predetermined positional relationship with the pixel to be interpolated is used as the value of the interpolated pixel.
(B) Bilinear: The average value of the values of the existing pixels weighted so as to be proportional to the distance to the existing pixels around the surrounding four pixels surrounding the pixel to be interpolated is set as the value of the interpolation pixel.
(C) Bicubic: A value obtained by performing an interpolation operation based on the value of 16 pixels obtained by adding 12 points surrounding these to 4 points surrounding the pixel to be interpolated is set as the value of the interpolated pixel.

  The display control unit 26 performs the above-described pixel decimation and interpolation, and then the inclination of the document including the content by the document inclination and the content inclination detected by the document inclination detection unit 241 and the content inclination detection unit 242 respectively. Each of the images is corrected, and further gamma correction based on the display characteristics of the image display device 4 is performed to generate a preview image. The display control unit 26 also generates a preview image in which the inclination of the original including the content is corrected by ½ of the detected original and the inclination of the content, respectively.

  The document correction unit 25 corrects the inclination information of the preview image selected by the user (that is, one of the inclination values detected by the document inclination detection unit 241 and the content inclination detection unit 242 or 1 / of these inclinations). Based on one of the values (2), the inclination of the document including the content is corrected by coordinate conversion shown in the following formula (1). However, the inclination is represented by an angle θ, and correction of the inclination is performed by rotating the coordinates counterclockwise by θ around the origin. Further, the coordinates before correction are (X, Y), and the coordinates after correction are (X ′, Y ′).

  FIG. 4 is an explanatory diagram showing the relationship between the inclination of the document and the content, and FIG. 5 is an explanatory diagram showing an example of processing for the state of the document and content tilt. In FIG. 4, the horizontal axis β represents the content inclination, and the vertical axis α represents the document inclination. Of the regions determined by the values of α and β, a region where α and β are not greater than the threshold T is (A), a region where α is not greater than the threshold T (excluding (A)) is (B), and β is the threshold T Regions that are not larger (except (A)) are (C), α and β are regions that are larger than the threshold T (except (A) to (C)), and the difference between α and β is smaller than the threshold D The area is indicated by (d) and the other areas are indicated by (e). Hereinafter, the contents of processing will be described with reference to FIG. 5 in the case where α and β are in the regions (a) to (e) in FIG. 4.

When α and β are not larger than the threshold T, they are expressed as “α≈0” and “β≈0”, respectively, and the inclinations of the original and the content are respectively expressed as “none” (that is, not significant). Further, when α and β are larger than the threshold value T, they are represented as “α ≠ 0” and “β ≠ 0”, respectively, and the inclinations of the document and the content are represented as “present” (that is, significant), respectively.
Further, when the difference between α and β is smaller than the threshold D, it is expressed as “α≈β”, and when the difference between α and β is not smaller than the threshold D, it is expressed as “α ≠ β”.

(A) When α≈β≈0 This is a case where neither the document inclination (α) nor the content inclination (β) is “None”. In this case, it is determined that the inclination of the document and the content is “none” and the reliability of the inclination detection is high. Further, since each inclination is “none”, it is determined that correction of the inclination of the document including the content is unnecessary. Therefore, selection by the user is unnecessary and a preview image is not displayed. This is the same when a mode for performing high-accuracy correction (hereinafter referred to as high-accuracy mode) is set in advance from the operation panel 6.

(B) When α≈0 and α ≠ β ≠ 0 This is the case where the document tilt is “none” and the content tilt is “present”. In this case, since the inclination of the document is “none”, it is determined that correction of the inclination of the document including the content is unnecessary. Therefore, selection by the user is unnecessary and a preview image is not displayed.
When the high-accuracy mode is set, a preview image that has not been corrected for inclination and a preview image that has been corrected for the inclination of the document including the content by β and β / 2 are displayed on the image display device 4. Display each one and ask the user for selection.

(C) When β≈0, β ≠ α ≠ 0 This is the case where the document tilt is “Yes” and the content tilt is “None”. Content with a tilt of “none” has been read. In this case, since the content inclination is “none”, it is determined that correction of the inclination of the document including the content is unnecessary. Therefore, selection by the user is unnecessary and a preview image is not displayed.
When the high-accuracy mode is set, a preview image in which the inclination of the document including the content is corrected by α and α / 2 and a preview image in which the inclination is not corrected are displayed on the image display device 4. Display each one and ask the user for selection.

(D) When α≈β ≠ 0 This is a case where the inclinations of the document and the content are “Yes” and substantially equal. In this case, it is determined that the inclinations of the document and the content are substantially the same, and the reliability of inclination detection is high. Therefore, selection by the user is unnecessary and a preview image is not displayed. The inclination to be corrected for the document including the content is α, β, or an average value of α and β.
When the high-accuracy mode is set, a preview image obtained by correcting the inclination of the document including the content by α and α / 2, a preview image obtained by correcting by β and β / 2 respectively, An average value of α and β and a preview image corrected by half of the average value are displayed on the image display device 4 respectively, and the user is asked to select.

(E) When α ≠ β, α ≠ 0, β ≠ 0 This is a case where the inclinations of the original and the content are “present” but cannot be said to be substantially equal, and other than the above (a) to (d) Corresponds to the case. In this case, since the inclinations of the document and the content are “Yes”, but the inclinations of each do not match, it is determined that the reliability of inclination detection is low. Therefore, a preview image is displayed to ask the user for selection. The preview image is prepared by correcting the inclination of the document including the content by α and α / 2, and by correcting by β and β / 2, respectively. This is the same when the high accuracy mode is set.

  FIG. 6 is an explanatory diagram illustrating an example in which a plurality of preview images are generated and displayed on the image display device 4 and the user is requested to select. For example, when the document and the content in the document image are inclined by α and β, respectively, as described above in (e), the preview image P2 in which the inclination of the document including the content is corrected by α and the preview image corrected by β. In addition to P1, an uncorrected preview image P0 is generated. A preview image in which the inclination of the document including the content is corrected by α / 2 and β / 2 is also generated, but is omitted in FIG.

  Thereafter, the generated preview images P0, P1, and P2 are displayed on the LCD screen 4a of the image display device 4 as “uncorrected”, “candidate 1”, and “candidate 2”, respectively, together with “select” buttons corresponding to the respective preview images. Is displayed. Then, the user visually recognizes the preview image whose inclination is appropriately corrected, and presses a selection button corresponding to the visually recognized preview image from the touch panel of the image display device 4 so that the document correcting unit 25 includes the document including the content. Whether or not to correct the inclination and the amount of inclination to be corrected (β or α in FIG. 6) are determined.

FIG. 7 is an explanatory diagram showing a method for detecting the inclination of the document as an angle. FIG. 8 is a chart showing a relationship between a tangent and an angle corresponding to the tangent. FIG. 7 shows a state where a document on which an image (content) is formed is scanned by the image input device 5 and read as a document image. In the figure, the solid line represents the document edge (edge), and the wavy line corresponds to the scanning line when the document is scanned, and represents the horizontal line constituting the document image. Each line is a set of a plurality of pixels having respective pixel values, and the left (or upper) pixel in the figure is transmitted so that it appears earlier in time / space than the right (or lower) pixel. / Memorized.
Note that the pixel value here indicates the brightness obtained by weighting the RGB values of each pixel, for example, by weighting using the following equation (2).

  Brightness = R x 0.30 + G x 0.59 + B x 0.11 (2)

  Prior to detecting the inclination of the original, the end of the original is detected for each line. The document edge is detected as the coordinates of the leftmost pixel and the rightmost pixel among the pixels that change so that the pixel value of the adjacent pixel is larger than a predetermined threshold in each line. The threshold value is selected so that an area other than the original is not detected as an original when the original cover of the image input device 5 is opened halfway and the original is read.

  When document edges are detected for all lines of the document image, the coordinates of the pixels on the uppermost, lower, left, and right sides of the detected pixel coordinates are (EdgeTx, EdgeTy), (EdgeBx), respectively. , EdgeBy), (EdgeLx, EdgeLy), and (EdgeRx, EdgeRy). In this case, the document inclination of the document image is detected as an angle θ corresponding to the tangent represented by the following equation (3).

  tan θ = (EdgeTy−EdgeLy) / (EdgeTx−EdgeLx) (3)

  Note that the value of the angle θ corresponding to tan θ can be read from FIG. However, when the value of the angle θ exceeds 45 °, the angle θ is converted by the following equation (4).

  θ = θ−90 (4)

Hereinafter, an example of a method for detecting the tilt of content will be described.
Prior to detecting the tilt of the content, each pixel value is converted into white / black binarized data depending on whether the pixel value of each pixel of the document image is larger than a predetermined threshold value. When the pixel value is represented by 8 bits, for example, the threshold value is set to 128. Alternatively, an average value of pixel values of each pixel may be calculated and used as a threshold for a plurality of pixels (for example, 25 pixels of 5 × 5) centering on the pixel of interest.

  Next, for each pixel having a pixel value binarized into white and black, a plurality of boundary points between the black pixel and the white pixel are extracted, and the coordinates (x, y) of the point sequence of each boundary point are obtained. For example, in the case of a document including k character strings as contents, (X1, Y1) to (Xk, Yk), which are coordinates of white / black boundary points at the upper end of each character of the character string, are point strings. Coordinates. Then, a regression curve is obtained from the coordinates of the point sequence, and a regression coefficient b of the regression curve is calculated.

  In general, an analysis coefficient b used for analyzing the relationship between two variables x and y is defined by the following equation (5).

  Here, Sx and Sy are the residual sum of squares of the variables x and y, respectively, and Sxy is the sum of the product of the residual of x and the residual of y. Therefore, Sx, Sy, and Sxy are represented by the following equations (6) to (8), respectively.

  From the regression coefficient b calculated in this way, the inclination of the content of the document image is detected as an angle θ corresponding to the tangent represented by the following equation (9).

  tan θ = b (9)

  Note that the value of the angle θ corresponding to tan θ can be read from FIG. 8 as in the case of the document inclination angle described above. When the value of the angle θ exceeds 45 °, θ is converted by the above-described equation (4) as in the case of the angle of inclination of the document.

  FIG. 9 is a flowchart of a main routine showing the processing procedure of the CPU 401 for determining the necessity of correcting the inclination of the document including the content and the amount of inclination of the document including the content. The following processing is executed each time a document image is acquired according to a control program stored in advance in the ROM 402.

  Note that “threshold value T” and “threshold value D” are threshold values that can be input in advance by a user from a numeric keypad (not shown) of the operation panel 6, and their contents (for example, 1 degree and 0.2 degree) are as follows. Stored in the RAM 403. The threshold value may be input from a mouse and a keyboard (not shown) according to a setting screen displayed on the image display device 4, or may be selected from a plurality of numerical values prepared in advance. Further, “correction necessity” and “correction amount” are variables stored in the RAM 403, and whether or not the operation mode set in advance from the operation panel 6 is the “high accuracy mode” is also stored in the RAM 403. To do.

The CPU 401 detects the inclination (α) of the document (step S11), detects the inclination (β) of the content (step S12), and determines whether α is larger than the “threshold value T” (step S13). . When it is determined that the value is not greater than the “threshold value T” (step S13: NO), the CPU 401 determines whether β is greater than the “threshold value T” (step S14). When it is determined that it is not larger than “threshold value T” (step S14: NO), the CPU 401 writes “0” in “necessity of correction” (step S15) and “0” in “inclination amount” (step S15). S16) The process ends.
As described above, when both α and β are not larger than the “threshold value T”, it is not necessary to correct the inclination of the document including the content.

When it is determined in step S14 that β is larger than “threshold value T” (step S14: YES), the CPU 401 determines whether or not the set operation mode is “high accuracy mode” (step S17). When it is determined that the mode is not “high accuracy mode” (step S17: NO), the CPU 401 writes “0” in “correction necessity” (step S18) and “α” in “inclination amount” (step S19). ) End the process.
As described above, when only β is larger than the “threshold value T”, it is not necessary to correct the inclination of the document including the content. In this case, the amount of inclination of the document including the content is assumed to be the inclination (α) of the document considered to have high detection reliability.

When it is determined in step S13 that α is larger than “threshold value T” (step S13: YES), the CPU 401 determines whether β is larger than “threshold value T” (step S20). When it is determined that it is not greater than the “threshold value T” (step S20: NO), the CPU 401 determines whether or not the set operation mode is the “high accuracy mode” (step S21). When it is determined that the mode is not “high accuracy mode” (step S21: NO), the CPU 401 writes “0” in “correction necessity” (step S22) and “β” in “inclination amount” (step S23). ) End the process.
As described above, when only α is larger than the “threshold value T”, it is not necessary to correct the inclination of the document including the content. In this case, the amount of inclination of the document including content is assumed to be the content inclination (β) considered to have high detection reliability.

  When it is determined in step S20 that β is larger than “threshold value T” (step S20: YES), the CPU 401 determines whether or not the difference between α and β is smaller than “threshold value D” (step S24). When it is determined that it is smaller than “threshold D” (step S24: YES), the CPU 401 determines whether or not the set operation mode is “high accuracy mode” (step S25).

If it is determined that the mode is not “high accuracy mode” (step S25: NO), the CPU 401 writes “1” in “necessity of correction” (step S26) and “α (or β)” in “inclination amount”. (Step S27), the process ends.
As described above, when α and β are larger than the “threshold value T” and the difference between them is smaller than the “threshold value D”, it is assumed that the inclination of the document including the content needs to be corrected, and the amount of inclination of the document including the content is included. Is α (or β substantially equal to α).
The inclination amount may be an average value of α and β.

When it is determined in steps S17, S21, and S25 that the mode is “high precision mode” (step S17: YES, step S21: YES, step S25: YES), or the difference between α and β is greater than “threshold D” in step S24. When it is determined that it is not small (step S24: NO), the CPU 401 calls and executes a subroutine related to the preview (step S28), and ends the process.
As described above, when α and β are larger than “threshold value T” and the difference between them is not smaller than “threshold value D”, the preview image is displayed unconditionally. Also, when the “high accuracy mode” is set and α or β is larger than the “threshold value T”, the preview image is positively displayed.

FIG. 10 is a flowchart showing the processing procedure of the CPU 401 relating to the preview subroutine.
When this subroutine is called from the main routine, the CPU 401 generates a preview image P0 that does not correct the inclination of the document including the content (step S31). Thereafter, the CPU 401 determines whether α is larger than the “threshold value T” (step S32). When it is determined that the value is larger than “threshold value T” (step S32: YES), the CPU 401 corrects the inclination of the document including the content by α and generates a preview image P2 (step S33). If it is determined that it is not larger than “threshold value T” (step S32: NO), the CPU 401 copies and generates the preview image P0 to the preview image P2 (step S34).

  When the processes of steps S33 and S34 are completed, the CPU 401 determines whether or not β is larger than “threshold value T” (step S35). If it is determined that the value is larger than “threshold value T” (step S35: YES), the CPU 401 corrects the inclination of the document including the content by β and generates a preview image P1 (step S36). When it is determined that it is not larger than “threshold value T” (step S35: NO), the CPU 401 copies and generates the preview image P0 to the preview image P1 (step S37).

  When the processes in steps S36 and S37 are completed, the CPU 401 displays the preview images P0, P1, and P2 on the LCD screen 4a of the image display device 4 together with the display of “no correction”, “candidate 1”, and “candidate 2”, respectively. It is displayed (step S38). Thereafter, the CPU 401 determines whether or not “no correction” is selected (step S39), and when it is determined that it is selected (step S39: YES), “0” is written to “necessity of correction” (step S40). Further, “0” is written in “inclination amount” (step S41), the subroutine processing is terminated, and the process returns to the main routine.

When it is determined that “no correction” is not selected (step S39: NO), the CPU 401 determines whether “candidate 1” is selected (step S42), and when it is determined that it is selected (step S42). : YES), “1” is written in “necessity of correction” (step S43), “β” is further written in “inclination amount” (step S44), the subroutine processing is terminated, and the process returns to the main routine.
As described above, when “candidate 1” is selected, it is necessary to correct the inclination of the document including the content, and the inclination amount of the document including the content is β.

When it is determined that “candidate 1” is not selected (step S42: NO), the CPU 401 determines whether or not “candidate 2” is selected (step S45), and when it is determined that it is not selected (step S45). Step S45: NO), the CPU 401 returns the process to Step S39. If it is determined that it has been selected (step S45: YES), “1” is written in “necessity of correction” (step S46), “α” is further written in “inclination amount” (step S47), and the subroutine processing ends. And return to the main routine.
Thus, when “candidate 2” is selected, it is necessary to correct the inclination of the document including the content, and the amount of inclination of the document including the content is α.

  Note that, in the above-described subroutine relating to the preview, when generating and displaying a preview image in which the inclination of the document including the content is corrected by α / 2 and β / 2, respectively, before step S35 and step S38, respectively. A step of generating a preview image may be inserted, and the respective preview images may be displayed together in step S38. Further, a step of determining whether or not a candidate corresponding to each preview image has been selected is inserted into the loop formed by steps S39, S42, and S45. “1” may be written in “α”, and α / 2 and β / 2 may be written in “inclination amount”.

As described above, according to the first embodiment, when at least one of the document inclination (α) and the content inclination (β) detected for the document image is not larger than the threshold T, each of α and β is the threshold. When the difference is larger than T and the difference between α and β is smaller than the threshold D, the preview image to be selected is not generated.
As a result, whether α or β is not significant enough to exceed the threshold value T and whether α and β are significant and substantially coincide with each other may be obvious. The preview image itself is not generated as high. For this reason, the user is not required to make a selection. Therefore, when there is a high possibility that the correction of the inclination of the document including the content is not necessary, it is possible to prevent the display image from being displayed and to prevent a reduction in work efficiency.

If the preview image is not generated because α and β are larger than the threshold value T and the difference between α and β is smaller than the threshold value D, the inclination of the document including the content is set to α, β, or an average value of α and β. Only correct.
Therefore, when α and β are significant and α and β substantially match, it is possible to automatically correct the inclination of the document including the content on the assumption that the reliability of the inclination detection result is high.

Furthermore, when the user selects one of the displayed preview images, the selection is accepted, and the original document image includes the content corresponding to the corrected inclination of the selected preview image. Correct the skew of the original.
Therefore, it is possible to correct the inclination of the document and the image based on the inclination expressed in the selected preview image.

Furthermore, when the setting of the high accuracy mode has been received in advance, a plurality of preview images are generated when at least one of α and β is greater than the threshold value T.
Therefore, when the high-accuracy mode is set, it is possible to actively display a plurality of preview images and to ask the user for selection when α or β is significant.

Furthermore, an output image is formed based on the document and the document image in which the inclination of the image is corrected by the image processing apparatus.
Therefore, an image processing apparatus that does not generate a preview image can be applied to a printer apparatus, a digital multi-function peripheral, or the like when it is highly likely that the correction of the inclination of the document including content is obvious.

(Embodiment 2)
The first embodiment is an embodiment in which the image processing apparatus and the image forming apparatus according to the present invention are applied to a digital color multifunction peripheral, whereas the second embodiment is a color image reading apparatus in which the image processing apparatus according to the present invention is applied. It is a form applied to.
FIG. 11 is a block diagram showing a configuration of a color image reading apparatus according to Embodiment 2 of the present invention. In the figure, reference numeral 200 denotes a color image reading device. The color image reading device 200 is an image input device 5 that outputs RGB analog signals as a document image, and an image processing device that acquires the analog signals and outputs RGB digital signals. 2a and an operation panel 6a for receiving operations on these devices.
Note that the operation panel 6a may be included in the image processing apparatus 2a.

  The image processing device 2a includes an A / D conversion unit 20 that converts an analog document image input from the image input device 5 into a digital document image, and an RGB digital signal output from the A / D conversion unit 20. The image input apparatus 5 includes a shading correction unit 21 that removes various distortions generated in the illumination system, the imaging system, and the imaging system, and an input processing unit 22 that performs gamma correction. The RGB digital signal (original image) output from the input processing unit 22 is stored in the transmission / reception unit / storage unit 23 having a large-capacity storage device such as a hard disk, and is read from the transmission / reception unit / storage unit 23. The data is supplied to the document correction unit 25 via the document detection unit 24.

A display control unit 26 that outputs a preview image (display image) to an external display such as an LCD is connected to the document detection unit 24 and the document correction unit 25. Each unit of the above-described image processing apparatus 2a is connected to a control unit 40 including a CPU 401, a ROM 402 that stores information such as a program, and a RAM 403 that stores temporarily generated information. The operation of each unit is controlled according to a control program stored in the ROM 402 in advance.
The display may be installed in the main body of the color image reading apparatus 200.

The RGB digital signals output from the document correction unit 25 are sent to an external computer, a hard disk, and a network such as an intranet or the Internet via a device interface and a network interface (not shown).
In addition, the same code | symbol is attached | subjected to the location corresponding to Embodiment 1, and the detailed description is abbreviate | omitted.

As described above, according to the second embodiment, the inclination of the original and the image is corrected by the image processing apparatus for the read original image.
Therefore, an image processing apparatus that does not generate a preview image can be applied to the image reading apparatus when it is highly likely that the correction of the inclination of the document including the content is obvious.

  The present invention provides a computer-readable recording medium on which program code (executable program, intermediate code program, source program) to be executed by a computer is recorded in accordance with the above-described original and image inclination determination results. It is also possible to record an image processing method for switching between image generation and non-generation. Accordingly, it is possible to provide a portable recording medium on which a program for performing an image processing method for switching between generation and non-generation of a display image according to the determination result of the document and the image inclination is portable.

  The recording medium may be, for example, a program medium such as a ROM, or a program medium that can be read by inserting the recording medium into a program reading device (not shown) provided as an external storage device. In any case, the stored program code may be configured to be accessed and executed by the CPU, or the program code may be read and downloaded to the program storage area of the RAM and executed. It may be. It is assumed that this download program is stored in the main device in advance.

  The program medium is a recording medium configured to be separable from the main body, such as a magnetic tape, a tape system such as a cassette tape, a magnetic disk represented by a floppy (registered trademark) disk and a hard disk, CD-ROM / MO / MD. / Disk systems such as optical disks represented by DVD, IC cards (including memory cards), card systems such as optical cards, mask ROM, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory) The program code may be fixedly carried on a semiconductor memory medium such as a flash ROM.

    The program medium may be a medium in which the program code is fluidly supported so that the program code can be downloaded from a communication network including the Internet. When downloading the program code from the communication network in this way, the download program may be stored in the main device in advance or may be installed from another recording medium. The present invention can also be realized in the form of a computer data signal in which the program code is embedded in a carrier wave and transmitted electronically.

  The recording medium is read by, for example, a program reading device provided in a digital color multifunction peripheral and a computer system, and the above-described image processing method is executed by a CPU. The computer system includes an image input device such as a flatbed scanner, a film scanner, and a digital camera, a computer that performs various processes such as the image processing method by loading a predetermined program, and a CRT display that displays the processing results of the computer. An image display device such as a liquid crystal display, and a printer that outputs the processing results of the computer to paper or the like. Furthermore, a communication means such as a network card and a modem for connecting to a server or the like via a network is provided.

1 is a block diagram illustrating a configuration of a digital color multifunction peripheral according to a first embodiment of the present invention. It is a typical front sectional view showing the composition of an image input device. FIG. 3 is a block diagram showing a main part configuration related to document detection and inclination correction. It is explanatory drawing which shows the relationship between the inclination of a document and content. It is explanatory drawing which shows the example of the process with respect to the state of the inclination of a document and content. It is explanatory drawing which shows the example which produces | generates a some preview image, displays it on an image display apparatus, and asks a user for selection. It is explanatory drawing which shows the method of detecting the inclination of a document as an angle. It is a graph which shows the relationship between a tangent and the angle corresponding to the tangent. 6 is a flowchart of a main routine showing a CPU processing procedure for determining whether or not the inclination of a document including content needs to be corrected and the amount of inclination of the document including the content. It is a flowchart which shows the process sequence of CPU which concerns on the subroutine of a preview. It is a block diagram which shows the structure of the color image reading apparatus which concerns on Embodiment 2 of this invention.

Explanation of symbols

100 Digital color MFP (image forming device)
200 Color Image Reading Device 2, 2a Image Processing Device 20 A / D Conversion Unit (Means for Acquiring Document Image)
24 Document detection unit 241 Document tilt detection unit (detection means)
242 Content inclination detection unit (detection means)
243 Inclination determination unit (first determination means, second determination means)
25 Document correction section (correction means)
26 Display control unit (generation means)
3 Image output device (image forming means)
4. Image display device (means for displaying display image, means for accepting selection)
4a LCD screen 40 Control unit 401 CPU
402 ROM
403 RAM
5 Image input device 6, 6a Operation panel (means for accepting settings)

Claims (12)

Means for acquiring a document image scanned and read from a document on which an image is formed, detection means for detecting the document and the inclination of the image with respect to the scanning direction from the document image acquired by the means, and the detection means Generating means for generating a plurality of display images representing the respective inclinations detected by the image forming means, and the original of the original image and the image based on the inclination expressed in one of the display images generated by the generating means. In an image processing apparatus comprising correction means for correcting inclination,
First determination means for determining whether each of the document and the inclination of the image detected by the detection means is greater than a first threshold;
Second determination means for determining whether or not the difference between the inclinations of the original and the image is smaller than a second threshold when the first determination means determines that both are large,
When it is determined that the second determination unit is small, or when the first determination unit determines that at least one is not large, the generation unit is configured not to generate the display image. Image processing device.   When it is determined that the second determination unit is small, the correction unit corrects the document and image inclinations of the document image based on the document or image inclination detected by the detection unit. The image processing apparatus according to claim 1. Means for displaying a plurality of display images generated by the generating means;
The image processing apparatus according to claim 1, further comprising: means for receiving selection of a display image displayed by the means. Means for accepting a setting relating to inclination correction;
When the means accepts the setting, the generating means generates the plurality of display images when the first determining means determines that at least one of them is larger. The image processing apparatus according to any one of 1 to 3. An image processing apparatus according to any one of claims 1 to 4,
An image forming apparatus comprising: an image forming unit that forms an output image based on a document image whose inclination is corrected by the image processing apparatus. A document image obtained by scanning and reading a document on which an image is formed is acquired, the document and the inclination of the image with respect to the scanning direction are respectively detected from the acquired document image, and a plurality of displays expressing each detected inclination In the image processing method of generating an image for use in the generation step, and correcting the document of the document image and the tilt of the image in the correction step based on the tilt expressed in one of the display images generated in the generation step.
A first determination step of determining whether each of the detected document and image inclination is greater than a first threshold;
A second determination step for determining whether or not the difference between the inclination of the document and the image is smaller than a second threshold when it is determined that both are large in the first determination step;
When it is determined that the second determination step is small, or when it is determined that at least one is not large in the first determination step, the display image is not generated in the generation step. Image processing method.   The document and image inclination of the document image are corrected in the correction step based on the detected document or image inclination when determined to be small in the second determination step. 6. The image processing method according to 6. Displaying a plurality of display images generated in the generating step;
The image processing method according to claim 6, further comprising a step of receiving selection of a display image displayed in the step. Including a step of accepting a setting relating to inclination correction;
The plurality of display images are generated in the generation step when the setting is accepted in the step and it is determined in the first determination step that at least one is larger. The image processing method according to any one of 6 to 8. A computer that acquires image data and performs image processing causes a document on which an image is formed to be scanned and read from a document image to detect the inclination of the document and the image with respect to the scanning direction, and each detected inclination is detected. A plurality of expressed display images are generated in the generation step, and the original of the original image and the inclination of the image are corrected in the correction step based on the inclination expressed in one of the display images generated in the generation step. Computer program
A first determination step for causing the computer to determine whether or not each of the detected document and image inclination is greater than a first threshold;
A second determination step for causing the computer to determine whether or not the difference between the inclinations of the original and the image is smaller than a second threshold when the computer determines that both are large in the first determination step;
When it is determined that the computer is small in the second determination step, or when it is determined that at least one is not large in the first determination step, the computer does not generate the display image in the generation step. A computer program characterized by the above.   When the computer determines that the second determination step is small, the computer is configured to correct the document image and the image inclination of the document image based on the detected document or image inclination in the correction step. The computer program according to claim 10.   The computer program of Claim 10 or 11 is recorded, The computer-readable recording medium characterized by the above-mentioned.

Images