JP4434803B2 - Image processing apparatus, image processing method, program, and storage medium - Google Patents

Description

  The present invention relates to an image processing apparatus, an image processing method, a program, and a storage medium that automatically detect and correct a tilt of a document image or the like.

  By automatically correcting the inclination of the document image read from the scanner or the like, it is possible to improve the accuracy of document image analysis processing such as area division and character recognition. For example, the document direction is automatically detected, the projections in the row direction are obtained in two search windows arranged along the row direction, one window is fixed, and the other window is perpendicular to the row direction. A technique is disclosed in which the tilt amount of a document image is obtained from the amount of shift in the vertical direction of two windows and the distance in the row direction when the correlation between projections is maximized while shifting in the direction (see, for example, Patent Document 1). ).

  According to the invention described in Patent Document 1, the projection indicates the position of the character line in the window, and the case where the correlation is maximized is the state where the line position matches. Then, the inclination of the document image can be determined from the inclination of the character line.

Further, a plurality of sets are set so that the set of windows extends over the entire document image, and the inclination as the document image is obtained using the magnitude of the inclination obtained from the plurality of positions. As described above, according to the invention described in Patent Document 1, by using the projection in the row direction in the set window on the character image, the character image can be processed at a high processing speed and with a small storage area. A tilt detection method is disclosed.
Japanese Patent Laid-Open No. 9-6914

  However, in the invention described in Patent Document 1, when there is a ruled line perpendicular to the row direction of a table or the like in the set window, a projection is acquired over the entire height of the window by projection by the ruled line, There was a drawback that the projection in the line direction of the characters could not be extracted properly.

  The present invention has been made in view of such circumstances, and an image processing apparatus, an image processing method, a program, and a program that can suitably determine the inclination of a document image including a ruled line. An object is to provide a storage medium.

In order to solve the above-described problem, the present invention is an image processing apparatus that determines the inclination of an input document image , and includes a plurality of pairs of two partial image regions that are arranged at a predetermined distance in the horizontal direction. A setting unit that sets the pair of images at a plurality of locations in the document image and, for each partial image area set by the setting unit, detects a projection indicating a pixel row in which the black pixel exists in the partial image region The length of the projection detected by the detecting means is shorter than a predetermined length or the length extending over the entire height of the partial image area for each of the detecting means and the pairs set at the plurality of locations. If there is a character line projection determining unit that determines that the projection of the character line cannot be specified, and the partial image region that is determined by the character line projection determining unit that the projection of the character line cannot be specified. In the area Determining an acquiring means for acquiring a histogram by counting the number of black pixels in a pixel row, based on the histogram obtained by the acquisition unit, whether or not include the partial image areas character row direction of the ruled line in If the ruled line determining means and the ruled line determining means determine that a ruled line in the character line direction is included in the partial image area , a pixel row whose histogram frequency acquired by the acquiring means is equal to or greater than a predetermined threshold is selected. The two partial image areas detected by the detection means with respect to a pair of partial image areas when it is determined that the projection of the character line can be specified by the specifying means for specifying the projection of the ruled line and the character line projection determining means A correlation between the respective projections is obtained, and it is determined that the projection of the character line cannot be specified by the character line projection determining unit, and a ruled line in the character line direction is determined by the ruled line determining unit. For a pair of partial image areas when determined to be rare, a correlation between the projections of the two partial areas specified by the specifying unit is obtained, and the obtained correlation and an interval between the two partial areas are determined. A local inclination angle calculating means for obtaining an inclination angle based on the character line, and determining that the projection of the character line cannot be specified by the character line projection determining means and determining that the ruled line determination means does not include a ruled line in the character line direction With respect to the pair of partial image areas in the case of being performed, based on the control unit for controlling not to perform the processing in the local tilt angle calculation unit, and the tilt angle calculated by the local tilt angle calculation unit, Determining means for determining the inclination of the document image.

The present invention is also an image processing method of an image processing apparatus for determining the inclination of a document image, wherein the setting means of the image processing apparatus extracts two partial image areas arranged at a predetermined distance in the horizontal direction. As a pair, a setting step for setting a plurality of pairs in each of a plurality of locations in the document image, and a detection unit of the image processing apparatus, for each partial image region set in the setting step, in the partial region A detection step of detecting a projection indicating a pixel row in which a black pixel is present, and a projection detected by the character row projection determination unit of the image processing device in the detection step for each of the pairs set in the plurality of locations. A character line projection determining step for determining that the projection of the character line cannot be specified, if the length of the image processing unit is shorter than a predetermined length or is a length extending over the entire height of the partial image region; Acquisition means Acquisition for obtaining a histogram by counting the number of black pixels in each pixel row in the partial image area for which the projection of the character line is determined not to be specified in the character line projection determination step a step, line determination unit of the image processing apparatus, based on the histogram obtained by the obtaining step, a line determination step of determining whether or not include the partial image areas character row direction of the ruled line in the When the specifying unit of the image processing apparatus determines that the ruled line determination step includes a ruled line in the character line direction in the partial image area , a pixel whose histogram frequency acquired in the acquisition step is equal to or greater than a predetermined threshold value a specifying step of specifying the row as the projection borders, local tilt angle calculation means of the image processing apparatus, it is determined that the projection of the character line can be identified by the character line projection determination step For the pair of partial image areas, a correlation between the projections of the two partial image areas detected in the detection step is obtained, and it is determined in the character line projection determination step that the projection of the character line cannot be specified and For the pair of partial image areas when it is determined that the ruled line determination process includes a ruled line in the character line direction, the correlation between the projections of the two partial areas specified in the specific process is obtained, and the obtained correlation And a local inclination angle calculation step for obtaining an inclination angle based on the interval between the two partial areas, and the control means of the image processing apparatus cannot identify the projection of the character line in the character line projection determination step. For the pair of partial image areas when it is determined and the ruled line determining step determines that the ruled line in the character line direction is not included, the processing in the local inclination angle calculating step is performed. And a determination step of determining the inclination of the document image based on the inclination angle calculated in the local inclination angle calculation step. Features.

Further, according to the present invention, there is provided a setting means for setting a plurality of the pairs at a plurality of locations in the document image, with the computer as a pair of two partial image regions arranged at a predetermined distance in the horizontal direction, For each partial image area set by the setting means, detection means for detecting a projection indicating a pixel row in which the black pixel exists in the partial image area, and the detection for each of the pairs set in the plurality of locations A character line projection determining means for determining that the projection of the character line cannot be specified when the length of the projection detected by the means is shorter than a predetermined length or is a length extending over the entire height of the partial image area; A histogram is obtained by counting the number of black pixels in each pixel row in the partial image area for which the projection of the character line is determined not to be specified by the character line projection determining means. Obtaining means, ruled line judging means for judging whether or not a ruled line in the character line direction is included in the partial image area based on the histogram obtained by the obtaining means, and the partial image area by the ruled line judging means If it is determined that a ruled line in the character line direction is included therein, a specifying unit that specifies a pixel line whose histogram frequency acquired by the acquiring unit is equal to or greater than a predetermined threshold as a ruled line projection, and the character line projection determination A correlation between the projections of the two partial image areas detected by the detection means for a pair of partial image areas when it is determined that the projection of the character line can be specified by the means, and the character line projection determination means The partial image area pair when the projection of the character line is determined to be unidentifiable and the ruled line determination means determines that the ruled line in the character line direction is included. A local inclination angle calculating means for obtaining a correlation between the projections of the two partial areas specified by the means and obtaining an inclination angle based on the obtained correlation and an interval between the two partial areas; and the character With respect to the pair of partial image areas when it is determined that the projection of the character line cannot be specified by the line projection determination unit and the ruled line determination unit determines that the ruled line in the character line direction is not included, the local inclination angle A program for causing the processing to be performed as a determination unit that determines the inclination of the document image based on the inclination angle calculated by the local inclination angle calculation unit ; It is characterized by being.

  Furthermore, the present invention is a computer-readable storage medium storing the above program.

  According to the present invention, it is possible to suitably obtain the inclination of a document image including a ruled line.

  Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

<First Embodiment>
FIG. 1 is a block diagram showing a configuration of an image processing apparatus according to the first embodiment of the present invention. In FIG. 1, reference numeral 101 denotes a CPU that controls the entire image processing apparatus according to a control program stored in the ROM 102. Reference numeral 102 denotes a ROM that stores a control program of the image processing apparatus executed by the CPU 101 in accordance with a processing procedure shown in a flowchart to be described later. Reference numeral 103 denotes a RAM for storing document images and the like, and 104 denotes an external storage device such as a magnetic disk. Furthermore, 105 is a display, 106 is a keyboard, 107 is a pointing device such as a mouse, and 108 is a scanner for reading a document image from a paper document or the like.

  Furthermore, the CPU 101, ROM 102, RAM 103, external storage device 104, display 105, and scanner 108 described above are connected to each other via a bus 110.

  Note that the image processing performed by the image processing apparatus according to the present embodiment can also be performed by a general-purpose computer. In this case, a control program provided on a storage medium or the like is stored in the external storage device 104 and the operator's It may be configured to be executed by the CPU 101 according to an instruction or the like. Reference numeral 109 denotes a network interface (I / F) that communicates with an information processing apparatus or the like that exists in a remote place, and that reads and writes programs and data, and is connected to the bus 110. Has been.

  The devices such as the scanner 108 and the display 105 may not be directly connected to the bus 110 but may be connected via the network I / F 109.

  The image processed by the image processing apparatus is an image optically read from a paper document or the like by the scanner 108, an image stored in the external storage device 104, or a network from another image input device or the like. What was received via I / F109 can be used. Further, in the present embodiment, the inspection area for detecting the tilt and the document direction in the inspection area are determined for the image obtained in this manner using a known technique. For example, the inspection area can be determined by removing margins of the input document image, or can be determined by extracting a text area from layout information about the document.

  FIG. 2 is a flowchart for explaining a processing procedure for detecting the inclination of the input image from the inspection area by the image processing apparatus according to the first embodiment. First, a detection position for detecting a local inclination of a character line or the like existing in the inspection area is determined for the inspection area in the document image determined using a known technique (step S201). For example, the detection positions are distributed at equal intervals over the entire inspection region, or are varied using random numbers.

  Next, a detection window having a predetermined size is set at the detection position determined in step S201 (step S202). In this embodiment, as an example, a rectangular partial image region is used as a detection window. The direction of the detection window to be set is determined according to the document direction.

  In addition, the detection window that is paired with the detection window set in step S202 is set to a position that is separated by a predetermined distance in the row direction on the document image (step S203). Then, projections in the row direction are obtained for the respective detection windows set in the inspection area (step S204). Here, the projection means that each pixel in the detection window is scanned in the row direction, and if there is a black pixel (a pixel constituting the character portion), it is determined that the row is projected. As a result, the height of the character line existing in the detection window is obtained as a projection.

  FIG. 4 is a diagram for explaining projection in the row direction obtained from characters in the detection window. In FIG. 4, 401 is an initial state of the detection window set in the inspection area in step S202, and 402 shows an example of the acquired projection. Here, each pixel in the detection window is scanned in the row direction, and a pixel row in which a pixel (for example, a black pixel) constituting the character exists is projected, so that the character row existing in the detection window Height is obtained as a projection.

  Then, it is determined whether or not a line projection is included in the detection window so as to be specified from the acquired projection (step S205). Here, when a character line is appropriately included in the detection window (so that it can be specified), a projection corresponding to the height of the character line is detected. However, if the projection does not exist in the detection window, its length is short, or the length of the detection window extends to the entire height of the detection window due to the presence of ruled lines in the direction perpendicular to the character line, In some cases, it is not possible to specify the projection of the height of. Therefore, in the present embodiment, when such an inappropriate projection is detected, it is determined that the line projection is not included (that is, cannot be specified).

  As a result, when it is determined in step S205 that the line projection is included in the detection window (Yes), the process proceeds to step S209. Then, one detection window is fixed, the other detection window is shifted in the vertical direction with respect to the line direction, and the amount of deviation that maximizes the correlation between the projections in the line direction of the character lines acquired for each detection window is determined. Obtained (step S209). As a result, the local inclination angle is obtained from the amount of deviation at the time of maximum correlation and the interval between the two detection windows (step S210). Then, the obtained angle is stored (step S211).

  FIG. 6 is a diagram for explaining the correlation of the projection of the detection window in the image processing apparatus according to the first embodiment. In FIG. 6A, 601a is a set first detection window, and 602a is a projection in the detection window 601a. Similarly, 601b is a second detection window set as a pair of detection windows 601a, and 602b is a projection in the detection window 601b. FIG. 6B is a graph 605 showing the detection window 604 shifted up and down with respect to the fixed detection window 607 and the magnitude of the correlation. Here, the inclination angle θ has a relationship of tan θ = t / d using the shift amount t when the correlation is maximum and the distance d of the detection window. Note that if the shift upward to t is positive and the shift downward is negative, it is possible to determine which is inclined by the sign.

  On the other hand, if it is determined in step S205 that the line projection is not included in the detection window (No), the pixels constituting the line-direction characters and ruled lines in the detection window (that is, pixels that are not background pixels) are displayed. The counted histogram is acquired (step S206). Then, it is determined from the acquired histogram whether or not a ruled line in the character line direction such as a table is included in the detection window (step S207). Whether or not a ruled line is included in the detection window is determined when, for example, black pixels (that is, pixels constituting the ruled line in the document image) are detected for all or most of the horizontal direction of the detection window. It is determined that a ruled line in the character line direction is included.

  As a result, when it is determined that the ruled line in the character line direction is not included (No), the inclination detection process using the detection window ends, and the process proceeds to step S212. On the other hand, if it is determined that the ruled line in the character line direction is included (Yes), the following processing is performed to obtain a projected part of only the ruled line part in the character line direction (step S208).

  FIG. 5 is a diagram for explaining the projection information acquired from the histogram in the row direction in the detection window. In FIG. 5, reference numeral 501 denotes a detection window set in a ruled line portion on the document image, and 502 denotes a histogram in the row direction in the detection window 501. Reference numeral 503 denotes a threshold value for determining a ruled line portion in the character line direction with respect to the histogram 502 determined from the width of the detection window 501. In this embodiment, the threshold value 503 is a portion having a frequency equal to or higher than the threshold value 503. It is assumed that there is a ruled line in the character line direction.

  On the other hand, reference numeral 504 denotes a projection threshold for the ruled line in the character line direction determined from the width of the detection window 501 and the frequency of the histogram in the detection window 501, and a portion having a frequency equal to or higher than the threshold 504 Acquired as a projection part by ruled lines in the row direction. For example, the threshold value 504 is determined from the threshold value 503 and the histogram frequency in the projection in the character line direction within the detection window. Then, a projected portion in the character line direction having a frequency equal to or higher than the threshold value 504 in the histogram is specified as a ruled line projection in the character line direction. Alternatively, the projection may be determined by multiplying the value of the threshold value 503 by a coefficient, or by extending the projection of the portion above the threshold value 503 by a predetermined length. As described above, in this embodiment, the inclination of the character line and the document image is calculated using the projection information in the detection window and the projection information obtained from the histogram.

  Then, one detection window is fixed, and the other detection window is shifted in the vertical direction with respect to the line direction, and the amount of deviation that maximizes the correlation of projections with the ruled lines in the line direction obtained for each detection window is determined. Obtained (step S209). As a result, the local inclination angle is obtained from the amount of deviation at the time of maximum correlation and the interval between the two detection windows (step S210). Then, the obtained angle is stored (step S211). The calculation capacity of the inclination of the document image from the correlation of the projection by the ruled line in the character line direction obtained from both detection windows is calculated from the correlation of the projection of the character line described above with reference to FIG. It is the same as the capacity.

  Then, it is determined whether or not the inclination angles at all detection positions have been obtained (step S212). As a result, when the detection position for which the inclination angle has not yet been obtained remains (No), the process returns to step S201 again, and the processes of steps S201 to S211 described above are repeated for the next detection position. On the other hand, when all are detected (Yes), the inclination angle of the input image is determined from the stored local inclination angle (step S213). For example, they can be determined by using the average value or median value of all inclination angles.

  In addition, when it becomes impossible to obtain an inclination in the processing of each step described above, for example, when an appropriate projection cannot be obtained or the correlation is insufficient, the local inclination angle in the detection window is obtained. Instead, the next detection position may be used. Further, when the local tilt angle stored in step S213 is small, it may be determined that the accuracy cannot be expected and the tilt angle of the input image has not been obtained.

  As described above, the projection of the character line and the projection of the ruled line are used for the document image including the ruled line in the vertical direction and the horizontal direction of the table or the like by the image processing by the image processing apparatus according to the present embodiment. The inclination can be obtained with appropriate and high accuracy.

  In the above-described embodiment, the description is given with the minimum configuration requirements for implementing the technical idea of the present invention. However, for example, an image processing program for performing processing for implementing the present invention on a general-purpose computer, etc. The data may be provided from the outside, or may be stored in advance in the external storage device 107 and stored in the RAM 103. Further, an input image stored in advance in the external storage device 107 may be processed.

<Second Embodiment>
Next, another embodiment executed by an image processing apparatus similar to the image processing apparatus shown in FIG. 1 will be described. FIG. 3 is a flowchart for explaining a processing procedure for detecting the inclination of the document image from the inspection area by the image processing apparatus according to the second embodiment.

  First, for the inspection area determined using a known technique in the document image, detection for detecting a local inclination of a character line or the like existing in the inspection area as in the first embodiment. The position is determined (step S301). For example, the detection positions are distributed at equal intervals over the entire inspection region, or are varied using random numbers.

  Next, a detection window having a predetermined size is set at the detection position determined in step S301 (step S302). In this embodiment, as an example, a rectangular partial image region is used as a detection window. Then, as in the first embodiment, the detection window that is paired with the detection window set in step S302 is set at a position separated by a predetermined distance in the row direction on the document image (step S303).

  Next, as in the first embodiment, a histogram in the row direction is acquired for the installed detection window (step S304). Then, similarly to the first embodiment, it is determined from the histogram whether or not a ruled line in the character line direction is included in the detection window (step S305). As a result, when it is determined that the ruled line in the character line direction is included (Yes), the projection of the ruled line part in the character line direction is acquired (step S306), respectively, as in the first embodiment. The amount of deviation that maximizes the correlation of projections with the ruled lines in the character line direction obtained for the detection window is obtained (step S308).

  On the other hand, if it is determined in step S305 that the ruled line in the character line direction is not included, the projection in the line direction in each detection window is acquired (step S307), as in step S204. A deviation amount that maximizes the correlation of the projection in the line direction of the character line acquired for the window is obtained (step S308).

  In step S308, after obtaining the deviation amount that maximizes the correlation between the projections of both detection windows, the local inclination angle is calculated from the deviation amount at the time of the maximum correlation and the interval between the two detection windows in the same manner as in the first embodiment. Obtained (step S309). Then, as with step S211, the obtained angle is stored (step S310).

  Then, it is determined whether or not the inclination angles at all detection positions have been obtained (step S311). As a result, when the detection position for which the inclination angle has not yet been obtained remains (No), the process returns to step S301 again, and the processes of steps S301 to S310 described above are repeated for the next detection position. On the other hand, if all are detected (Yes), the inclination angle of the input image is determined from the stored local inclination angle (step S312). For example, they can be determined by using the average value or median value of all inclination angles.

  As described above, even when the image processing apparatus according to the second embodiment is used, a document image including ruled lines in the vertical direction and the horizontal direction of a table or the like as in the first embodiment. Also, the inclination can be determined appropriately and with high accuracy using the projection of the character line and the projection of the ruled line.

<Other embodiments>
FIG. 7 is a diagram for explaining an example of a memory map of a storage medium that stores various data processing programs that can be read by the image processing apparatus according to the present invention. That is, a program as shown in FIG. 7 is stored in the image processing apparatus shown in FIG. 1, and the process described in the first embodiment is selectively performed by a user who uses the apparatus. Alternatively, the processing described in the second embodiment may be performed.

  Moreover, in each embodiment mentioned above, which detection window may be fixed and which detection window may be shifted.

  In the embodiment described above, when the width of the ruled line is small, there is a possibility that a sufficient accumulated value (histogram) of pixels in the row direction cannot be obtained depending on the degree of inclination of the document image. Therefore, the dilation processing of each pixel constituting the character or ruled line in the detection window may be performed before the above-described processing of taking the histogram. This process is effective even if the expansion process is performed on the character portion, because the influence on the shape of the histogram is considered to be lower than the effect obtained by the ruled line portion with a higher cumulative value.

  As described above, the embodiment has been described in detail. However, the present invention can take an embodiment as a system, apparatus, method, program, storage medium, or the like, and specifically includes a plurality of devices. The present invention may be applied to a system that is configured, or may be applied to an apparatus that includes a single device.

  In the present invention, a software program (in the embodiment, a program corresponding to the flowchart shown in the drawing) that realizes the functions of the above-described embodiment is directly or remotely supplied to the system or apparatus, and the computer of the system or apparatus Is also achieved by reading and executing the supplied program code.

  Accordingly, since the functions of the present invention are implemented by computer, the program code installed in the computer also implements the present invention. In other words, the present invention includes a computer program itself for realizing the functional processing of the present invention.

  In that case, as long as it has the function of a program, it may be in the form of object code, a program executed by an interpreter, script data supplied to the OS, or the like.

  As a recording medium for supplying the program, for example, floppy (registered trademark) disk, hard disk, optical disk, magneto-optical disk, MO, CD-ROM, CD-R, CD-RW, magnetic tape, nonvolatile memory card ROM, DVD (DVD-ROM, DVD-R) and the like.

  As another program supply method, a client computer browser is used to connect to an Internet homepage, and the computer program of the present invention itself or a compressed file including an automatic installation function is downloaded from the homepage to a recording medium such as a hard disk. Can also be supplied. It can also be realized by dividing the program code constituting the program of the present invention into a plurality of files and downloading each file from a different homepage. That is, the present invention includes a WWW server that allows a plurality of users to download a program file for realizing the functional processing of the present invention on a computer.

  In addition, the program of the present invention is encrypted, stored in a storage medium such as a CD-ROM, distributed to users, and key information for decryption is downloaded from a homepage via the Internet to users who have cleared predetermined conditions. It is also possible to execute the encrypted program by using the key information and install the program on a computer.

  In addition to the functions of the above-described embodiments being realized by the computer executing the read program, the OS running on the computer based on the instruction of the program is a part of the actual processing. Alternatively, the functions of the above-described embodiment can be realized by performing all of the processes.

  Furthermore, after the program read from the recording medium is written in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer, the function expansion board or The CPU or the like provided in 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.

1 is a block diagram illustrating a configuration of an image processing apparatus according to a first embodiment of the present invention. It is a flowchart for demonstrating the process sequence for detecting the inclination of an input image from the test | inspection area | region by the image processing apparatus which concerns on 1st Embodiment. 10 is a flowchart for explaining a processing procedure for detecting a tilt of a document image from within an inspection area by an image processing apparatus according to a second embodiment. It is a figure for demonstrating the projection of the line direction obtained from the character in a detection window. It is a figure for demonstrating the projection information acquired from the histogram of the row direction in a detection window. It is a figure for demonstrating the correlation of the projection of the detection window in the image processing apparatus which concerns on 1st Embodiment. It is a figure for demonstrating an example of the memory map of the storage medium which stores the various data processing program which can be read with the image processing apparatus which concerns on this invention.

Explanation of symbols

101 CPU
102 ROM
103 RAM
104 External storage device 105 Display 106 Keyboard 107 Pointing device 108 Scanner 109 Network interface 110 Bus

Claims (8)

An image processing apparatus for determining an inclination of an input document image,
A setting means for setting a plurality of the pairs in each of a plurality of locations in the document image, with two partial image areas arranged at a predetermined distance in the horizontal direction as a pair ;
For each partial image area set by the setting means, detecting means for detecting a projection indicating a pixel row in which black pixels exist in the partial image area ;
For each of the pairs set in the plurality of places, if the length of the projection detected by the detection means is shorter than a predetermined length or the length extending over the entire height of the partial image area, A character line projection judging means for judging that the projection of the line cannot be specified;
Acquisition for obtaining a histogram by counting the number of black pixels in each pixel row in the partial image area for which the projection of the character line is determined not to be specified by the character line projection determining means Means,
Based on the histogram obtained by the obtaining unit, a line determination means for determining whether or not include the partial image area in the character line direction of the ruled line,
When it is determined by the ruled line determination means that a ruled line in the character line direction is included in the partial image area , a pixel line whose histogram frequency acquired by the acquisition means is equal to or greater than a predetermined threshold is specified as a ruled line projection . Specific means,
For the pair of partial image areas when it is determined that the projection of the character line can be specified by the character line projection determination means, the correlation between the projections of the two partial image areas detected by the detection means is obtained, A pair of partial image areas when the projection of the character line is determined not to be specified by the character line projection determination unit and the ruled line determination unit determines that the ruled line in the character line direction is included is specified by the specification unit. A local inclination angle calculation means for obtaining a correlation between the projections of the two partial areas and obtaining an inclination angle based on the obtained correlation and an interval between the two partial areas;
Regarding the pair of partial image areas when it is determined by the character line projection determining means that the projection of the character line cannot be specified and the ruled line determining means determines that the ruled line in the character line direction is not included, Control means for controlling so as not to perform processing in the tilt angle calculation means;
An image processing apparatus comprising: a determination unit that determines the inclination of the document image based on the inclination angle calculated by the local inclination angle calculation unit . The line determination unit, by comparing the frequency of the histogram obtained by the partial image area threshold and the acquisition means is determined based on the width of the character row direction of the ruled line to the partial image area The image processing apparatus according to claim 1 , wherein it is determined whether or not it is included. When the local inclination angle calculation means acquires one of the two partial image areas and vertically moves the other to obtain a correlation of projections detected from the respective partial image areas, and the correlation is maximized. of the positional relationship between the respective partial image region, on the basis of said distance, the image processing apparatus according to claim 1 or 2, characterized in that determining said tilt angle. An image processing method of an image processing apparatus for determining the inclination of a document image,
A setting step in which the setting unit of the image processing apparatus sets a plurality of the pairs in each of a plurality of locations in the document image, with two partial image regions arranged at a predetermined distance in the horizontal direction as a pair ;
A detecting step for detecting, for each partial image region set in the setting step, a projection indicating a pixel row in which the black pixel exists in the partial region ;
The character line projection determining means of the image processing apparatus may detect that the length of the projection detected in the detection step is shorter than a predetermined length or the height of the partial image region for each of the pairs set at the plurality of locations. If the length extends over the entire length, the character line projection determination step for determining that the projection of the character line cannot be specified,
The acquisition unit of the image processing device calculates the number of black pixels in each pixel row in the partial image area for the partial image area determined in the character line projection determination step that the projection of the character line cannot be specified. An acquisition step of acquiring a histogram by counting;
Line determination means of the image processing apparatus, based on the histogram obtained by the obtaining step, a line determination step of determining whether or not include the partial image areas character row direction of the ruled line in,
When the specifying unit of the image processing apparatus determines that the ruled line determination step includes a ruled line in the character line direction in the partial image area, the frequency of the histogram acquired in the acquisition step is equal to or greater than a predetermined threshold. A specific step of identifying a pixel row as a ruled line projection ;
When the local inclination angle calculation means of the image processing apparatus determines that the projection of the character line can be specified in the character line projection determination step, the pair of partial image areas detected in the detection step A correlation between the projections of each partial image region is obtained, and it is determined that the projection of the character line cannot be specified in the character line projection determination step and the ruled line determination step determines that a ruled line in the character line direction is included. For a pair of partial image areas, a local correlation is obtained by calculating a correlation between the projections of the two partial areas specified in the specifying step and calculating an inclination angle based on the calculated correlation and an interval between the two partial areas. The step of calculating the tilt angle,
A partial image when the control means of the image processing device determines that the projection of the character line cannot be specified in the character line projection determination step and that the ruled line determination step does not include a ruled line in the character line direction For the pair of regions, a control step for controlling not to perform the processing in the local tilt angle calculation step;
An image processing method comprising: a determining step in which the determining means of the image processing apparatus determines the tilt of the document image based on the tilt angle calculated in the local tilt angle calculating step . Wherein the line determination step, said part by comparing the frequency of the histogram obtained by the image region width threshold defined based on the said acquisition means, character row direction of the ruled line to the partial image area The image processing method according to claim 4 , wherein it is determined whether or not an image is included. In the local tilt angle calculation step, when one of the two partial image areas is fixed and the other is vertically moved to obtain a correlation of projections detected from the respective partial image areas, the correlation is maximized. 6. The image processing method according to claim 4 , wherein the inclination angle is obtained based on a positional relationship between the partial image areas and the interval . Computer
A setting means for setting a plurality of the pairs in each of a plurality of locations in the document image, with two partial image areas arranged at a predetermined distance in the horizontal direction as a pair;
For each partial image area set by the setting means, detecting means for detecting a projection indicating a pixel row in which black pixels exist in the partial image area;
For each of the pairs set in the plurality of places, if the length of the projection detected by the detection means is shorter than a predetermined length or the length extending over the entire height of the partial image area, A character line projection judging means for judging that the projection of the line cannot be specified;
Acquisition for obtaining a histogram by counting the number of black pixels in each pixel row in the partial image area for which the projection of the character line is determined not to be specified by the character line projection determining means Means,
Based on the histogram obtained by the obtaining unit, a line determination means for determining whether or not include the partial image area in the character line direction of the ruled line,
When it is determined by the ruled line determination means that a ruled line in the character line direction is included in the partial image area , a pixel line whose histogram frequency acquired by the acquisition means is equal to or greater than a predetermined threshold is specified as a ruled line projection . Specific means,
For the pair of partial image areas when it is determined that the projection of the character line can be specified by the character line projection determination means, the correlation between the projections of the two partial image areas detected by the detection means is obtained, A pair of partial image areas when the projection of the character line is determined not to be specified by the character line projection determination unit and the ruled line determination unit determines that the ruled line in the character line direction is included is specified by the specification unit. A local inclination angle calculation means for obtaining a correlation between the projections of the two partial areas and obtaining an inclination angle based on the obtained correlation and an interval between the two partial areas;
Regarding the pair of partial image areas when it is determined by the character line projection determining means that the projection of the character line cannot be specified and the ruled line determining means determines that the ruled line in the character line direction is not included, Control means for controlling so as not to perform processing in the tilt angle calculation means;
Determining means for determining the inclination of the document image based on the inclination angle calculated by the local inclination angle calculating means;
Program to make it function . A computer-readable storage medium storing the program according to claim 7 .

Images