JP2020086494A - Image processing apparatus - Google Patents

Abstract

To provide an image processing apparatus capable of preventing error detection due to foreign substances and improving an accuracy.SOLUTION: An image processing apparatus 1 includes a camera interface 11 that receives an input of a photograph image, a paper edge detection unit 15 that detects a paper edge of a printed matter, a point detection unit 16 that detects a plurality of frame points respectively assumed to be on a frame edge by determining black and while of vertical pixels toward inside of a plurality of starting points respectively set at a known interval on the paper edge, an error detection point specification unit 17 that specifies an error detection point assumed to be error detection among the plurality of frame points based on a distance between the points of adjacent frame points, and instructs the point detection unit 16 to detect the error detection point again, and a frame edge calculation unit 18 that calculates an equation of the frame edge to the paper edge X by using a least square method based on the frame points detected and detected again by the point detection unit 16.SELECTED DRAWING: Figure 3

Description

The present invention relates to an image processing device that detects an inclination angle of an image.

An image processing apparatus has been proposed which detects a boundary between a blank area and a black pixel area, and calculates the tilt angle of the entire image based on the tilt angle of the boundary from horizontal or vertical (see, for example, Patent Document 1). In Patent Document 1, the inclination from the horizontal or the vertical is calculated by performing the linear approximation by the least square method from the position information of the black pixel row located at the boundary.

JP, 2009-123155, A

However, the printed matter output from the image forming apparatus may have foreign matter such as toner, paper dust, and dust attached at unintended positions. In the related art, there is a problem that accuracy is significantly reduced when a foreign substance attached to an unintended position is detected as a black pixel located at the boundary.

The present invention has been made in view of the above problems, and an object of the present invention is to provide an image processing apparatus capable of preventing erroneous detection due to foreign matter and improving accuracy.

The image processing apparatus of the present invention is an image processing apparatus that inspects the printed matter by analyzing a photographic image of a printed matter on which a frame edge is printed, and an image input unit that receives input of the photographic image, By determining the black and white of pixels in the vertical direction toward the inside from each of the paper edge detection unit that detects the paper edge of the printed matter P and each of a plurality of start points set at known intervals on the paper edge, A point detection unit that detects each of a plurality of frame points that are supposed to be on a frame edge, and an erroneous detection point that is assumed to be an erroneous detection among the plurality of frame points based on the distance between the adjacent frame points. Based on the erroneous detection point identification unit for instructing the point detection unit to re-detect the erroneous detection point and the frame point detected and re-detected by the point detection unit, the sheet by the least square method. A frame edge calculation unit that calculates an equation of the frame edge with respect to an edge and outputs a distance between the paper edge and the frame edge as an inspection result is provided.

According to the present invention, it is possible to eliminate erroneous detection points that are assumed to be erroneous detections, and thus it is possible to prevent erroneous detections due to foreign matter and improve accuracy.

It is a block diagram which shows the system configuration of a printed matter inspection system. It is a figure which shows the example of the printed matter of an inspection target. FIG. 2 is a block diagram showing a schematic configuration of the image processing device shown in FIG. 1. 6 is a flowchart illustrating an inspection operation performed by the image processing apparatus illustrated in FIG. 1. FIG. 3 is an explanatory diagram explaining an inspection operation by the image processing apparatus shown in FIG. 1.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In addition, in the following embodiments, the same reference numerals are given to the configurations having the same functions.

Referring to FIG. 1, an image processing apparatus 1 according to the present embodiment includes a mounting table 2 on which a printed material P output from an image forming apparatus such as a printer, a copying machine, and an MFP (Multifunction Peripheral / Printer / Product) is mounted. The camera 3 that captures a photographic image by photographing the printed matter P placed on the placing table 2 constitutes a printed matter inspection system.

The image processing apparatus 1 is an information processing apparatus such as a personal computer, and analyzes the photographic image acquired by the camera 3 to inspect the printing state of the printed matter P and output the inspection result.

As shown in FIG. 2, a frame line (hereinafter, referred to as a frame edge Y) along an outer periphery (hereinafter, referred to as a paper edge X) of the printed product P is printed on the printed matter P to be inspected. The device 1 outputs the distance Z between the paper edge X and the frame edge Y as the inspection result. The distance Z is a length on a straight line perpendicular to the paper edge X. Further, the image processing apparatus 1 calculates the distance Z as an inspection result at a plurality of locations per side, as shown in FIG. Furthermore, the location where the distance Z is calculated can be set appropriately, and the distance Z between the paper edge X and the corner of the frame edge Y may be calculated as the inspection result. Thereby, the position and inclination of the image printed on the printed matter P can be inspected.

Referring to FIG. 3, the image processing apparatus 1 of the present embodiment includes a camera interface 11, an input unit 12 such as a keyboard, a display unit 13 such as a liquid crystal display, and a control unit 14.

The camera interface 11 is a connection unit with the camera 3, and functions as a shooting instruction unit that notifies the camera 3 of a shooting instruction input from the input unit 12 and image input that receives input of a photographic image acquired by the camera. Function as a department.

The control unit 14 is an arithmetic processing circuit such as a microcomputer including a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like. The ROM stores a control program for controlling the operation of the image processing apparatus 1. The control unit 14 reads the control program stored in the ROM and expands the control program in the RAM to control the entire apparatus according to various instruction information input from the input unit 12.

The control unit 14 also functions as a paper edge detection unit 15, a point detection unit 16, an erroneously detected point identification unit 17, a frame edge calculation unit 18, and a distance calculation unit 19.

The paper edge detection unit 15 detects the boundary between the mounting surface of the mounting table 2 and the printed matter P as the paper edge X by binarizing the input photographic image and analyzing the binarized photographic image. By setting the mounting surface of the mounting table 2 to have a color scheme whose brightness is clearly different from that of the peripheral portion of the printed matter P, it is possible to easily detect the paper edge X by the change in black and white.

The point detection unit 16 discriminates black and white of pixels in the vertical direction from the start point set on the paper edge X toward the inside, identifies a portion where the white pixel changes to a black pixel, and changes from a black pixel to a white pixel, and determines a black portion. The center of the pixel is detected as a frame point assumed to be on the frame edge Y. A plurality of start points are set at known intervals per side, and the point detection unit 16 detects a frame point for each start point.

The erroneous detection point identification unit 17 identifies a frame point (hereinafter, referred to as an erroneous detection point) that is assumed to be erroneously detected due to a foreign substance such as toner, paper dust, and dust, based on the distance between adjacent frame points. Then, the point detection unit 16 is instructed to re-detect the identified erroneous detection point.

The frame edge calculation unit 18 calculates the equation of the frame edge Y with respect to the paper edge X by the least square method based on the frame points (including re-detection) detected by the point detection unit 16.

The distance calculation unit 19 detects the distance Z between the paper edge X and the frame edge Y at a plurality of positions per side based on the equation of the frame edge Y calculated by the frame edge calculation unit 18, and the display unit displays the inspection result as the inspection result. Output from 13th etc.

Next, the inspection operation by the image processing apparatus 1 will be described in detail with reference to FIGS.
The user places the printed matter P to be inspected on the mounting table 2 and inputs a photographing instruction to the input unit 12 of the image processing apparatus 1. As a result, the photographic image acquired by the camera is input to the image processing apparatus 1.

Upon receiving the input of the photographic image, the control unit 14 of the image processing apparatus 1 functions as the paper edge detection unit 15, and binarizes the input photographic image (step S101).

Next, the paper edge detection unit 15 detects the boundary between the mounting surface of the mounting table 2 and the printed matter P as the paper edge X by analyzing the binarized photographic image (step S102). It should be noted that although the processing from step S102 is executed on each of the four sides, it will be described as one side for convenience.

Next, the control unit 14 functions as the point detection unit 16 and sets a plurality of start points A1 to _N at known intervals on the paper edge X detected in step S102 (step S103). FIG. 5A shows an example in which the starting points A _{1 to} A ₄ are set at intervals of L ₁₂ =L ₂₃ =L ₃₄ , respectively.

Next, the point detection unit 16 discriminates black and white of pixels in the vertical direction from each of the start points A _{1 to N} inward, and specifies a location where white pixels change to black pixels and black pixels change to white pixels. Then, the centers of the black pixels are detected as the frame points _{B1 to N} (step S104). FIG. 5A shows an example in which the frame points B _{1 to} B ₄ are detected corresponding to the start points A _{1 to} A ₄ , respectively.

Next, the control unit 14 functions as a false detection point specifying unit 17 calculates the distance between points of adjacent frame point _{B 1~N M 12 ~M (n-} 1) n , respectively (step S105). FIG. 5B shows an example in which the inter-point distances M ₁₂ , M _23, M ₃₄ of the frame points B _{1 to} B ₄ are calculated.

Then, the false detection point specifying unit 17, the calculated point distance M _{12 ~M (n-1)} toner on the basis of _n, paper powder, whether there is a foreign matter due erroneous detection points such as dust, Is determined (step S106). When the frame point B is correctly detected, the point-to-point distance M becomes almost the same value as the start point interval L. Therefore, the threshold value α is set to a small value, and the both sides are specified as a frame point with a distance M between points>the interval LA+α and an erroneous detection point. In this case, it is premised that erroneous detection due to foreign matter such as toner, paper dust, and dust does not occur continuously. Then, in step S106, it is determined whether or not the false detection point is specified. In the example shown in FIG. 5 (b), between both sides of the frame points _{B 3} points distance _{M 23>} interval _{L 23} + alpha, point distance _{M 34>} next interval _{L 34} + alpha, the frame point _{B 3} mis An example specified as a detection point is shown.

If there is an erroneous detection point in step S106, the erroneous detection point identification unit 17 instructs the point detection unit 16 to re-detect the identified erroneous detection point.

The point detection unit 16 instructed to perform the re-detection moves the position of the start point (A ₃ ) corresponding to the erroneous detection point (B ₃ ) by a preset predetermined distance h, as shown in FIG. 5C. It is not the starting point _{(a 3} ') and re-identify (step S107). The point detecting section 16, re-detect the 'frame point _{(B 3} based on) again identified starting point _{(A 3)'} (step S108), the flow returns to step S105.

When there is no erroneous detection point in step S106, the control unit 14 functions as the frame edge calculation unit 18, and based on the frame points (including re-detection) detected by the point detection unit 16, the least squares method is applied to the paper edge X. The equation of the frame edge Y is calculated (step S109).

Next, the frame edge calculation unit 18 calculates the distance Z as an inspection result at a plurality of locations per side (step S110), outputs the inspection result from the display unit 13 and the like, and ends the inspection operation.

As described above, according to the present embodiment, the image processing apparatus 1 inspects the printed matter P by analyzing the photographed image of the printed matter P on which the frame edge Y is printed. Inside from each of the camera interface 11 that functions as an image input unit that receives an input, the paper edge detection unit 15 that detects the paper edge X of the printed matter P, and a plurality of start points A set at known intervals on the paper edge X. Based on the inter-point distance L of the adjacent frame points B and the point detection unit 16 that respectively detects a plurality of frame points B that are supposed to be on the frame edge Y by discriminating black and white of pixels in the vertical direction. Then, the false detection points that are supposed to be false detections are identified from the plurality of frame points B, and the false detection point identification unit 17 that instructs the point detection unit 16 to re-detect the false detection points, and the point detection unit 16 Based on the detected and re-detected frame points B, the equation of the frame edge Y with respect to the paper edge X is calculated by the least square method, and the distance Z between the paper edge X and the frame edge Y is output as the inspection result. And a section 18.
With this configuration, it is possible to eliminate erroneous detection points that are assumed to be erroneous detection, so that it is possible to prevent erroneous detection due to foreign matter and improve accuracy.

Further, in the present embodiment, when the point detection unit 16 is instructed to re-detect an erroneous detection point, the point detection unit 16 moves the position of the start point A corresponding to the erroneous detection point by a preset distance h to set the frame point. Re-detect B'.
With this configuration, it is possible to re-detect the frame point B′ while avoiding the foreign matter that has caused the erroneous detection.

Further, in the present embodiment, the erroneously detected point identification unit 17 sets a frame in which each of the distances M between the points on both sides is larger than a value obtained by adding a preset threshold α to the interval L between the corresponding start points A. The point B is specified as an erroneous detection point.
With this configuration, it is possible to easily specify the false detection point.

It should be noted that the present invention is not limited to each of the above-described embodiments, and it is obvious that each embodiment can be appropriately modified within the scope of the technical idea of the present invention. Further, the number, position, shape, etc. of the above-mentioned constituent members are not limited to those in the above-mentioned embodiment, and the number, position, shape, etc. suitable for carrying out the present invention can be adopted. In each figure, the same components are designated by the same reference numerals.

DESCRIPTION OF SYMBOLS 1 Image processing apparatus 2 Mounting table 3 Camera 11 Camera interface 12 Input section 13 Display section 14 Control section 15 Paper edge detection section 16 Point detection section 17 False detection point identification section 18 Frame edge calculation section 19 Distance calculation section

Claims (3)

An image processing apparatus for inspecting the printed matter by analyzing a photographic image of a printed matter on which a frame edge is printed,
An image input unit that receives the input of the photographic image,
A paper edge detection unit for detecting the paper edge of the printed matter,
Point detection that detects a plurality of frame points that are supposed to be the frame edges by determining black and white of pixels in the vertical direction from the respective start points set at known intervals on the paper edge toward the inside Department,
An error that specifies an erroneous detection point that is assumed to be an erroneous detection from a plurality of the frame points based on the distance between the adjacent frame points and instructs the point detection unit to re-detect the erroneous detection point. A detection point identification unit,
Based on the frame points detected and re-detected by the point detection unit, the equation of the frame edge with respect to the paper edge is calculated by the least square method, and the distance between the paper edge and the frame edge is output as an inspection result. An image processing apparatus, comprising: When the redetection of the false detection point is instructed, the point detection unit moves the position of the start point corresponding to the false detection point by a predetermined distance and redetects the frame point. The image processing apparatus according to claim 1, which is characterized in that. The erroneous detection point identification unit identifies, as the erroneous detection point, a frame point in which any of the distances between the points on both sides is larger than a value obtained by adding a preset threshold to the interval between the corresponding start points. The image processing apparatus according to claim 2, wherein

Images