JPH11195121A - Device for evaluating picture and method therefor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a picture evaluating device and method for quantitatively, stably and quickly evaluating the dirt of the surface of an object to be evaluated instead of the visual evaluation of an operator. SOLUTION: The surface of an inspection sheet 9 is read by image pickup devices 1 and 2, each area of a pattern part due to dirt per each unit area of a picture is obtained based on the picture data, and an evaluated value corresponding to the level of the dirt is calculated based on the total sum of the areas of the pattern parts due to the dirt per the unit area.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image evaluation apparatus and method capable of evaluating the degree of dirt on the surface of an object to be evaluated from an image of the surface.

[0002]

2. Description of the Related Art Hitherto, evaluation of printed images by an image forming apparatus such as a laser beam printer, a copying machine, an ink jet printer or the like has been mostly performed by visual inspection by hand. In particular, defective items when unnecessary toner or ink that does not contribute to printing adheres to a print surface such as a paper surface on which an image is printed, for example, "fogging" or "fogging" in which a printing surface that should be white is stained black. Defective items such as "dirt" and "ghost" had to be visually evaluated.

[0003]

However, in the above-described conventional visual evaluation, individual differences occur in the evaluation results, and each evaluation itself shows an ambiguous value. Attempts have also been made to use a reflection densitometer in order to quantitatively measure the defective items. However, even at a density level that can be distinguished by the human eye, there is a problem that it is difficult to obtain a difference between the density of the non-defective part and the density of the defective part, and the measurement takes a considerable time.

An object of the present invention has been made in view of the above-mentioned problems, and it is possible to quantitatively, stably and quickly evaluate dirt on the surface of an object to be evaluated instead of a visual evaluation of an operator. An image evaluation device and method are provided.

[0005]

An image evaluation device according to the present invention comprises: image input means for reading an image of an evaluation object surface;
On the basis of the image data read by the image input means, for each unit area of the image, based on the area calculation means for calculating the individual area of the pattern portion due to dirt, based on the total sum of the area of the pattern portion per unit area Evaluation value calculating means for obtaining an evaluation value corresponding to the degree of contamination for each unit area.

According to the image evaluation method of the present invention, an image of the surface of an object to be evaluated is read, and based on the read image data, an individual area of a pattern portion due to dirt is determined for each unit area of the image. An evaluation value corresponding to the degree of dirt per unit area is obtained based on the total sum of the areas of the pattern units per area.

[0007]

Preferred embodiments of the present invention will be described below with reference to the accompanying drawings.

FIG. 1 is a schematic configuration diagram of an image evaluation apparatus according to an embodiment of the present invention. In FIG. 1, imaging devices 1 and 2
Have a light receiving element (photoelectric conversion element) such as a one-dimensional CCD line sensor. These imaging devices 1 and 2
, Repeatedly picks up an image of an inspection sheet (a sheet on which an image is printed) 9 to be evaluated set on a document table in a main scanning direction 13 and outputs an electric signal converted for each scan.
The illumination unit 14 illuminates the imaging positions of the imaging devices 1 and 2.
The moving mechanism 10 is a mechanism for relatively moving the imaging devices 1 and 2 and the inspection paper 9 in the sub-scanning direction 12 orthogonal to the main scanning direction 13. By such a relative movement between the imaging devices 1 and 2 and the inspection paper 9 in the main scanning direction 13 and the sub-scanning direction 12, a print image on the inspection paper 9 can be read as a two-dimensional image.

As described above, the imaging devices 1 and 2 and the moving mechanism 1
By cooperation with 0, a video signal over the entire area of the inspection paper 9 to be evaluated is obtained. The video signal is input to the image processing unit 4 after A / D conversion. The image processing unit 4 performs image processing operations such as an image data capturing operation, a sensor sensitivity correction operation, an area division processing operation, and an area calculation operation for each area in accordance with an operation command of the host computer 5. The moving mechanism control unit 6 includes a host computer 5
The control of the moving mechanism 10 is performed according to the operation command. The host computer 5 and the image processing unit 4 are connected by a bus 15, and the host computer 5 can directly read out image data stored in an image memory unit (see FIG. 2) 54 of the image processing unit 4 described later. it can. Further, the host computer 5 and the moving mechanism control unit 6 communicate with the communication unit 16.
Connected by

The host computer 5 reads out the operation result in the image processing section 4, converts it into a value necessary for evaluation, and outputs the result and the stored image data to the monitor 17.
To be displayed. Furthermore, an input unit 7 such as a keyboard and a pointing device 8 such as a mouse are connected to the host computer 5, and the operator can use these to input parameters and operation commands necessary for evaluation. .

FIG. 2 is a schematic block diagram of the image processing section 4 of the present embodiment. Here, portions common to FIG. 1 are denoted by the same reference numerals, and description thereof is omitted.

In FIG. 2, as the imaging devices 1 and 2,
For example, a one-dimensional line sensor camera or the like is used. 5
Reference numeral 1 denotes an image input unit, which receives video signals from the imaging devices 1 and 2 and converts them into digital signals, and further performs dark correction for correcting the dark current output of the line sensor and sensitivity unevenness and illumination unevenness for each pixel. The digital image data subjected to the shading correction to be corrected is output. An area dividing unit 52 separates a background part and a pattern part from the input image data, and labels the pattern part. In the case of this example, no image is printed on the inspection paper 9, and therefore, the background portion in the image data is an image that appears on the surface due to the properties of the inspection paper 9 itself. The pattern portion separated from the background portion is, for example, due to a deposit such as toner or ink that stains a print surface that should be originally white. An area calculation unit 53 calculates the area of each pattern unit labeled by the area division unit 52. An image memory unit 54 stores image data.

The image input unit 51 and the area dividing unit 5
2. The area calculation unit 53 and the image memory unit 54 are connected to the host computer 5 via a system bus 56. Further, the image input unit 51, the area dividing unit 52,
The area calculation unit 53 and the image memory unit 54 are connected to an image bus 57, and transfer of image data between them is performed at high speed by the image bus 57.

Next, the principle of evaluation of defective phenomena such as "fog", "dirt", and "ghost" realized by the above configuration will be described.

FIG. 3 is a diagram schematically showing the relationship between the unit area 21 used for evaluation and the inspection paper 9 to be evaluated. In FIG. 3, a unit area 21 is set on a part of the inspection paper 9. Here, there is no particular restriction on the size of the unit area 21, and the unit area 21 can be set to an arbitrary size. In the area of the unit area 21, there is a deposit such as toner or ink which causes a defective phenomenon such as "fog", "dirt" or "ghost", that is, an unnecessary deposit 23 which stains the print surface.
There are many. On the basis of the state of the deposits 23, for example, defective items such as "fog", "dirt", and "ghost" that stain the print surface, which should be originally white, are evaluated.

FIG. 4 is a diagram showing a state where the unit area 21 is defective. The vertical side of the unit area 21 is WY, and the horizontal side is WX. The area dividing unit 52 of the image processing unit 4 performs image processing on the inside of the unit area 21 to separate the pattern portion formed by the individual attached matter 23 from the background part described above.
Label each pattern part. In FIG.
The deposit 23 exists from T1 to T23. Also,
The areas of the individual attachments 23 from T1 to T23 are calculated by the area calculation unit 53 of the image processing unit 4.

FIG. 5 is a diagram showing a state where the inside of the unit area 21 is good. Also in this case, similarly to FIG. 4, each unit area 21 is image-processed by the image processing unit 4, and the pattern part by the attached matter 23 is separated from the background part, and is labeled for each attached matter 21. In FIG. 5, the deposit 21 exists from T1 to T5. Further, the image processing unit 4 also calculates the areas of the individual attachments 23 from T1 to T5.

FIG. 6 is a graph showing T within the unit area 21 in FIG.
It is explanatory drawing of the area of each attached matter 23 from 1 to T23, and the total area. FIG. 7 shows the unit area 2 in FIG.
FIG. 3 is an explanatory diagram of the area of each attached matter 23 from T1 to T5 in 1 and the total area thereof. Based on these areas, an evaluation value D of a defect such as “fog”, “dirt”, or “ghost” is calculated.

Here, the evaluation value D is calculated by the following equation (1).

[0020]

D = −log ₁₀ ((S−ΣTi) / S) (1) S: unit area ΣTi: total area of attached matter The data of FIG. 6 is applied to the above equation (1). When the evaluation value D for the unit area 21 of 4 is obtained, D = 0.134.

When the data of FIG. 7 is applied to the above equation (1) to obtain an evaluation value D for the unit area 21 of FIG. 5, D = 0.015.

By comparing the evaluation value D obtained in this way, it is possible to discriminate a non-defective / defective product according to the degree of contamination of the inspection paper 9.

FIG. 8 is a flowchart for explaining a series of operations of this embodiment.

In FIG. 8, in step S1, an inspection paper 9 to be evaluated is set on a document table. Next, in step S2, an inspection start command is issued from the host computer 5, and in step S3, the moving mechanism 10 causes the imaging devices 1, 2 and the inspection paper 9 to move relative to each other at a constant speed in the sub-scanning direction 12. Movement is started. Moving mechanism 10
After that, as described later, the imaging devices 1 and 2 and the inspection paper 9 are relatively moved at a constant speed until the input of the image data to be inspected is completed. In the case of this example, the imaging device 1
The inspection paper 9 is moved in the sub-scanning direction 12 with respect to 2, and the stage on which the inspection paper 9 is placed is moved. In the next step S4, after confirming that the inspection paper 9 to be evaluated has reached the image input start position, the process proceeds to step S4.
At 5, input of image data from the imaging devices 1 and 2 is started.

The input image data is subjected to dark correction in step S6 and shading correction in step S7, and then stored as two-dimensional image data in the image memory unit 54 in step S8. This image input operation is continued until the inspection paper 9 as the evaluation object reaches the image input end position. If it is determined in step S9 that the inspection paper 9 has reached the image input end position, the moving mechanism 10 is stopped in step S10, and the image input ends. After the image input is completed in this manner, in step S11, a command is issued to the moving mechanism 10 to return the stage on which the test paper 9 is placed to the original start position.

The read image data of the evaluation object is
All are stored on the image memory unit 54. As described above, the labeling of the image data is performed within a unit area (step S12), the area of each label is calculated (step S13), and the sum of the areas is calculated (step S15). Calculate D. This series of evaluation processing is repeated for the image data of the entire evaluation target.
After it is confirmed in step S16 that the calculation of the evaluation values D over all the regions of the evaluation object has been completed, in step S17, the maximum value is obtained from the evaluation values D calculated for each region. . Next, in step S18, a non-defective / defective determination level predetermined according to the degree of dirt is determined.
A comparison is made with the maximum value of the evaluation value D obtained in step S17, and it is determined whether this evaluation target is a good product or a defective product. For example, when the maximum value of the evaluation value D is equal to or less than the determination level, it is determined to be a non-defective product, and when it is higher than that, it is determined to be a defective product. Further, it is possible to judge non-defective / defective products based on the average value of the evaluation values D for the entire inspection object and the standard deviation as a distribution state. Then, step S19
Then, the inspection paper 9 to be evaluated is removed from the platen, and a series of operations is completed.

The test paper 9 to be evaluated may be an image on which an image is printed. In that case,
With respect to a portion where the print image portion is removed from the image data or a blank portion, the degree of dirt can be evaluated in the same manner as described above.

[0028]

As described above, according to the present invention,
The image of the surface of the evaluation object is read, and within the unit area of the image, the evaluation value of the degree of contamination based on the sum of the areas of the pattern portions due to the contamination is obtained. "Dirt", "Fog",
Evaluation of defective items such as "ghost" can be performed automatically. As a result, it is possible to replace the image evaluation that has been performed visually by a human until now.

Further, variations due to individual differences such as evaluation results by humans are eliminated, stable evaluation can be performed, and the number of personnel involved in the evaluation can be reduced, thereby realizing cost reduction.

[Brief description of the drawings]

FIG. 1 is a block diagram showing the overall configuration of an image evaluation device according to the present invention.

FIG. 2 is a block diagram illustrating a schematic configuration of an image processing unit in FIG. 1;

FIG. 3 is an explanatory diagram of a relationship between an evaluation unit area and an attached matter on the inspection paper of FIG. 1;

FIG. 4 is a plan view when an evaluation unit area on the inspection paper in FIG. 1 is in a defective state.

FIG. 5 is a plan view in a good state within an evaluation unit area on the inspection paper of FIG. 1;

FIG. 6 is an explanatory diagram of an area and a total sum of individual attachments in an evaluation unit area of FIG. 4;

FIG. 7 is an explanatory diagram of an area and a total sum of individual attachments in an evaluation unit area of FIG. 5;

FIG. 8 is a flowchart for explaining the operation of the image evaluation device according to the present invention.

[Description of Signs] 1, 2 imaging apparatus 4 image processing unit 5 host computer 6 moving mechanism control unit 9 inspection paper 21 unit area 23 attached matter 51 image input unit 52 image division unit 53 area calculation unit 54 image memory unit

Claims (10)

[Claims] An image input means for reading an image of the surface of an object to be evaluated, and an area for obtaining an individual area of a pattern portion due to dirt for each unit area of the image based on image data read by the image input means. An image evaluation apparatus comprising: a calculation unit; and an evaluation value calculation unit that obtains an evaluation value corresponding to a degree of contamination for each unit area based on a total area of the pattern units per unit area. . 2. The evaluation value calculation means according to claim 1, wherein the unit area is S, and the total area of the pattern unit per unit area is ΔTi, and the evaluation value D is obtained by the following equation. 2. The image evaluation device according to 1. D = −log ₁₀ ((S−ΔTi) / S) 3. The image processing apparatus according to claim 1, further comprising a determination unit configured to determine that the image is defective when a maximum value among a plurality of evaluation values for each unit area of the entire image is equal to or greater than a predetermined reference value. The image evaluation device according to claim 1. 4. The image input device according to claim 1, wherein the image input unit includes an imaging unit that reads the image and outputs a video signal, and a conversion unit that corrects the video signal and converts the video signal into a digital image signal. Item 4. The image evaluation device according to any one of Items 1 to 3. 5. The image processing apparatus according to claim 1, wherein the area calculating unit includes a processing unit that separates data of a background portion based on characteristics of the surface of the evaluation object from image data read by the image input unit. Item 5. The image evaluation device according to any one of Items 1 to 4. 6. An image of the surface of the object to be evaluated is read, and an individual area of the pattern portion due to dirt is obtained for each unit area of the image based on the read image data. An image evaluation method for obtaining an evaluation value corresponding to the degree of dirt for each unit area based on the sum total of the areas. 7. The image evaluation method according to claim 6, wherein the unit area is S and the total area of the pattern units per unit area is ΔTi, and the evaluation value D is obtained by the following equation. . D = −log ₁₀ ((S− 10Ti) / S) 8. The image processing apparatus according to claim 6, wherein the image is determined to be defective when the maximum value among the plurality of evaluation values per unit area for the entire image is equal to or greater than a predetermined reference value. Or the image evaluation method according to 7. 9. The image processing device according to claim 6, wherein the image is read, a video signal is output, and the video signal is corrected and converted into a digital image signal to obtain the image data. The described image evaluation method. 10. The image evaluation method according to claim 6, wherein data of a background portion based on characteristics of the surface of the evaluation object is separated and removed from the read image data.