JPS60218165A - Density unevenness detecting circuit - Google Patents

Abstract

PURPOSE:To detect exactly and rapidly the unevenness of density by calculating the density histogram of a character part in each range, calculating the whole area of the character part from the density histogram and the area of a picture element having a certain threshold or more and measuring the distribution of the character part. CONSTITUTION:A picture signal from a picture signal input part 10 is inputted to a character part extracting circuit 13 through an I/O control part 11 to extract the range of a part such as a character. A decision range determining circuit 20 determines whether each range is to be decided or not on the basis of the output of the circuit 13, a density histogram calculating circuit 23 calculates the density histogram of the character part of each range and a decision range area calculating circuit 24 calculates the whole area of the character part and the area of a picture element having a certain threshold or more. Thus, a density unevenness deciding circuit 26 decides the unevenness of density on the basis of said calculated results.

Description

[Detailed Description of the Invention] [Technical Field of the Invention] The present invention relates to a circuit for inspecting unevenness in shading of stamped or printed characters, and in particular, a circuit for comparing with normal data and specifying character positions, etc. in advance. It is possible to detect unevenness in density without the need.

[Conventional technology and problems]

For example, as a method for detecting uneven shading in characters printed on symbols of ICs, there is a conventional binarization method. In this method, a grayscale image of a normal character (seal) is previously binarized and held as reference data, and this is compared with the binary data of a sample grayscale image to detect unevenness in grayscale. At this time, as a comparison method, only the "1" part of them is displayed on the X axis (horizontal)
Alternatively, methods such as projecting in the Y-axis (vertical) direction and comparing the projected images are used, but in any case, correct data must be input at least once, and surroundings such as light source and lighting conditions are used. There is a drawback that the threshold value at the time of binarization needs to be reset depending on changes in the conditions and the object to be inspected.

[Purpose of the invention]

The purpose of the present invention is to accurately and quickly detect uneven shading in printed characters, etc., without requiring input of normal data or character position in advance, in order to improve these problems. It is an object of the present invention to provide a density unevenness detection circuit.

[Structure of the invention]

In order to achieve the above object, the shading unevenness detection circuit of the present invention detects shading unevenness of printed characters, stamped characters, symbols, etc. in an input image. an image signal output means for outputting;
A character part extraction circuit that extracts areas of parts such as characters, a judgment area determination circuit that determines whether or not each area is to be determined based on the output of this character part extraction circuit, and a judgment area determination circuit that extracts areas of character parts in each area. a density histogram calculation circuit that calculates a density histogram; an area calculation circuit that outputs the area (A) of the entire character part and the area (B) of pixels having a value equal to or higher than a certain darkness value from the density histogram of the character part; Shade unevenness determination that calculates the area of the character part of the area to be determined and the area of pixels having a value greater than the darkness value from the outputs of the area determination circuit and the area calculation circuit, and determines the unevenness of darkness based on the distribution state of this ratio in each area. It is characterized by comprising a circuit.

[Embodiments of the invention]

Before describing the present invention in detail based on one embodiment, its outline will be explained based on FIGS. 1 and 9.

For example, as shown in Figure 1, a character or symbol A is placed on a certain area.
-D is stamped, extract the number a of pixels in this stamped part, then slice the density of each pixel in this stamped part a by a plurality of threshold values Th1 to Thn, and calculate the number of pixels with the darkness value or higher. and calculate their ratio c-b. In this way, as shown in FIG. 9, the ratio C for each divided area O11, 2-45 is obtained according to the threshold value Thl''Thn.Then, for each threshold value, the maximum value and the minimum value of the ratio C are obtained. Difference l Cmax
- Add Cmin 1. If the uneven shading is reduced, this ratio C takes approximately the same value in each divided region of 0.1 and -45 at each threshold value, and therefore lCmax-Cmin l shows a small value. However, if there is unevenness in the shading of the stamp, the value of C within that divided area will vary greatly, and therefore the value of l Cmax-Cmin 1 will become thicker. Therefore, the presence or absence of uneven shading can be determined based on the value of C.

Next, one embodiment of the present invention will be described in detail with reference to FIGS. 1 to 9.

Figure 1 is an explanatory diagram showing the stamping (printing) state and each area;
Fig. 2 is a configuration diagram of an embodiment of the present invention, Fig. 3 is an explanatory diagram of a differential filter, Fig. 4 is an explanatory diagram of a projection state, Fig. 5 is an explanatory diagram of a region not subject to judgment, and Fig. 6 is a comprehensive explanation of the region. FIG. 7 is an explanatory diagram of dark value selection for a histogram, FIG. 8 is an explanatory diagram of uneven shading, and FIG. 9 is an explanatory diagram of the operation of determining uneven shading.

In the figure, 10 is an image signal input unit, such as a video camera, which converts the stamped area into an electrical signal and outputs this as image data with 8-bit density in pixel units, and 11 is an input/output unit. Control circuit and memory 1
2, and performs control such as storing image data sent from the image signal input section 10 in the memory 12 and reading necessary image data from the memory 12. 12 is a memory in which, for example, image data is stored; 13 is a character portion extraction circuit for extracting the vicinity of the character portion as will be described later; a differentiation circuit 14; a differential darkness value holding register 15; It includes a differential threshold value binarization circuit 16, a density threshold value binarization circuit 17, a density threshold value holding register 1B, an OR circuit 19, and the like.

Reference numeral 20 denotes a determination area determination circuit which determines whether or not to integrate areas to be determined, as will be described later, and includes a number projection circuit 21 for each area, an area integration circuit 22, and the like. Reference numeral 23 denotes a density histogram calculation circuit for each area, which creates a density histogram of a character portion; 24, a determination area area calculation circuit which examines the density distribution state by changing the threshold value Th; and 25, a determination threshold holding register. 26 is a shading non-uniformity determining circuit which determines the presence or absence of shading unevenness. Reference numeral 27 denotes a general control unit which divides the density unevenness determination area into areas θ to 15.

The character part extraction circuit 13 extracts the character part as described above, and has a differentiation circuit 14 for this purpose.The differentiation circuit 14 includes a differentiation filter in the horizontal axis direction as shown in FIG. 3(a). It has Dx and a differential filter Dy in the vertical axis direction.

Each differential filter has, for example, nine sections, and the values x and y of the central section are expressed as the sum of the values obtained by multiplying the densities of eight surrounding pixels by the coefficient of the differential filter. This differential filter Dx
The degree of change in density of image data in the horizontal axis direction is determined by
Further, the degree of change in density in the vertical axis direction can be determined by the differential filter Dy. And the output of each differential filter is xl
When y, the output of the differentiating circuit 14 is obtained as E+y"r. This differentiating circuit 14 outputs the density gradient of the image, and for example, near the outline of a character part, this differential output shows a large value. Therefore, The output of this differentiation circuit 14 is converted into a differentiation threshold value holding register 1 by a differentiation threshold value binarization circuit 16.
By comparing the level of the differential image output with the darkness value written in 5, a binary pattern is obtained.

This two-value pattern indicates the vicinity of the outline of the character portion. Further, the density threshold value binarization circuit 17 performs level discrimination on the grayscale image using the threshold value written in the density threshold value holding register 18 to obtain a binary pattern. This binary pattern indicates the vicinity of the median value of the character portion. and logical sum circuit 1
At step 9, the binary patterns obtained by the density threshold binarization circuit 17 and the differential threshold binarization circuit 16 are logically summed, thereby stably determining the character portion.

The judgment area determination circuit 20 determines whether or not to integrate adjacent areas for judgment, and for areas that are not to be integrated, makes judgments such as excluding the area from the judgment target when a certain number or more of pixels of the character part do not exist. It has a region number projection circuit 21 and a region integration circuit 22 for each region. Each area number projection circuit 21 obtains a projection of the number of pixels of a character part in the X-axis and y-axis directions of each image, and for example, when the pixels of the character part of an area are in the state shown in FIG. The number of "1"s seen from the X-axis is shown in Figure 4 (C) (obtained as projection data to the X-axis, and the number of "1s" seen from the y-axis is shown as the mountain in Figure 4). This is obtained as projection data on the y-axis. The area integration circuit 22 integrates the two areas based on the output from each area number projection circuit 21 when there is a character on the boundary with the right-adjacent area, and for areas that are not integrated, it integrates the two areas where the character part exceeds a certain number of pixels. If it does not exist, the area is determined to be outside the determination target. For example, if there are characters in areas P and Q as shown in Figure 6(a), the horizontal projection of area P will be as shown in Figure 6(bl), and areas, Q
The horizontal projection of is as shown in Figure 6 (C), so when two large character parts are consecutive like this, the area P
will be determined by integrating it with Q.

Further, as shown in FIG. 5 (b), when the number of pixels in each region is small, such a region is excluded from the determination target.

Each area density histogram calculating circuit 23 calculates a density histogram for the character portion determined by the logical sum circuit 19' in the area divided into n× type (divided into '16' in FIG. 1). Then, the data of the character part obtained from the OR circuit 19 is sent to the input/output control circuit 11, the image data of the character part is read from the memory 12, and a density histogram is calculated.

0 The determination area area calculation circuit 24 calculates the area A of the character part and the character part from the density histogram of the character part in each area obtained from the area density histogram calculation circuit 23 in the area to be determined determined by the area integration circuit 22. The area B of a pixel having a density level equal to or higher than a certain threshold Th is calculated. The darkness value at this time is varied in several types, such as Thl and Th2-. When the threshold value is changed from Ttz to Th3 for the density histogram shown in FIG. 7 +al to ICI, the shaded area becomes the area B that is larger than each darkness value.

The density unevenness determination circuit 26 calculates the ratio C of the areas A and B of each determination area to each darkness value from the areas A and B obtained from the output from the determination area area calculation circuit 24 (C-area B/area A).
If the difference between the maximum value and the minimum value is large, it is determined that uneven shading exists. For example, for characters as shown in FIG. 8, the threshold value T h is
1, Th 2 - Th n, as shown in Fig. 9, in the case of Th+, C4-+, Cs for each region
−1・−(, +s−1 is obtained, and in the case of Th2, C4
-1 2, Cs-2-c I 5-2 is obtained, and in the case of Thn, C4-n, Cs -n-C+ s -n is obtained. Then, the maximum value C of the above C calculated in each region for each threshold value
Take max and minimum value Cm1n and calculate the difference Cmax - Cm
Calculate in. If the density unevenness is small, the value of C for the same threshold value will be approximately the same in each region, so the value of Cmax-Cmin for the same threshold value will not become large. However, when uneven shading exists, the value of Cmax - Cmin increases in the region of the character where the uneven shading exists. Therefore, data serving as the judgment reference value for uneven shading is written in the judgment darkness value holding register 25 in advance.
This is compared with Cmax-Cmin at each of the thresholds, and if a certain threshold T h m exceeds this determination reference value, it is determined that the stamped character has uneven shading. For example, in the state shown in FIG. 8, since the character A has uneven shading, when characters A to D including such seal data are judged, it is determined that there is an uneven shading.

Next, the operation of the present invention will be explained.

(1) As shown in FIG. 1, the image data of the surface on which characters A to D are stamped is inputted to the image signal input section 10, and is stored in the memory 12 after being divided into areas 0 to 15.

(2) The vicinity of the character contour is detected from the data stored in the memory 12 by the differentiation circuit 14 and the differential threshold value binarization circuit 16, and this character contour data is output to the OR circuit 19.

(3) The data stored in the memory 12 is also output to the density/darkness value binarization circuit 17, where image data with a density above a specified level is binarized, and the data near the center of the character is also logically summed. It is output to the circuit 19.

Therefore, from the OR circuit 19, the differential threshold value binarization circuit 1
Based on the character outline data and the data near the center of the character output from 6, the area of the character part and its coordinate values are output.

(4) Each area number projection circuit 21 projects the character portions for each area O to 15 and outputs the position and number to the area integration circuit 22. For each area, the area integration circuit 22 first excludes areas with a small number of pixels in the character part from being judged. (not subject to judgment), and if there are many character parts in adjacent parts, these are integrated to form a judgment area (in Figure 8, areas 4, 5, 13, 14, 14, and 15 are judged as integrated) .

(5) Each region density histogram calculation circuit 23 obtains the image data of the character portion from the memory 12 based on the coordinate data of the character portion output from the OR circuit 19, and calculates the image data for each region as shown in FIG. Create a concentration histogram. As a result, a density histogram of the character portion of each area is obtained.

(6) The determination area area calculation circuit 24 is the area integration circuit 22
The area A of the character part with respect to the judgment target area is calculated based on the non-judgment target information and the area integrated information output from the , and the threshold value Th+ is set for the density histogram.
Th2-・Thn determines the number of pixels B l that is greater than the threshold value,
Add B 2-B n.

Then, these are sent to the density unevenness determination circuit 26.

(7) Based on these data, the density unevenness determination circuit 26 calculates the ratio C of the character area A for each darkness value to the pixel area B that is equal to or higher than the threshold value for the determination target area, as shown in FIG. For each threshold, its maximum value Cmax and minimum value C
Calculate the difference in m1n. As shown in FIG. 8, if there is a stamp with uneven shading, at least one of the Cmax-Cmin values for each threshold value will be larger than the determination threshold, so the presence of uneven shading can be detected.

In the above embodiment, the stamped characters (symbols) were explained, but
In the same way, uneven shading can be detected for printed characters. Of course, the pixel calculation process can also be executed at high speed based on pipeline processing.

〔Effect of the invention〕

According to the present invention, it is possible to accurately and quickly detect the overall shading unevenness of stamped (printed) characters (symbols) without having to input normal data in advance or giving character positions. I can do it.

[Brief explanation of the drawing]

Fig. 1 is an explanatory diagram showing the stamping (printing) state and each area, Fig. 2 is a configuration diagram of an embodiment of the present invention, Fig. 3 is an explanatory diagram of the differential filter, Fig. 4 is an explanatory diagram of the projection state, Fig. 5 is an explanatory diagram of areas not subject to judgment, Fig. 6 is an explanatory diagram of area integration, Fig. 7 is an explanatory diagram of threshold value selection for density histogram, and Fig. 8 is an explanatory diagram of threshold value selection for density histogram.
The figure is an explanatory diagram of uneven shading, and FIG. 9 is an explanatory diagram of an operation for determining uneven shading. In the figure, 10 is an image signal input section, 11 is an input/output control circuit,
12 is a memory, 13 is a character portion extraction circuit, 14 is a differentiation circuit, 15 is a differential darkness value holding register, 16 is a differential darkness value binarization circuit, 17 is a density threshold value binarization circuit, 18 is a density threshold value holding register, 19 is an OR circuit, 20 is a judgment area determination circuit, 21 is a number projection circuit for each area, 22 is an area integration circuit,
23 is a density histogram calculation circuit for each region, 24 is a determination area area calculation circuit, 25 is a determination darkness value holding register, and 26 is a density unevenness determination circuit. Patent Applicant: Fujitsu Ltd. Representative Patent Attorney Akira Yamatani 6 Body 3 Figure 4 Figure + 5 Figure O 6 Concave 'lI'9 Figure

Claims (1)

[Scope of Claims] 1. Image signal output means for scanning characters, etc. and outputting image signals thereof in a shading unevenness/detection circuit that detects shading unevenness of printed characters, stamped characters, symbols, etc. in an input image. and a character part extraction circuit for extracting a region of parts such as characters;
□A judgment area determination circuit that determines whether or not each area is subject to judgment based on the output of the character area extraction circuit; □A density histogram calculation circuit that calculates the density histogram of the character area in each area; an area calculation circuit that outputs the area (A) of the entire character portion and the area CB of pixels having a value greater than a certain threshold value from the density histogram;
The area of the character part of the area to be determined and the area of the pixels having a value equal to or greater than the threshold value are calculated from the outputs of the determination area determination circuit and the area calculation circuit, and the unevenness of shading is determined based on the distribution state of this ratio in each area. A density unevenness detection circuit comprising a determination circuit. 2. The character portion extraction circuit includes a density gradient position detection circuit that detects the density gradient of an image, a level discrimination binarization circuit that discriminates levels based on a reference level and converts them into binarized images, and a 2. The unevenness detection circuit according to claim 1, further comprising an OR circuit that performs a logical sum of the level-discriminated and binarized signals. □ 3. The judgment area determination circuit includes a number projection circuit for each area that projects the number of pixels for the character part horizontally and vertically in each area, and an adjacent area that is integrated as an area to be judged based on the projection value. 2. The density unevenness detection circuit according to claim 1, further comprising a region integration circuit for determining whether or not the image is detected.