KR100955180B1 - Method and System for Computing Quality Value of Image - Google Patents

Abstract

Image quality index calculation method according to an aspect of the present invention that can calculate the quality index of the image by using one or more feature information extracted from the image, image basic information, color distribution information, gray (Gray) from a predetermined image Extracting feature information including at least one of distribution information and texture information; And calculating a quality index of the image by using at least two feature information of the feature information.

Image, Quality, Index, and Features

Description

Method and System for Computing Quality Value of Image

The present invention relates to image processing, and more particularly, to a method for calculating a quality index of an image.

Due to the development of the Internet and the increase of the Internet, various services are provided using the Internet, and a representative example thereof is a search service. When a search service inputs a word or a combination of words to be searched by a user, the search engine searches a search result document (eg, a web site or an article including a search query entered by the user) corresponding to the search engine. Means services provided to

Recently, in order to meet various search demands of users, search service providers have provided content such as a video or an image as a search result as well as a textual search result. In this case, in providing a video or image as a search result, a video or image having a file name including a query input by the user or a video or image including a query input by the user in text related to the video or image is provided. Done.

However, when providing an image as a search result, as described above, when the file name of the image includes the query entered by the user or the query entered by the user in the text file related to the image, the image is returned as the search result. Since the images provided in the search results may not be related to the query entered by the user or have poor quality, the reliability of the search service may be lowered when these images are provided as the search results. There is a problem.

In addition, in the case of providing a bulletin board service through the Internet in addition to the above-described search service, various image contents are registered and provided. However, as described above, when images of poor quality are registered and provided in the bulletin board, the reliability of users is high. There is a problem that can be degraded.

Since the problem of the quality of the image may become more serious as the range of service provision through the Internet is expanded, a method of evaluating the quality of the image is required to solve such a problem.

SUMMARY OF THE INVENTION The present invention has been made in an effort to provide an image quality index calculation method and system capable of calculating a quality index of a corresponding image by using one or more feature information extracted from an image.

An image quality index calculation method according to an aspect of the present invention for achieving the above object includes at least one of the image basic information, color distribution information, gray distribution information, and texture information from a predetermined image. Extracting feature information; And calculating a quality index of the image by using at least two feature information of the feature information.

The basic image information may include at least one of a size value of the image, a ratio of a width and a height of the image, and compression information of the image. Here, the size value of the image is determined as a first value when the product of the width and the height of the image is larger than a threshold value, and the width and the width of the image when the product of the width and height of the image is less than or equal to the threshold value. It is determined by the ratio of the log value of the product of the height and the log value of the threshold, the compression information of the image may be defined as the ratio of the byte size of the image multiplied by the width and height of the image. .

The color distribution information includes at least one of color histogram information, color channel information, and geometric color distribution information. Here, the color histogram information includes the number of color bins in which the probability of occurrence of color bins included in the image is greater than or equal to a threshold, the maximum value of the probability of occurrence of all color bins, and the maximum value of the probability of occurrence of all color bins. And at least one of a ratio of a second maximum value, a color / monochrome flag, and a difference value between an appearance probability value of color bins included in a reference color histogram and an occurrence probability value of color bins included in a color histogram of the image, wherein the color channel The information includes at least one of an average HSV (Hue, Saturation, Value) value of the entire image and an average HSV value of a central region of the image, wherein the geometric color distribution information is each of the average HSV value of the entire image and the image. It characterized in that it comprises a difference value of each average HSV value of the middle region.

The gray distribution information may include the number of gray bins having an appearance probability value greater than or equal to a threshold value among the total gray bins included in the image, a maximum value of the appearance probability values of all gray bins, and an appearance probability value of all gray bins. At least one of the ratio of the maximum value and the second maximum value.

In addition, the texture information is defined as a statistical value for the spatial distribution of gray values constituting the image, the texture information may be calculated using a Gray-Level Co-occurrence Matrix (GLCM), wherein the The texture information is at least one of an energy value, an entropy value, a correlation value, an inertia value, and a local homogeneity value calculated using the GLCM. do.

In an embodiment, the calculating of the image quality index may include: calculating a quality index of the image using at least two feature information of the extracted feature information; Applying a penalty to the quality index when specific feature information of the extracted feature information is included within a predetermined range; And calculating a final quality index by compensating for the quality index when the quality index becomes a reference value or less as a result of applying the penalty to the quality index.

The image quality index calculation method may further include determining whether the corresponding image is an abnormal image by using some characteristic information of the extracted feature information. It is characterized by determining the quality index of the image as the lowest value.

The image quality index calculation method may further include reflecting weights calculated for each feature information in each of the extracted feature information. In the image quality index calculation step, the feature information reflecting the weights may be used. The image quality index may be calculated. In this case, the weight may be calculated by applying a logistic regression method to a predetermined training set.

The image quality index calculation system according to another aspect of the present invention for achieving the above object, the feature information including at least one of the image basic information, color distribution information, gray distribution information, and texture information from a predetermined image Feature information extraction unit; And a quality index calculator for calculating a quality index of the image by using at least two feature information of the feature information.

As described above, according to the present invention, since the quality index of the corresponding image of the corresponding image is calculated using at least one feature information of image basic information, color distribution information, gray distribution information, and texture information extracted from a predetermined image. This has the effect of accurately assessing the quality of the image.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram of an image quality index calculation system according to an embodiment of the present invention. As shown, the image quality index calculation system 100 includes a feature information extractor 110, an abnormal image determiner 120, a weight reflector 125, and a quality index calculator 130.

The feature information extractor 110 extracts feature information of a corresponding image from a predetermined image. The feature information extractor 110 decodes an image compressed in various formats by using an image decoding library. Generate raw data in the form of (Red, Blue, Green). Then, the feature information is extracted from the corresponding image by applying an image processing technique to the generated raw data.

In one embodiment, the feature information extractor 110 may extract image basic information, color distribution information, gray distribution information, and texture information as feature information of the corresponding image. have. To this end, as shown in FIG. 1, the feature information extracting unit 110 includes an image basic information extracting unit 112, a color distribution information extracting unit 114, a gray distribution information extracting unit 116, and a texture information extracting unit. 118;

The basic image information extractor 112 extracts basic image information from a predetermined image. In an exemplary embodiment, the basic image information extractor 112 extracts image size and width of the image as image basic information. At least one of a ratio of height and compressed information of an image may be extracted.

The image size value is a value representing the size of a predetermined image, and the image basic information extractor 112 may determine the size value of the image by comparing a value obtained by multiplying the width and the height of the corresponding image with a threshold. Specifically, if the product of the width and height of the image is larger than the threshold, the size of the image is determined as 1, and if the product of the width and height of the image is less than or equal to the threshold, the product of the width and height of the image is multiplied. The ratio of the log value of the log and the log value of the threshold may be determined as the size value of the corresponding image. In one embodiment, the threshold for determining the size value of the image may be set to a maximum size value of the image, which may be 300 in width and 400 in height. A method of calculating an image size value is expressed by Equation 1 below.

The ratio of the width to the height of the image can be determined within a range of 1 or less, which means that it sets a maximum value of 1 for an image with the same height and width of the image.

The image compression information is conceived that the image may have better quality than that of which the image is compressed much. The image basic information extracting unit 112 calculates the bit per pixel constituting the image. Compression information can be calculated. At this time, the number of bits per pixel can be calculated by dividing the byte size constituting the image by the product of the width and height of the image, which is expressed by Equation 2 below.

Next, the color distribution information extractor 114 extracts color distribution information from the image. In one embodiment, the color distribution information extractor 114 extracts color histogram information and color as color distribution information. Color channel distribution information and geometric color distribution information may be extracted.

The color histogram means that color bins corresponding to each pixel are determined by using HSV (Hue, Saturation, Value) values of each pixel of the corresponding image, and the probability of occurrence of these color bins is represented graphically. . Where H means the color of the image, S means the brightness of the image, V means the saturation of the image.

The color distribution information extracting unit 114 is color histogram information. The number of color bins in which the probability of occurrence of the color bins included in the image is greater than or equal to the threshold, the maximum value of the probability of occurrence of all the color bins included in the image, and the corresponding image. The color bins of the reference color histogram having a ratio between the maximum value and the second largest value among the probability values of all the color bins included in the image, the probability of occurrence of each of the color bins constituting the image, and the uniform probability of uniformity. At least one of the difference value of the probability of appearance and the color / monochrome flag is extracted.

For example, as shown in FIG. 2A, when the threshold for the appearance probability value of the color bins is 0.02, among the 512 color bins, there are seven color bins whose probability of occurrence is 0.02 or more, and the maximum value of the appearance probability is 0.241. It can be seen that the ratio of the maximum value of the probability (0.241) and the second largest value (0.232) is 1.04. Here, the ratio of the maximum value of the probability of occurrence to the second largest value may mean that the image quality is not good.

In addition, the difference between the appearance probability value of each of the color bins constituting the image and the appearance probability value of the color bins of the reference color histogram having a uniform appearance probability value is 0.1 as the probability value of the color bin is 0.1. All can be calculated using the same reference color histogram. At this time, the difference (D) between the appearance probability value of the color bins of the reference color histogram and the color bins of the color histogram of the corresponding image may be calculated using Equation 3 below.

Where I represents an image corresponding to the reference color histogram, I 'represents the image, f _j represents the probability of occurrence of the j-th color bin of the reference color histogram, and f _j ' represents _{j of} the color histogram of the image. The probability of occurrence of the first color bean.

On the other hand, the color / black and white flag indicates whether the image is black and white / color, and whether or not the black and white / color of the image can be determined using the degree that the pixel value of the image is distributed in a specific color. For example, when the pixel values of the image are concentrated only on the black and white axes in the HSV color space, the image is determined as a black and white image.

The color channel distribution information includes at least one of an average HSV value of the entire image and an average HSV value of the center region of the image. That is, as shown in FIG. 2C, the color distribution information extractor 114 configures an average of H values, an average of S values, and an average of V values of the pixels constituting the image, and a central region of the image. At least one of an average of an H value, an average of an S value, and an average of a V value of all pixels is calculated as color channel distribution information of the corresponding image.

On the other hand, the geometric color distribution information means a difference between each average HSV value of the image and the average HSV value of the center region of the image. That is, as shown in FIG. 2C, the color distribution information extracting unit 114 calculates a difference value between each average HSV value of the entire image and the average HSV value of the center region of the image as geometric color distribution information of the corresponding image. It is.

Here, a small difference between the calculated HSV value of the center region and the entire HSV value of the image, which may be characteristic of the image, may mean that the quality of the image is not good. have.

Next, the gray distribution information extractor 116 extracts gray distribution information from the corresponding image. In one embodiment, the gray distribution information extractor 114 extracts gray histogram information as gray distribution information. can do.

The gray histogram is a graph showing probability values of all gray bins constituting the image in a graph form, and the gray distribution information extractor 116 is included in the image as shown in FIG. 3 as gray histogram information. The number of gray bins whose threshold probability is greater than or equal to the threshold, the maximum value of the probability of occurrence of all gray bins included in the image, and the second maximum value of the probability of occurrence of all the gray bins included in the image. At least one of the ratios of the large values can be extracted.

For example, in FIG. 3, when the threshold for the appearance probability value of the gray bins is 0.02, five color bins having a probability of occurrence of 0.02 or more out of 128 total gray bins are 5, the maximum value of the probability of occurrence is 0.241, and the maximum value of the probability of appearance. We can see that the ratio of (0.241) to the second largest value (0.232) is 1.04.

Like the histogram information, the gray histogram information may mean that the image quality is not good because the ratio of the maximum value of the appearance probability value to the second largest value is large.

Next, the texture information extractor 118 extracts texture information of the image from the image, where texture information is defined as a statistical value for the spatial distribution of gray values constituting the image. In one embodiment, the texture information extractor 118 may calculate texture information of the image using a gray-level co-occurrence matrix (GLCM) technique.

The GLCM technique is a method for expressing the spatial relationship between two pixels. As shown in FIG. 4, the average, contrast, and correlation of brightness values of neighboring pixels are averaged using distances and angles between neighboring pixels. It is a technique of calculating basic statistics such as relations, and expressing the calculated values by assigning new brightness values to the central pixels in the kernel and expressing them as partial texture features of the image.

In one embodiment, the texture information extractor 118 corresponds to an energy value, an entropy value, a correlation value, an inertia value, and a homogeneity value using GLCM. Can be calculated with the texture information of the image.

Here, the energy value is a value representing the uniformity of the contrast value in the image, and if the contrast value appears in a constant or repeated form, the image has a large energy value, otherwise the image has a low energy value. Will have

The entropy value represents the degree of disorder or confusion of the image, that is, the randomness of the intensity distribution. If the difference in contrast between pixels in the image varies, the image has a large entropy value, and the difference in contrast varies. Otherwise, the image will have a small entropy value. In other words, it can be seen that the entropy value tends to be inversely proportional to the energy value.

The correlation value represents a linear dependence of contrast between two neighboring pixels in the image, and if a specific pattern exists in the distribution of contrast values, it is determined that there is a correlation. For example, a correlation value of 0 indicates no correlation, and a correlation value of 1 indicates perfect correlation. That is, if a similar contrast pattern appears at a specific distance, the image has a high correlation value.

The inertia value represents the inertia of the contrast within the image. The inertia value can be calculated using the difference between the contrasts of two adjacent pixels. The larger the difference between the two pixels, the larger the inertia of the image. It will have a value.

The homogeneity value indicates the homogeneity of the pixels in the image. The more similar contrast values within a certain distance, the greater the homogeneity of the image. The more contrast values within a certain distance, the smaller the homogeneity of the image. do.

In this case, the texture information extractor 118 may calculate the GLCM used to calculate the energy value, entropy value, correlation value, inertia value, and homogeneity value by using Equation 4 below.

Here, P (i, j; d, Θ) means a joint probability density function, i and j are the first coordinate (k, l) and the second coordinate (m) of the corresponding image, respectively. , n) means a gray value, and d means the distance between the first coordinate and the second coordinate, and is defined as in Equation 5, and Θ means the angle between the first coordinate and the second coordinate. It is defined as Equation 6.

In summary, the feature information extractor 110 uses the image basic information extractor 112, the color distribution information extractor 114, the gray distribution information extractor 116, and the texture information extractor 118. Image basic information, color distribution information, gray distribution information, and texture information are extracted from the corresponding image.

Next, the abnormal image determination unit 120 performs a function of determining whether the corresponding image is an abnormal image. Here, the abnormal image is, for example, the image is composed only of a graph or a table, or the image is black. Or it means an image that consists of only white, or when the ratio of the width and height of the image is less than the threshold.

In an embodiment, the abnormal image determiner 120 may determine the corresponding image as an abnormal image when some feature information among the feature information extracted by the feature information extractor 110 is equal to or less than a predetermined value.

For example, among the feature information extracted by the feature information extractor 110, the compressed information of the image, the number of color bins in which the appearance probability value of the color bins included in the image is greater than or equal to a threshold, and the total gray bins included in the image. The maximum value of the probability of appearance, the ratio of the maximum value and the second largest value among the probability values of all the color bins included in the image, the color / monochrome flag, and the gray whose probability of occurrence of the total gray bins in the image is above the threshold. Characteristic information such as the number of bins, the maximum value of the probability of occurrence of the total gray bins included in the image, and the ratio of the maximum value and the second largest value of the probability of occurrence of the total gray bins included in the image may be higher than the threshold. If it is small, the image can be determined as an abnormal image.

If it is determined by the abnormal image determination unit 120 that the image is an abnormal image, the quality index of the corresponding image may be determined as 0 without going through the process of reflecting the weight and calculating the quality index described below.

The weight reflector 125 calculates a weight for each feature information extracted by the feature information extractor 110 and reflects the calculated weight for each feature information in the feature information. In one embodiment, the weight reflector 125 configures a training set using predetermined images and then applies regression analysis techniques such as logistic regression to each training set. Calculate the star weight.

In the above-described embodiment, although the weight reflecting unit 125 is described as an essential component of the image quality index calculation system 100, the weight reflecting unit 125 is optional because reflecting the weight on each feature information is optional. It may optionally be included. In addition, in the above-described embodiment, the weight reflector 125 calculates the weight for each feature information and reflects it for each feature information. In the modified embodiment, one weight is calculated for all the feature information. This may be reflected for each feature information.

The quality index calculator 130 calculates the quality index of the image by using the feature information extracted by the feature information extractor 110. Here, the weights calculated for each feature information by the weight reflecting unit 125 may be reflected in the extracted feature information.

In order to calculate the quality index of the image, the quality index calculator 130 may include a quality index calculator 132, a penalty applying unit 134, and a quality index compensation unit 136 as shown in FIG. 1. Can be.

The quality index calculator 132 calculates the quality index of the corresponding image by summing two or more feature information of the extracted feature information. In this case, the weights calculated for each feature information may be reflected in each feature information.

The penalty application unit 134 applies a predetermined penalty to the quality index calculated by the quality index calculator 132 when some feature information of the extracted feature information is included within a predetermined range. The reason for applying the penalty to the quality index through the penalty applying unit 134 is that the quality of the image may be very poor regardless of other feature information when specific feature information is included within a predetermined range. It is to reflect.

In an embodiment, the penalty applying unit 134 may determine that the size of the image is less than or equal to the threshold, the ratio of the width and height of the image is within the critical range, or the compression information of the image is less than or equal to the threshold. The number of color bins whose probability of occurrence is greater than or equal to a predetermined value among all the color bins constituting the image is equal to or less than a threshold value, or the maximum value of the probability values of all gray bins included in the image is greater than or equal to the threshold or all gray bins included in the image. A penalty may be applied to an image when a ratio between the maximum value and the second largest value of the probability of is greater than or equal to a threshold, or the average S value of the central region of the image is smaller than or equal to a threshold.

The quality index compensator 136 applies a penalty to the quality index calculated by the quality index calculator 132, resulting in a penalty when the quality index of the image becomes negative or the quality index of the image becomes smaller than the reference value. Compensates the applied quality index to calculate the final quality index for the image.

In one embodiment, the quality index calculator 130 may determine the quality grade of the image using the image quality index calculated through the above-described method. For example, if the final quality index of the image is 0, the image is determined to be an abnormal image rating. If the final quality index is less than 0.001, the image is determined to be a very poor rating, and the final quality index is greater than 0.001 and less than 0.002. In this case, the image may be determined to be of a poor grade. If the final quality index is greater than 0.001 and less than 1, the image may be of a general grade.

Hereinafter, a method of calculating an image quality index according to an embodiment of the present invention will be described in detail with reference to FIG. 5.

First, feature information is extracted from a predetermined image (S500). In one embodiment, at least one of basic image information, color distribution information, gray distribution information, and texture information may be extracted as feature information of the corresponding image.

Here, the basic image information includes at least one of a size value of the image, a ratio of the width and height of the image, and compression information of the image, and the color distribution information includes color histogram information, color channel information, and geometric color distribution information. The gray distribution information includes at least one gray histogram of the corresponding image. The color histogram information, the color channel information, the geometric color distribution information, and the gray histogram information may again include various detailed information. The various detailed information included in each information may be described in the description of the image quality index calculation system described above. Since the description in detail will be omitted.

Meanwhile, the texture information refers to a statistical value of a spatial distribution of gray values constituting the image, and may be calculated using a gray-level co-occurrence matrix (GLCM) in one embodiment. Specifically, the present invention can calculate the energy value, entropy value, correlation value, inertia value, and homogeneity value from the GLCM value with such texture information.

Next, it is determined whether the corresponding image is an abnormal image using the extracted feature information (S510). Here, the abnormal image refers to an image such as when the image is composed only of a graph or table, the image is composed only of black or white, or the ratio of the width and height of the image is less than a threshold.

According to an embodiment of the present disclosure, when some feature information of the extracted feature information is less than or equal to a predetermined value, the present invention may determine the corresponding image as an abnormal image. The number of color bins in which the probability of occurrence of color bins is greater than or equal to the threshold, the maximum value of the probability of occurrence of all gray bins included in the image, and the maximum value of the probability of occurrence of all the color bins included in the image. The ratio of large values, color / monochrome flags, the number of gray bins whose threshold probability is above the threshold, the maximum of all gray bins included in the image, and included in the image Characteristics such as the ratio of the maximum value to the second largest value of the occurrence probability of the entire gray bins Information is available.

As a result, if it is determined that the image is an abnormal image, the final quality index of the image is determined as 0 (S580). If it is determined that the image is not an abnormal image, the weight for each feature information is extracted for each feature information extracted. Reflect (S520). In one embodiment, the weight for each feature information may be calculated by configuring a training set using predetermined images and then applying a logistic regression method to the training set.

In the present embodiment, the weight reflecting step is described as an essential process, but since the weight reflecting is optional, the weight reflecting step may be selectively included. In addition, in the above-described embodiment, the weight calculated for each feature information is described as reflecting each feature information. However, in the modified embodiment, the same weight may be reflected for all feature information.

Next, the quality index of the corresponding image is calculated by summing two or more feature information among the feature information reflecting the weight (S530).

Thereafter, it is determined whether the specific feature information among the feature information extracted in step S500 is included within a predetermined range (S540), and when included within the predetermined range, a predetermined penalty is applied to the quality index calculated in step S530. Here, the reason for applying the penalty to the quality index is to reflect this in the image quality index since the quality of the image may be very poor regardless of other feature information when the specific feature information is included within a predetermined range.

For example, the size value of the image is less than or equal to the threshold, the ratio of the width and height of the image is within the threshold range, the compression information of the image is less than or equal to the threshold, and the probability of occurrence of all color bins constituting the image is predetermined. The number of color bins above the value is less than or equal to the threshold, or the maximum of the probability values of all the gray bins included in the image is greater than or equal to the threshold, or second to the maximum value of the probability of the total gray bins included in the image. If the ratio of the large value is more than the threshold or the average S value of the central region of the image is less than the threshold, a penalty may be applied to the image.

On the other hand, if the specific feature information is not included within the predetermined range as a result of the determination in step S540 determines the quality index calculated in step S530 as the final quality index of the image (S580).

Next, it is determined whether the quality index to which the penalty is applied is negative or less than the reference value (S560). If the quality index is determined to be negative or less than the reference value, the quality index to which the penalty is applied is compensated (S570), and the compensated quality index is applied. Determine the final quality index for the image (S580).

On the other hand, if it is determined in step S560 that the quality index to which the penalty is applied is not negative or less than the reference value, the quality index to which the penalty is applied is determined as the final quality index of the image (S580).

In an embodiment, in the final quality index determination step, the quality grade of the corresponding image may be determined using the final image quality index calculated through the above-described process. For example, if the final image quality index is 0, the image is determined to be an abnormal image grade; if the final quality index is less than 0.001, the image is determined to be very poor; if the final quality index is greater than 0.001 and less than 0.002, An image may be determined to be of poor grade, and if the final quality index is greater than 0.001 and less than 1, the image may be of general grade.

The above-described image quality index calculation method may also be implemented in a program form that can be executed using various computer means. In this case, a program for performing the image quality index calculation method may include a hard disk, a CD-ROM, a DVD, a ROM ( ROM), a RAM, or a flash memory, such as a computer readable recording medium.

Those skilled in the art to which the present invention pertains will understand that the present invention can be implemented in other specific forms without changing the technical spirit or essential features.

For example, in the above-described embodiment, the penalty application unit, the quality index compensation unit, the penalty application process, and the quality index compensation process are described as essential components, but the result of simply adding the feature information without applying the penalty and compensation of the quality index Since may be determined as the final quality index of the image, in this case, the penalty application unit, the quality index compensation unit, the penalty application process and the quality index compensation process may be omitted.

Therefore, it is to be understood that the embodiments described above are exemplary in all respects and not restrictive. The scope of the present invention is shown by the following claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

1 is a schematic block diagram of an image quality index calculation system according to an embodiment of the present invention.

2A illustrates a method of extracting color histogram information in accordance with an embodiment of the present invention.

2B illustrates a method of extracting color channel distribution information according to an embodiment of the present invention.

2C is a diagram illustrating a method of extracting daughter geometric color distribution information in an embodiment of the present invention.

3 is a diagram illustrating a method of extracting gray histogram information according to an embodiment of the present invention.

4 is a diagram illustrating a method of extracting texture information according to an embodiment of the present invention.

5 is a flowchart showing a method of calculating an image quality index according to an embodiment of the present invention.

Claims (22)

Extracting feature information including at least one of basic image information, color distribution information, gray distribution information, and texture information from a predetermined image; And Calculating a quality index of the image using the feature information; The image quality index calculation step Calculating a quality index of the image using at least two feature information of the feature information; Applying a penalty to the quality index when specific feature information of the extracted feature information is included within a predetermined range; And And calculating a final quality index by compensating for the quality index when the quality index becomes a reference value or less as a result of applying the penalty to the quality index. The method of claim 1, And the basic image information includes at least one of a size value of the image, a ratio of a width and a height of the image, and compression information of the image. The method of claim 2, The size value of the image is determined as a first value when the product of the width and height of the image is larger than a threshold, and the width and height of the image when the product of the width and height of the image is less than or equal to the threshold. The image quality index calculation method, characterized in that determined by the ratio of the log value for the product and the log value of the threshold. The method of claim 2, And the compressed information of the image is defined as a ratio of a byte size of the image multiplied by a width and a height of the image. The method of claim 1, The color distribution information includes at least one of color histogram information, color channel information, and geometry color distribution information. The color channel information includes at least one of an average HSV (Hue, Saturation, Value) value of an entire image and an average HSV value of a central region of the image, and the geometric color distribution information is equal to each of the average HSV values of the entire image. And a difference value of each average HSV value of the center area of the image. The method of claim 5, The color histogram information includes the number of color bins in which the probability of occurrence of color bins included in the image is greater than or equal to a threshold, the maximum value of the probability of occurrence of all color bins, the maximum value and the second maximum value in the probability of occurrence of all color bins. An image quality comprising at least one of a ratio of values, a color / monochrome flag, and a difference value of an appearance probability value of color bins included in a reference color histogram and an occurrence probability value of color bins included in the color histogram of the image. Index calculation method. delete delete The method of claim 1, The gray distribution information includes a maximum number of gray bins in which the probability of occurrence of the total gray bins included in the image is greater than or equal to a threshold, a maximum value of the probability of occurrence of all the gray bins, and a probability of occurrence of the total gray bins. And gray histogram information including at least one of a ratio between a value and a second maximum value. The method of claim 1, And the texture information is defined as a statistical value for a spatial distribution of gray values constituting the image. The method of claim 1, And the texture information is calculated using a gray-level co-occurrence matrix (GLCM). The method of claim 11, The texture information is at least one of an energy value, an entropy value, a correlation value, an inertia value, and a local homogeneity value calculated using the GLCM. Image quality index calculation method. delete The method of claim 1, Determining whether the corresponding image is an abnormal image by using some feature information of the extracted feature information; And determining that the quality index of the image is the lowest value when the image is an abnormal image. The method of claim 1, And reflecting the weights calculated for each feature information in each of the extracted feature informations, In the image quality index calculation step, the image quality index calculation method, characterized in that for calculating the image quality index by using the feature information reflecting the weight. The method of claim 15, And the weight is calculated by applying a logistic regression method to a predetermined training set. A computer-readable recording medium having recorded thereon a program for performing the method according to any one of claims 1 to 6 or 9 to 12 or 14 to 16. A feature information extracting unit for extracting feature information including at least one of basic image information, color distribution information, gray distribution information, and texture information from a predetermined image; And A quality index calculator for calculating a quality index of the image using the feature information; The quality index calculation unit, A quality index calculator configured to calculate a quality index of the image using at least two feature information of the feature information; A penalty application unit applying a penalty to the quality index when specific feature information of the extracted feature information is included within a predetermined range; And And a quality index compensator for calculating a final quality index by compensating for the quality index when the quality index becomes less than a reference value as a result of applying the penalty to the quality index. The method of claim 18, wherein the feature information extracting unit, An image basic information extracting unit extracting the basic image information including at least one of a size value of the image, a ratio of a width and a height of the image, and compressed information of the image; A color distribution information extraction unit configured to extract the color distribution information including at least one of color histogram information, color channel information, and geometric color distribution information from the image; A gray distribution information extracting unit extracting the gray distribution information defined by the gray histogram of the image from the image; And A texture information extracting unit extracting the texture information defined as a statistical value of a spatial distribution of gray values constituting the image from the image, The color channel information may include at least one of an average HSV (Hue, Saturation, Value) value of the entire image and an average HSV value of the central region of the image, and the geometric color distribution information may be equal to each of the average HSV values of the entire image. And a difference value of each average HSV value of the center area of the image. delete The method of claim 18, The apparatus may further include an abnormal image determiner configured to determine whether the corresponding image is an abnormal image by using some feature information of the extracted feature information. The quality index calculation unit, if the image is an abnormal image image quality index calculation system, characterized in that for determining the minimum quality index of the image. The method of claim 18, The apparatus further includes a weight reflecting unit configured to calculate a weight for each of the extracted feature information, and to reflect the calculated weight for each feature information to each feature information. The quality index calculation unit, the image quality index calculation system, characterized in that for calculating the image quality index by using the feature information reflecting the weight.

Images