KR102055253B1

KR102055253B1 - Apparatus for enhancing image and method thereof

Info

Publication number: KR102055253B1
Application number: KR1020150059916A
Authority: KR
Inventors: 김세훈; 최원희; 김창수; 이세호; 고영준; 김영배
Original assignee: 삼성전자주식회사; 고려대학교 산학협력단
Priority date: 2015-04-28
Filing date: 2015-04-28
Publication date: 2019-12-13
Also published as: KR20160128101A

Abstract

An image enhancement apparatus for improving the contrast ratio of an image is disclosed. The image enhancement device calculates a weight to be applied to a corresponding pixel based on an input unit receiving an image including a backlight area and a non-backlight area and pixel brightness of each pixel in the input image, and a distance between each pixel and another pixel, And a processor configured to apply the calculated weight to the pixel brightness of each pixel included in the backlight area to improve the contrast ratio of the input image.

Description

Image Enhancement Device and Image Enhancement Method {APPARATUS FOR ENHANCING IMAGE AND METHOD THEREOF}

The present invention relates to an image enhancement apparatus and an image enhancement method, and more particularly, to an image enhancement apparatus and an image enhancement method for improving contrast ratio of an image including a backlight region.

With the rapid growth of the smart phone market, the performance of the portable terminal has developed remarkably, and in particular, the portable terminal has various multimedia functions. Among the functions of the mobile terminal, the camera function is frequently used because it can easily and quickly acquire an image by replacing a digital camera. However, since users who take images through the portable terminal are generally not experts, when the image is taken through the portable terminal, a low contrast ratio of the subject is often caused by backlight.

In addition, the camera of the portable terminal is vulnerable to a low light environment, such as backlight, because of the small module size and low performance. In this case, it is possible to obtain an effect of acquiring a normal image which is not distorted by the backlight by detecting the backlight region in the image and improving the contrast ratio.

In the prior art, discontinuities in the boundary pixel brightness were generated by dividing the backlight region and the non-backlit region. Discontinuity means that a sudden change in pixel brightness occurs at the boundary between the backlight area and the non-backlight area. In addition, the conventional method for improving the contrast ratio of the backlight region has a problem in that the color of the bright region aggregates in the non-backlit region and the detail of the image is damaged.

SUMMARY OF THE INVENTION An object of the present invention is to provide an image enhancement apparatus and an image enhancement method for improving a contrast ratio of an image by applying a weight to a pixel brightness of an image having a backlight region.

According to an aspect of the present invention, there is provided an apparatus for improving an image contrast ratio, including: an input unit configured to receive an image including a backlight area and a non-backlight area, and a pixel of each pixel in the input image A weight to be applied to the corresponding pixel is calculated based on the brightness and the distance between the respective pixels and the other pixel, and the calculated weight is applied to the pixel brightness of each pixel included in the backlight region. A processor that improves contrast ratio.

In this case, the processor may detect the backlight area and the non-backlight area by using color intensity values representing pixel intensity and color difference between each pixel in the input image.

The processor may calculate the weight to be proportional to the number of pixels having the same pixel brightness as the pixel brightness of each pixel and inversely proportional to a distance from the pixel having the same pixel brightness.

The processor may calculate the weight to be inversely proportional to the distance between the pixel brightness of each pixel and a pixel having a pixel brightness within a predetermined range.

In this case, the processor may calculate the weight to be inversely proportional to the pixel brightness difference between the pixel brightness of each pixel and a pixel having a pixel brightness within the preset range.

The processor may apply the calculated weight to pixel brightness of each pixel included in the backlight area and the non-backlight area, and apply the weighted input image and the non-backlight of the input image to which the weight is not applied. By combining regions, the contrast ratio of the input image may be improved.

In this case, the processor calculates a predetermined value for increasing a brightness difference between the pixel and the adjacent pixel based on the pixel brightness of each pixel in the input image and the distance between the pixel and the at least one adjacent pixel. The predetermined ratio may be added to each pixel to which the weight is applied to improve the contrast ratio of the input image.

The processor may further include a first numerical value calculated based on the number of pixels having the same pixel brightness as the pixel brightness of each pixel and a distance from the pixel having the same pixel brightness, and at least one adjacent pixel. The weight may be calculated by multiplying a second value calculated based on a brightness difference between the pixels and a distance between each pixel and an adjacent pixel.

In addition, the processor is configured to set a super pixel composed of a set of pixels whose pixel brightness is within a predetermined range in the input image, and calculate the first pixel based on a weight to be applied to each pixel included in the super pixel. The backlight region may be detected based on a third value and a fourth value calculated based on an average pixel brightness of the super pixel.

In this case, the third numerical value may be a value obtained by normalizing the calculated weight, and the fourth numerical value may be a value obtained by inverting and normalizing an average pixel brightness of the super pixel.

On the other hand, the image enhancement method for improving the contrast ratio of the image according to an embodiment of the present invention, the step of receiving an image including a backlight region and a non-backlight region, the pixel brightness of each pixel in the input image, and each pixel Calculating a weight to be applied to the corresponding pixel based on a distance between the pixel and another pixel, and improving the contrast ratio of the input image by applying the calculated weight to the pixel brightness of each pixel included in the backlight region. It includes.

In this case, the improving may include detecting the backlight area and the non-backlight area by using a color contrast value indicating a pixel intensity of each pixel and a color difference between each pixel in the input image.

The calculating may include calculating the weight so as to be proportional to the number of pixels having the same pixel brightness as the pixel brightness of each pixel and inversely proportional to a distance from the pixel having the same pixel brightness.

The calculating may include calculating the weight to be inversely proportional to the distance between the pixel brightness of each pixel and a pixel having a pixel brightness within a predetermined range.

In this case, the calculating may include calculating the weight to be inversely proportional to a pixel brightness difference between the pixel brightness of each pixel and a pixel having a pixel value within the preset range.

The improving may include applying the calculated weight to pixel brightness of each pixel included in the backlight area and the non-backlight area, and applying the weight to the input image to which the weight is applied and the input image to which the weight is not applied. A non-backlit area may be synthesized to improve the contrast ratio of the input image.

In this case, the improving may include setting a predetermined numerical value for increasing a difference in brightness between the pixel and the adjacent pixel based on the pixel brightness of each pixel in the input image and a distance between the pixel and the at least one adjacent pixel. May be calculated and the predetermined numerical value may be added to each pixel to which the weight is applied to improve the contrast ratio of the input image.

The calculating may include a first value calculated based on the number of pixels having the same pixel brightness as the pixel brightness of each pixel and a distance from the pixel having the same pixel brightness and at least one of the pixels. The weight may be calculated by multiplying a second value calculated based on a brightness difference between adjacent pixels and a distance between each pixel and the adjacent pixel.

The improving may include setting a super pixel composed of a set of pixels whose pixel brightness is within a predetermined range in the input image, and calculating the super pixel based on a weight to be applied to each pixel included in the super pixel. The backlight region may be detected based on the third value calculated and the fourth value calculated based on the average pixel brightness of the super pixel.

As described above, according to various embodiments of the present disclosure, weighting is applied to the pixel brightness of the backlight area to improve the contrast ratio of the image including the backlight area without discontinuity between the backlight area and the non-backlight area.

1 is a block diagram illustrating a configuration of an image enhancement apparatus according to an exemplary embodiment.
FIG. 2 is a block diagram illustrating a detailed configuration of the image improving apparatus illustrated in FIG. 1.
3 to 6 are diagrams for describing a method of calculating a weight for a pixel brightness of an input image according to an exemplary embodiment.
7 is a diagram illustrating a histogram to which weights are applied according to an embodiment of the present invention.
8 is a diagram illustrating a first numerical value, a second numerical value, and a weight applied to pixel brightness of an input image according to an exemplary embodiment.
9 is a diagram for describing a process of applying weights to pixel brightness of an input image according to an exemplary embodiment.
10 is a flowchart illustrating an image improving method according to an exemplary embodiment.
11 is a diagram illustrating an image to which an image improving method is applied according to an exemplary embodiment.

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

1 is a block diagram illustrating a configuration of an image enhancement apparatus according to an exemplary embodiment.

The image improving apparatus 100 may be implemented in the form of a photographing apparatus to improve the contrast ratio of the image photographed by the photographing apparatus. In addition, the image enhancement apparatus 100 may be implemented in the form of a TV, a tablet PC, a PMP, a PDA, a smartphone, a digital picture frame, an e-book, and the like.

The input unit 110 may receive an image from the outside. Here, the image may be an image including a backlight area and a non-backlight area. The input unit 110 may receive an image by wireless or wired, and in the case of wireless, may receive an image through a communication method such as Bluetooth or Wi-Fi.

The processor 120 may detect a backlight area and a non-backlight area in the input image by using the pixel intensity of each pixel in the input image and a color contrast value representing the color difference between the pixels. In detail, the processor 120 first divides the input image by setting a super pixel from the input image. Here, the superpixel refers to a set of pixels composed of pixels whose pixel brightness is within a predetermined range in the image. Subsequently, the processor 120 may detect the backlight region based on a third value normalized by applying a weight to the super pixel and a fourth value normalized by inverting the average pixel brightness of the super pixel.

The processor 120 may calculate a weight to be applied to the pixel based on the pixel brightness of each pixel in the input image and the distance between each pixel and another pixel. In detail, the processor 120 may calculate a weight so as to be proportional to the number of pixels having the same pixel brightness as the pixel brightness of each pixel and inversely proportional to the distance from the pixel having the same pixel brightness.

In addition, the processor 120 may calculate a weight to be inversely proportional to a pixel brightness of each pixel and a distance having a pixel brightness within a preset range, and the processor 120 may calculate the pixel brightness of each pixel and the pixel brightness within the preset range. The weight can be calculated so as to be inversely proportional to the difference in pixel brightness from the pixel to have.

The processor 120 may generate a histogram to which the weight is applied to calculate pixel brightness of each pixel. For example, when a large number of pixels having the same pixel brightness exist in a particular area, since a high weight is applied to the particular area, the pixel brightness difference of each pixel increases in the histogram, thereby improving the image clearly.

The processor 120 may improve the contrast ratio of the input image by applying a weight to the pixel brightness of the backlight region. In detail, the processor 120 may apply a weight calculated to the pixel brightness of each pixel in the backlight region, and apply the weighted pixel brightness to each pixel in the backlight region to improve the contrast ratio of the image.

In addition, the processor 120 may improve the contrast ratio of the input image by weighting the non-backlit area and the weighted backlit area of the input image. That is, the processor 120 does not apply weights to the non-backlit areas detected by the processor 120, but applies weights only to the backlit areas, and then weights the weighted backlit areas and non-weighted non-backlit areas. have. In the case of the non-backlit area, the pixel brightness is higher than that of the backlit area. When the weighted sum is applied to the non-backlit area, the color may aggregate and the detail of the image may be degraded. Therefore, the processor 120 may weight the non-backlit area to which the weight is applied to the non-backlight area to prevent color aggregation.

FIG. 2 is a block diagram illustrating a detailed configuration of the image improving apparatus illustrated in FIG. 1.

According to FIG. 2, the image enhancement apparatus 100 ′ includes an input unit 110, a processor 120, a storage unit 130, a video processor 140, and an audio processor 150. Detailed description of parts overlapping with those shown in FIG. 1 among the elements shown in FIG. 2 will be omitted.

The processor 120 controls the overall operation of the display apparatus 100 ′.

In detail, the processor 120 may access the RAM 121, the ROM 122, the main CPU 123, the graphic processor 124, the first to n interfaces 125-1 to 125-n, and the bus 126. Include.

The RAM 121, the ROM 122, the main CPU 123, the graphics processor 124, the first through n interfaces 125-1 through 125-n, and the like may be connected to each other through the bus 126.

The first to n interfaces 125-1 to 125-n are connected to the various components described above. One of the interfaces may be a network interface connected to an external device via a network.

The main CPU 123 accesses the storage unit 130 and performs booting using an operating system stored in the storage unit 130. Then, various operations are performed using various programs, contents, data, etc. stored in the storage 130.

The ROM 122 stores a command set for system booting. When the turn-on command is input and the power is supplied, the main CPU 123 copies the O / S stored in the storage unit 130 to the RAM 121 according to the command stored in the ROM 122 and executes O / S. Boot the system When booting is completed, the main CPU 123 copies various application programs stored in the storage unit 130 to the RAM 121 and executes the application programs copied to the RAM 121 to perform various operations.

The graphic processor 124 generates a screen including various objects such as an icon, an image, a text, and the like, using a calculator (not shown) and a renderer (not shown), for example, a screen including a pointing object. An operation unit (not shown) calculates attribute values, such as coordinate values, shapes, sizes, colors, and the like, on which objects are displayed based on the layout of the screen. The renderer generates a screen having various layouts including objects based on the attribute value calculated by the calculator. The screen generated by the renderer (not shown) is displayed in the user interface area.

3 to 6 are diagrams for describing a method of calculating a weight for pixel brightness of an input image according to an exemplary embodiment.

3 is a view for explaining the similarity between the interaction between electrons and the interaction between pixels. That is, the mutual repulsive force acts between the electrons, the strength of the repulsive force is proportional to the magnitude of the charge amount and inversely proportional to the distance between the electrons. By applying this concept to a pixel, weights according to the first and second numerical values may be calculated.

Specifically, the first value and the second value may correspond to the charge amount and the electric field of the electron. The amount of charge in an electron means the total amount of charge passing through a point, and the electric field means a physical quantity that varies in size depending on the amount of charge of an interacting counterpart electron and its spatial distance from the counterpart electron. Similarly, the first value is a value that depends on the number of pixels having the same pixel brightness and the distance between the pixels, and the second value is a value that depends on the pixel brightness difference between the neighboring pixels and the distance between the pixels. That is, the first value and the second value may be determined by the pixel brightness and the distance between the pixels.

4 is a diagram for describing a process of calculating a first numerical value. In FIG. 4, the first numerical value may be calculated using pixels 402, 403, 404, and 405 having the same pixel brightness as the pixel p 401. The first numerical value increases as the number of pixels having the same pixel brightness as the pixel p increases. For example, the first numerical value of the pixel p may be calculated by Equation 1 below. When the pixel p is locally isolated from other pixels having the same pixel brightness, the probability of noise is high. Therefore, the first value is calculated by considering the distance from the pixel p.

here,

May be 1, and S (p) represents the backlight importance of the pixel p. Backlight importance can be calculated by calculating the inverted pixel brightness I (p) of the pixel p and then gamma correcting it as shown in Equation 2 below.

here,

May be 2.2.

5 is a diagram for describing a process of calculating a second numerical value. In FIG. 5, a second value may be calculated using pixels 501, 502, 503, and 504 having pixel brightness different from that of the pixel p 401. The second value becomes larger as pixels having different pixel brightnesses from the pixel p are spatially dense and the pixel brightness difference between the pixels is smaller. For example, the second value of the pixel p may be calculated by Equation 3 below. Can be. At this time, when the pixel brightness I (q) of the neighboring pixel is the same as the pixel brightness I (p) of the pixel p, it is assumed that there is no interaction between the two pixels.

here,

May be 0.8,

May be 1.

FIG. 6 is a diagram for describing a method of calculating a weight using a first value and a second value. The first numerical value calculated using the pixels 402, 403, 404, and 405 having the same pixel brightness as the pixel p 401 based on the pixel p and the pixels having a pixel brightness different from the pixel p 401 ( The weights may be calculated by multiplying the second values calculated using 501, 502, 503, and 504. That is, the weight f (p) may be calculated using Equation 4 below.

Here, f (p) represents a weight, Q (p) represents a second numerical value of the pixel p, and E (p) represents a first numerical value of the pixel p.

The processor 120 determines the pixel brightness of each pixel of the input image by using the calculated weight f (p), so that the contrast ratio of the input image having the backlight region can be more clearly improved.

7 is a diagram illustrating a weighted histogram.

Referring to FIG. 7, the normal histogram determines the pixel brightness of a specific pixel without considering the backlight region, whereas the weighted histogram weights the pixel brightness by considering the pixel brightness of the neighboring pixel and the distance between the pixels. By applying, the backlight area can be displayed more clearly.

78 is a diagram illustrating a result of normalizing an image to which a first value, a second value, and a weight are applied to [0,1]. 8 (a) is a normalized image, FIG. 8 (b) is a normalized image to which the first value calculated from the original image is applied, and FIG. 8 (c) is a normalized image to which the second value calculated from the original image is applied. 8 (d) shows a diagram in which the weighted image calculated using the first value and the second value is normalized.

Referring to FIG. 8B, since the density of the pixels having the same pixel brightness and the distance between the pixels are considered in the case of the first numerical value, the result normalized to [0,1] has a noticeable difference between the backlight area and the non-backlight area. Occurs, but details are poor. On the other hand, referring to FIG. 8 (c), since the second numerical value considers the degree of compactness of the pixels having different pixel brightness and the distance between the pixels, the result normalized to [0,1] is the difference between the backlight area and the non-backlight area Are separated equally without. Accordingly, in FIG. 8 (d), the weighted image in consideration of both the first value and the second value may be displayed brightly while preserving detail.

9 is a diagram for describing a process of improving contrast ratio of an image. 9 (a) shows an original image. It can be seen from FIG. 9A that the backlight region appears relatively dark.

9B is a diagram illustrating an initial contrast ratio improvement image in which an initial enhancement pixel brightness is applied to an input image. When the weight is calculated using the first value and the second value in the processor 120, the processor 120 may improve the contrast ratio of the input image using the calculated weight. Specifically, the processor 120 accumulates and normalizes a contrast ratio equal to or less than the pixel brightness I (p) of the pixel p to initially improve the pixel brightness.

Is calculated and applied to the input image. In this case, the contrast ratio may be calculated through the sum of weights, as shown in Equation 5 below.

9 (c) shows a weighted contrast ratio improvement image obtained by weighting an initial contrast ratio improvement image of a backlight region and an original image of the non-backlit region. As shown in FIG. 9B, since the initial contrast ratio improvement image is also weighted to the non-backlight area, the non-backlight area may be brightened, resulting in color aggregation and damage to detail. Therefore, in the case of a weighted contrast ratio improvement image in which the original image of the non-backlit region and the initial contrast ratio improvement image are fused without weighting, color aggregation and detail damage can be prevented. In this case, the weighted summation may be used to naturally connect the boundary between the backlight area and the non-backlight area.

Specifically, weighted contrast ratio improvement

May be calculated using Equation 6 below.

9 (d) is a diagram illustrating a final contrast ratio improvement image to which detail amplification is applied. In general, when the contrast ratio is increased, the detail of the image is damaged, and thus the final contrast ratio improvement image may be obtained by adding the detail amplification value to the weighted contrast ratio improvement image. Specifically, the detail amplification value B (p) can be calculated by Equation 7 below.

here,

Denotes an 8-connected neighbor pixel of pixel p.

Thereafter, as shown in Equation 8 below, the final contrast ratio improvement image may be obtained by summing detail amplification values to the weighted contrast ratio improvement image.

10 is a flowchart illustrating an image improving method according to an exemplary embodiment.

According to the image enhancement method illustrated in FIG. 10, first, an image is input (S910). Here, the image may include a backlight area and a non-backlight area.

Next, a weight to be applied to each pixel of the input image is calculated (S920). In detail, the weight may be calculated based on the pixel brightness of each pixel in the input image and the distance between the pixel and the other pixel.

Subsequently, the contrast ratio of the input image is improved by applying weights calculated to pixel brightness of each pixel included in the backlight region (S930).

In operation S930, the backlight area and the non-backlight area may be detected by using the pixel brightness of each pixel in the input image and a color contrast value representing the color difference between the pixels.

In operation S920, the weight may be calculated to be proportional to the number of pixels having the same pixel brightness as the pixel brightness of each pixel and inversely proportional to the distance from the pixel having the same pixel brightness.

In operation S920, the weight may be calculated to be inversely proportional to the distance between the pixel brightness of each pixel and the pixel having the pixel brightness within a preset range.

In operation S920, the weight may be calculated to be inversely proportional to the pixel brightness difference of the pixel and the pixel brightness difference between the pixel having the pixel value within the preset range.

In operation S930, the calculated weight is applied to the pixel brightness of each pixel included in the backlight area and the non-backlight area, and the contrast ratio of the input image is synthesized by combining the non-backlight area of the input image to which the weight is applied and the input image to which the weight is not applied. Can be improved.

In operation S930, based on the pixel brightness of each pixel in the input image and the distance between each pixel and at least one adjacent pixel, a predetermined value for increasing the brightness difference between the pixel and the adjacent pixel is calculated and weighted. The contrast ratio of the input image may be improved by adding predetermined values to each pixel.

In operation S920, the first numerical value calculated based on the number of pixels having the same pixel brightness as the pixel brightness of each pixel and the distance from the pixel having the same pixel brightness, and the brightness difference between each pixel and at least one adjacent pixel, and The weight may be calculated by multiplying a second value calculated based on the distance between each pixel and the adjacent pixel.

In operation S930, a super pixel configured with a set of pixels whose pixel brightness is within a preset range in the input image is set, and a third value calculated based on a weight to be applied to each pixel included in the super pixel, and The backlight region may be detected based on a fourth numerical value calculated based on the average pixel brightness of the super pixel.

The third numerical value may be a value obtained by normalizing the calculated weight, and the fourth numerical value may be a value obtained by inverting and normalizing the average pixel brightness of the super pixel.

As described above, according to various embodiments of the present disclosure, weighting is applied to the pixel brightness of each pixel of the backlight area to improve the contrast ratio of the image including the backlight area without discontinuity between the backlight area and the non-backlight area.

Meanwhile, the above-described methods according to various embodiments of the present disclosure may be implemented by only upgrading the existing image enhancement apparatus.

In addition, a non-transitory computer readable medium may be provided in which a program for sequentially performing the image enhancement method according to the present invention is stored.

For example, receiving an image including a backlight area and a non-backlight area, calculating a weight to be applied to the pixel based on pixel brightness of each pixel in the input image, and a distance between each pixel and another pixel, and backlighting A non-transitory computer readable medium may be provided in which a program for performing a step of improving contrast ratio of an input image by applying weights calculated to pixel brightness of each pixel included in an area is stored.

A non-transitory readable medium refers to a medium that stores data semi-permanently and is read by a device, not a medium storing data for a short time such as a register, a cache, a memory, and the like. Specifically, the various applications or programs described above may be stored and provided in a non-transitory readable medium such as a CD, a DVD, a hard disk, a Blu-ray disk, a USB, a memory card, a ROM, or the like.

11 is a diagram illustrating an image to which an image improving method is applied according to an exemplary embodiment.

Referring to FIG. 11, in the image to which the image enhancement method according to the exemplary embodiment of the present invention is applied, the contrast ratio of the backlight region and the non-backlit region is improved, and it is confirmed that no discontinuity occurs at the boundary between the backlight region and the non-backlit region. have.

In addition, although the preferred embodiment of the present invention has been shown and described above, the present invention is not limited to the above-described specific embodiment, the technical field to which the invention belongs without departing from the spirit of the invention claimed in the claims. Of course, various modifications can be made by those skilled in the art, and these modifications should not be individually understood from the technical spirit or the prospect of the present invention.

100: video enhancement device 110: input unit
120: processor

Claims

In the image enhancement device for improving the contrast of the image,
An input unit configured to receive an image including a backlight area and a non-backlight area; And
A weight to be applied to the pixel is calculated based on the pixel brightness of each pixel in the input image and the distance between the pixel and another pixel, and the calculated pixel brightness of each pixel included in the backlight area is calculated. And a processor configured to apply a weight to improve a contrast ratio of the input image.
The processor,
A third value calculated based on a weight to be applied to each pixel included in the super pixel, by setting a super pixel composed of a set of pixels whose pixel brightness is within a predetermined range in the input image; And the backlight region is detected based on a fourth numerical value calculated based on an average pixel brightness of.

The method of claim 1,
The processor,
And the non-backlit area is detected using a color contrast value representing a pixel intensity of each pixel in the input image and a color difference between the pixels.

The method of claim 1,
The processor,
And calculating the weight to be proportional to the number of pixels having the same pixel brightness as the pixel brightness of each pixel and inversely proportional to a distance from the pixel having the same pixel brightness.

The method of claim 1,
The processor,
And calculating the weight so as to be inversely proportional to a distance between the pixel brightness of each pixel and a pixel having a pixel brightness within a predetermined range.

The method of claim 4, wherein
The processor,
And calculating the weight to be inversely proportional to a pixel brightness difference between the pixel brightness of each pixel and a pixel having a pixel brightness within the predetermined range.

The method of claim 1,
The processor,
The calculated weight is applied to pixel brightness of each pixel included in the backlight area and the non-backlight area, and the input is performed by synthesizing the non-backlight area of the input image to which the weight is applied and the input image to which the weight is not applied. An apparatus for improving an image, characterized by improving an contrast ratio of an image.

The method of claim 6,
The processor,
Calculating a predetermined value for increasing a brightness difference between the pixel and the adjacent pixel based on a pixel brightness of each pixel in the input image and a distance between the pixel and the at least one adjacent pixel, And adding the predetermined numerical value to a pixel to improve the contrast ratio of the input image.

The method of claim 1,
The processor,
A first value calculated based on the number of pixels having the same pixel brightness as the pixel brightness of each pixel and a distance from the pixel having the same pixel brightness, and the difference in brightness between each pixel and at least one adjacent pixel, and the angle And calculating the weight by multiplying a second value calculated based on the distance between the pixel and the adjacent pixel.

delete

The method of claim 1,
And wherein the third numerical value is a value obtained by normalizing the calculated weights, and the fourth numerical value is a value obtained by inverting and normalizing an average pixel brightness of the super pixel.

In the image enhancement method for improving the contrast ratio of the image,
Receiving an image including a backlight area and a non-backlight area;
Calculating a weight to be applied to a corresponding pixel based on pixel brightness of each pixel in the input image and a distance between the pixel and another pixel; And
And improving the contrast ratio of the input image by applying the calculated weight to the pixel brightness of each pixel included in the backlight region.
The step of improving,
A third value calculated based on a weight to be applied to each pixel included in the super pixel, by setting a super pixel composed of a set of pixels whose pixel brightness is within a predetermined range in the input image; And detecting the backlight region based on a fourth numerical value calculated based on the average pixel brightness of.

The method of claim 11,
The step of improving,
And detecting the non-backlit area by using the pixel intensity of each pixel in the input image and a color contrast value representing a color difference between the pixels.

The method of claim 11,
The calculating step,
And calculating the weight proportional to the number of pixels having the same pixel brightness as the pixel brightness of each pixel and inversely proportional to the distance from the pixel having the same pixel brightness.

The method of claim 11,
The calculating step,
And calculating the weight so as to be inversely proportional to the distance between the pixel brightness of each pixel and a pixel having a pixel brightness within a predetermined range.

The method of claim 14,
The calculating step,
And calculating the weight so as to be inversely proportional to a pixel brightness difference between the pixel brightness of each pixel and a pixel having a pixel value within the predetermined range.

The method of claim 11,
The step of improving,
The calculated weight is applied to the pixel brightness of each pixel included in the backlight area and the non-backlight area, and the input is performed by synthesizing the non-backlight area of the input image to which the weight is applied and the input image to which the weight is not applied. An image enhancement method comprising improving the contrast ratio of an image.

The method of claim 16,
The step of improving,
Calculating a predetermined value for increasing a brightness difference between the pixel and the adjacent pixel based on the pixel brightness of each pixel in the input image and the distance between the pixel and the at least one adjacent pixel, And adding the predetermined numerical value to a pixel to improve the contrast ratio of the input image.

The method of claim 11,
The calculating step,
A first value calculated based on the number of pixels having the same pixel brightness as the pixel brightness of each pixel and a distance from the pixel having the same pixel brightness, and the difference in brightness between each pixel and at least one adjacent pixel, and the angle And multiplying a second value calculated based on a distance between a pixel and an adjacent pixel to calculate the weight.

delete

The method of claim 11,
The third numerical value is a value obtained by normalizing the calculated weight, and the fourth numerical value is a value obtained by inverting and normalizing an average pixel brightness of the super pixel.