KR20120030635A - Image processing method for backlight image judgment and image compensation on cell phone camera - Google Patents

Abstract

PURPOSE: An image processing method for improving back light image quality is provided to compensate back light image by automatically determining the back light image. CONSTITUTION: A mobile phone camera photographs an image(S30). If an auto back light correction function is selected, it is automatically determined whether the photographed image is back light image or not(S40,S50). If the automatic back light image correction function is not selected, the mobile phone camera stores the photographed image or manually selects the back light image correction function(S60). The mobile phone corrects the back light image(S70).

Description

Image processing method for improving backlight image quality based on mobile phone {Image processing method for backlight image judgment and image compensation on cell phone camera}

The present invention relates to an image processing method for improving a backlight image quality based on a mobile phone, and more particularly, to an image processing method for improving a backlight image quality based on a mobile phone, which improves the contrast of an image obtained using a mobile phone camera. .

Currently, various interfaces through mobile phones are no longer additional devices, but essential elements of modern society. Among them, camera functions of mobile phones can be used easily without using camera devices. It's so simple that camera functions are available on almost all phones.

However, since the mobile phone is not a device that deals with the camera function as a main purpose, there is a limit to expecting the high quality of the video from the mobile phone camera. Of course, the existing mobile phone has a camera correction function, but as shown in FIG. There is a cumbersome and inconvenient problem because you have to judge and adjust yourself.

In addition, the amount of memory and performance speed that can be tolerated in a mobile phone also makes camera correction functions simple and simple, so that backlit photos are more difficult to improve with the correction function in a mobile phone camera.

Therefore, the functions added to the mobile phone camera are simple and can only be processed one at a time, and since the existing mobile phones do not have an effective function to improve the backlight image, the user can People who want to erase pictures from their mobile phones or remember the memories of the moment have the disadvantage of going through the complicated process of correcting the images by using a program that can directly improve the image by transferring the backlight image to the PC.

In order to solve the problems described above, the present invention improves the contrast of the image obtained by using a mobile phone camera, when the user is taking a picture with a mobile phone due to backlight when the picture is dark and the image quality is lowered automatically The purpose of the present invention is to provide an image processing method for improving the quality of a backlight image of a mobile phone, which determines the quality of image quality and, when it is determined that the image is a backlight image, improves the image quality and processes the image vividly and brightly.

In addition, the present invention is adaptive because the user can select whether to handle the backlight in advance before shooting with a mobile phone, after the shooting can be improved by contrasting the range of stretching techniques by calculating the range of stretching according to each image RGB color contrast distribution value An object of the present invention is to provide an image processing method for improving a backlight image quality based on a mobile phone.

A method for achieving the object comprises the step 10 of selecting whether to automatically correct the backlight image when the image of the mobile phone; A 20th step of storing a command value corresponding to the backlight image when the backlight image is selected as the automatic correction and waiting for completion of the automatic correction setting; A thirtieth step of capturing and storing an image with a mobile phone camera; Determining whether the backlight automatic correction is selected; If the backlight automatic correction is selected, automatically determining whether the photographed image is a backlight image based on contrast; If backlight automatic correction has not been selected, step 60 for storing the photographed image as it is or manually selecting backlight image correction; In step 50, if it is determined that the backlight image is selected, or when the backlight image correction is manually selected in step 60, the backlight image correction may be performed to correct the backlight image.

As described above, the present invention can be easily corrected in the mobile phone without processing the backlight image obtained by the mobile phone camera on the PC, and it is possible to determine whether the image was taken with backlight at the same time as the picture is taken and the user directly It provides automatic processing that can be processed without judgment, and has an effect of speeding up image correction processing by minimizing performance in the image processing process of the system.

In addition, the present invention can improve the contrast by providing an improved stretching method based on the existing stretching method, there is no need to add the memory of the mobile phone does not add additional cost, the way to handle in the mobile phone No additional image correction program or tool is required, and the user can choose whether to correct automatically at the moment of shooting, so it is adaptive and more effective in terms of function.

1 is a schematic diagram of a mobile phone-based backlight image quality improvement according to the present invention.
2 is a flowchart of an image processing method for improving a backlight image quality based on a mobile phone according to the present invention;
Figure 3 is a flow chart illustrating a process for setting automatic correction in accordance with the present invention.
4 is a flowchart illustrating a backlight image determination process in setting automatic backlight compensation according to the present invention.
5 is a reference picture for determining a backlight image according to the present invention.
6 is a flowchart illustrating a backlight image correction process according to the present invention.
7 is a reference diagram showing a method for finding a valley point according to the present invention.
8 is a reference diagram showing an example of an image corrected by merging the original RGB image and each stretched RGB histogram according to the present invention.

1 is a schematic diagram of improving a backlight image quality based on a mobile phone according to the present invention, FIG. 2 is a flowchart of an image processing method for improving backlight image quality based on a mobile phone according to the present invention, and FIG. 3 is an automatic correction according to the present invention. 4 is a flowchart illustrating a setting process, FIG. 4 is a flowchart illustrating a process of determining a backlight image when setting automatic backlight compensation according to the present invention, FIG. 5 is a reference picture for determining a backlight image according to the present invention, and FIG. FIG. 7 is a reference diagram illustrating a method of finding a valley point according to the present invention, and FIG. 8 is a view corrected by merging an original image and each stretched RGB histogram according to the present invention. See also an example image.

Hereinafter, an image processing method for improving a backlight image quality based on a mobile phone of the present invention will be described with reference to the accompanying drawings.

1 is a schematic diagram of a mobile phone-based backlight image quality improvement of the present invention, in which a user photographs an image using a mobile phone camera and determines an automatic or backlight image and corrects the image.

FIG. 2 is a flowchart illustrating an image processing method for improving a mobile phone-based backlight image quality according to an embodiment of the present invention. The tenth step (S10) of selecting whether to automatically correct a backlight image when an image of the mobile phone is photographed is performed. When the user selects the automatic correction, the corresponding command value is stored and waits until the completion of the automatic correction setting (S20), the thirtieth step (S30) captured and stored by the camera of the mobile phone, and the backlight automatic correction is selected. Step S40 of determining whether or not the automatic backlight compensation is selected, if it is selected, the step 50 of automatically determining whether the photographed image is a backlight image based on contrast, and if the backlight automatic correction is not selected, In step 60, the image is stored as it is or the backlight image correction is manually selected, and whether it is the backlight image is determined in the 50th step S50, or the 60th step S60. In step S70, when the backlight image correction is manually selected in step S70, the backlight image correction is performed to correct the backlight image.

FIG. 3 is a detailed configuration diagram of a 20th step S20 of completing setting and waiting according to the automatic backlight image correction, in which a backlight image is selected as an automatic correction in step 21, and a selected command value is stored. A twenty-second step (S22), a twenty-third step (S23) of allocating a memory of an image size size to process an image captured by the command value, and a twenty-fourth step (S24) of allocating each RGB data size memory; do.

FIG. 4 is a detailed configuration diagram of step 50 (S50) of determining whether a photographed image according to the backlight auto-correction selection is a backlight image, and converting an RGB color image into a gray image when the photographed image is input. S51), a 52 th step (S52) of generating a contrast histogram of the converted gray image, a 53 th step (S53) of calculating an average value according to the distribution of the histogram, and a backlight image based on the set parameter value. In operation S54, the method may include determining whether the image is backlit, and storing the image after correcting the image in operation S55.

FIG. 5 shows a reference picture for determining a backlight image. In operation 54 of determining the backlight image, a parameter value designated by calculating a distribution degree of a dark brightness region (symbol A of FIG. 5) on a histogram of a gray image is illustrated. Step 54-1 (S54-1) for determining whether it is greater than (C in FIG. 5), and if it is larger than the designated parameter value (symbol C in FIG. 5), the distribution diagram of the bright area (symbol B in FIG. 5) on the histogram Step 54-2 to compare with (S54-2), and if the value of the dark brightness area (symbol A in Fig. 5) is larger than step 54-3 to determine the dark backlight image to improve color correction and brightness ( S54-3).

FIG. 6 is a detailed configuration diagram of a seventy step S70 of correcting a backlight image by improving the backlight image contrast, and generating a histogram of each RGB color when an image to be corrected is input; 72 step (S72) of generating a histogram by merging the histograms of each color of RGB and finding a valley point, step 73 (S73) of calculating a distribution point according to the valley point, and stretching application ranges according to the distribution point A seventy-seventh step (S74) of calculating a value, a seventy-seventh step (S75) of calculating a stretch by each RGB application range, and merging the stretched RGB histogram to generate and store a corrected image in a backlight image Step S76 is included.

As shown in FIG. 7, the histogram is composed of peak points and pitted valley points that rise from the darkest 0 position to the brightest 255 position, that is, the valley point means the recessed points.

In the 72th step (S72) of finding the valley point, the histogram of the first figure on the left side of FIG. 7 shows that the increase and decrease change too radically. In addition, if the histogram is changed by calculating the average value by adding the neighboring distributions on both sides of the histogram, the histogram of the smooth curve can be obtained as shown in the second image on the left of FIG. 7 (step S72-1).

Then, by accumulating each brightness value, a cumulative graph of the corresponding histogram is generated as shown in the third image on the left side of FIG. 7 (step S72-2). To calculate the angle of the graph from (step S72-3), as shown in the first picture on the right of FIG. 7, the slope is initially 0 and gradually increases, but the gradually increasing slope is decreased again. This first point is the position that goes down from the peak point to the valley point, that is, the peak point, and on the contrary, the point where the slope gradually decreases and then increases again is the position that goes up from the valley point to the peak point, that is, the valley point. .

If all the points of the increase and decrease of the slope are found, the peak point and the valley point of the histogram can be finally obtained as shown in the second figure on the right side (step S72-4). Therefore, the obtained peak point is removed and the required valley point is found as shown in the right third picture of FIG. 7 (step S72-5).

It can be seen from the right third figure of FIG. 7 that six valley points were finally found (symbols 1 to 6 of the right third figure of FIG. 7).

Step 73 (S73) of calculating distributions for each area based on the six points calculates the brightness distribution from Valley No. 1 to Valley No. 2 in the third image on the right side of FIG. The brightness distribution from point 2 to point 3 is also calculated, and the value calculated in turn up to point 6 is a ratio of how much each region is stretched.

On the basis of the distribution rate from point 1 to point 6, each region is calculated by the percentage of stretching to the total length of the histogram (brightness from 0 to 255) to calculate the stretching coverage according to the distribution ( Step S74), when the% value is obtained, the stretching range may be calculated using the total length 255, and the stretching technique is applied only to this range (step S75). Since the above operation is performed three times since all of the RGB histograms are performed, and when all the RGB histograms are stretched, the three histograms are merged to generate a corrected image from the backlight image (step S76). .

FIG. 8 shows an example of an image corrected by merging the stretched RGB histogram with the original image. The image is dark due to backlight of the original image, which is the first picture on the left of FIG. As can be seen from the histogram, which is the second figure on the left of FIG. 8, it can be seen that the RGB distribution is bitten at a dark position.

As described above, when the partial stretching is obtained, the result value as shown in the first picture on the right of FIG. 8 can be obtained, and the contrast of the building is improved, and the image is generally brightened to obtain the improved contrast image. In the histogram, as shown in the second right side of FIG. 8, it can be seen that the high distribution region is stretched at a wide interval and the small distribution region is stretched at a narrow interval.

Therefore, the present invention improves the contrast of the image obtained by using a mobile phone camera, when the user is taking a picture with the mobile phone due to backlight when the target image is dark and the image quality is lowered automatically determines the quality of the image, If it is determined that it is a backlight image, the image quality can be improved to make the image clearer and brighter.

In addition, the present invention is adaptive because the user can select whether to handle the backlight in advance before shooting with a mobile phone, after the shooting can be improved by contrasting the range of stretching techniques by calculating the range of stretching according to each image RGB color contrast distribution value have.

Although the present invention has been shown and described with respect to specific embodiments thereof, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined by the appended claims. Anyone who can afford it will know.

Claims (6)

An image processing method for improving a backlight image quality based on a mobile phone,
A tenth step (S10) of selecting whether to automatically correct a backlight image when the image of the mobile phone is taken;
A 20th step (S20) of storing a command value corresponding to the backlight image when the backlight image is selected as an automatic correction and waiting for completion of the automatic correction setting;
A thirtieth step (S30) of capturing and storing an image with a mobile phone camera;
A 40th step S40 of determining whether the backlight automatic correction is selected;
If the backlight automatic correction is selected, step 50 (S50) for automatically determining whether the photographed image is a backlight image based on contrast;
If backlight automatic correction is not selected, step 60 (S60) of storing the captured image as it is or manually selecting backlight image correction;
If it is determined in step 50 that the backlight image is determined or if the backlight image correction is manually selected in step 60, step 70 of correcting the backlight image is performed by improving the contrast of the backlight image. Image processing method for improving the backlight image quality based on the mobile phone, characterized in that it comprises a. The method of claim 1, wherein the 20th step (S20)
A twenty-first step S21 in which the backlight image is selected for automatic correction;
A twenty-second step S22 of storing the selected command value;
A twenty-third step (S23) of allocating a memory having an image size to process an image captured by the command value;
And a twenty-fourth step (S24) of allocating each RGB data size memory. The method of claim 1, wherein the 50th step (S50)
A 51 st step of converting an RGB color image into a gray image when the captured image is input;
A 52nd step (S52) of generating a contrast histogram of the converted gray image;
Calculating an average value according to the distribution of the histogram (S53);
A step S54 of determining whether the backlight image is based on the set parameter value;
The image processing method for improving the backlight image quality of the mobile phone, characterized in that it comprises a 55 step (S55) for storing after the image correction in the case of a backlight image. The method of claim 3, wherein the 54th step (S54) is
Step 54-1 (S54-1) of calculating a distribution degree of the dark brightness area on the histogram of the gray image to determine whether the value is greater than a specified parameter value;
Step 54-2 (S54-2) comparing the degree of distribution of bright areas on the histogram if greater than a specified parameter value;
If the value of the dark brightness area is larger, the image processing for improving the backlight image quality of the mobile phone, characterized in that it comprises a step 54-3 (S54-3) to determine the dark backlight image to improve color correction and brightness. Way. The method of claim 1, wherein the seventy step (S70)
A 71 st step (S71) of generating a histogram of each RGB color when an image to be corrected is input;
A 72 th step (S72) of generating a histogram by merging the histograms of respective RGB colors and finding valley points;
A 73 th step (S73) of calculating a distribution degree according to the valley point;
A 74th step (S74) of calculating a stretching application range according to the distribution;
A seventy-fifth step S75 of calculating stretching by each RGB application range;
And a step S76 of merging the stretched RGB histograms to generate and store a corrected image from a backlight image. The method of claim 5, wherein the 72th step (S72)
Step 72-1 (S72-1) of obtaining a smooth curve histogram by changing the histogram by calculating a mean value by adding the neighboring distributions of both histograms;
Step 72-2 (S72-2) of accumulating respective brightness values to generate a cumulative graph of the histogram;
A 72-3 step (S72-3) of calculating the angle of the graph from the back when the cumulative graph is generated;
Step 72-4 (S72-4) of finally finding peak and valley points of the histogram after finding a point where the slope increases and decreases;
The obtained peak point is removed and the image processing method for improving the backlight image quality of the mobile phone based on the step 72-5 (S72-5) to find the required valley point.

Images