KR20110008587A - Method for taking a photograph of face - Google Patents

Abstract

PURPOSE: An individual photographing method for revising the distortion of video data created due to backlight is provided to compensate an individual area and an individual peripheral area in a pixel generating the backlight. CONSTITUTION: Pixels which are lower than a second standard brightness range pixel are detected(S207). If an iris region is detected by using the adjacent brightness difference included in the medium luminance domain, a plurality of edges is detected(S209). In the luminance domain among a plurality of edges, the individual domain is detected near the boundary line(S210). The brightness of the pixel is set up as a predetermined level(S211).

Description

How to photograph a person {Method for taking a photograph of face}

The present invention relates to a person photographing method for photographing a person using a camera module.

The camera's Auto Exposure or Auto Iris is a function to optimize the light entering the CCD (Charge-coupled devices).

That is, the exposure of the camera is controlled by setting an optimum aperture value according to the amount of incident light.

Such automatic exposure control is a phenomenon in which a strong light incident above the amount of saturation light enters a signal charge, and excess charge is mixed in the surrounding pixels, thereby brightening the part where the light is not illuminated. Phenomena of Bright Stripes in a Vertical Direction by the Vertical Direction It also provides a function of removing or preventing a smear, such as a smear caused by incomplete shading of a CCD vertical transfer unit.

However, in order to capture dark subjects in the dark state and bright subjects in the bright state, the dynamic range of the CCD must be wide enough, but the saturation output of the high resolution (more than 3 million pixels) CCD It is limited to 200mV ~ 500mV, and the SN ratio (signal-to-noise ratio) cannot be increased, so it is not able to cope with the above blooming and smear completely.

In particular, when the subject's face is not darkened in the backlight, and the image is taken clearly while looking directly at the light, the noise may appear even when the car can be photographed even when the headlight comes in at night.

In order to prevent the noise phenomenon as described above, the conventional technique uses a screen averaging method and a screen division averaging method in which specific screen weights are assigned.

The screen averaging method is a technique for controlling the iris by comparing the average value of luminance levels of the whole screen or a part of the screen, and the screen split averaging method is used to control the iris in the photographing screen by using brightness information obtained for each area by dividing the video signal into a plurality of screens. Refers to a technique for detecting and automatically correcting a distribution.

However, the above method is also not an effective solution to the noise (Smear, Blooming), in particular, when applied to a mobile device camera, such as a mobile phone or notebook computer iris due to the spatial constraints of the camera module However, it is very difficult to apply ND (Neutral Density) filter.

In particular, when the image data is distorted, such as a backlight image, it is necessary to correct the image data to improve the image quality of the image.

The present invention provides a person photographing method for correcting a person area of an image in which backlight is generated.

According to an aspect of the present invention, the method may include: dividing an input image into a plurality of window regions, calculating a total luminance average value of the plurality of window regions, and calculating a luminance average value of each of the plurality of window regions. Counting the number of high luminance regions that are window regions that are equal to or greater than the overall luminance average value among the luminance average values for each window region, and when the number of the high luminance regions is equal to or greater than a reference number, the window region included in the set first reference luminance range. Detecting as an intermediate luminance region, detecting pixels included in a reference saturation range of saturation among the plurality of pixels included in the intermediate luminance region as a face region, and generating a set luminance among the luminance of the pixels included in the face region. Pixels below the upper limit of the 2 reference luminance range are detected as the iris region In the step of detecting the iris region in the intermediate luminance region, detecting a plurality of edges by using the luminance difference between two adjacent pixels included in the intermediate luminance region, the edge of the intermediate luminance region of the plurality of edges A method for capturing a person is provided that includes detecting a person area having an edge closest to the boundary and increasing the luminance of a pixel included in the person area by a predetermined level.

In an embodiment of the present invention, by correcting a person area and a person surrounding area separately in a backlit image, it is possible to correct distortion of the image data caused by the backlight, and the boundary between the person area and the person surrounding area becomes clearer. Can improve the picture quality.

As the inventive concept allows for various changes and numerous embodiments, particular embodiments will be illustrated in the drawings and described in detail in the written description. However, this is not intended to limit the present invention to specific embodiments, it should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention.

Terms including ordinal numbers such as first and second may be used to describe various components, but the components are not limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

For example, without departing from the scope of the present invention, the second component may be referred to as the first component, and similarly, the first component may also be referred to as the second component.

When a component is referred to as being "connected" or "connected" to another component, it may be directly connected to or connected to that other component, but it may be understood that other components may be present in between. Should be. On the other hand, when a component is said to be "directly connected" or "directly connected" to another component, it should be understood that there is no other component in between.

The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting of the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present application, the terms "comprises", "having", and the like are used to specify that a feature, a number, a step, an operation, an element, a component, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Now, a person photographing method according to an exemplary embodiment of the present invention will be described in detail with reference to the drawings. The same or corresponding elements are denoted by the same reference numerals regardless of the reference numerals, and redundant description thereof will be omitted.

1 is a flowchart illustrating a person photographing method according to an exemplary embodiment of the present invention.

FIG. 1 relates to an operation of a processor for processing an image input from a means capable of acquiring an image. The configuration of an apparatus including a processor is not illustrated, and the method illustrated in FIG. 1 is a processor for processing an image. Applicable to all devices including the. In particular, the present invention can be applied to a camera module embedded in a mobile communication terminal.

As shown in FIG. 1, the present invention includes the step of inputting the acquired image (S100), and determining whether or not the backlight image is generated in the input image (S200). If it is determined that the image is a backlight image, detecting and correcting a region of the person and a non-person region of the image (S300); and if it is determined that the image is not a backlight image, outputting the image to the display unit (not shown) without correction (S400). Include.

2 is a flowchart illustrating a backlight image determination step (S100) according to an exemplary embodiment of the present invention, and FIG. 3 is a diagram illustrating a method of dividing an image according to an exemplary embodiment.

As shown in Figs. 2 and 3, first, the acquired image is divided into a plurality of window regions W1 to Wn (S101). In the present invention, for convenience of description, the image data is divided into 16 window regions and described. One window area includes a plurality of pixels.

Converting R, G, and B data of an image into luminance signals Y and chroma signals Cb and Cr (S102), calculating an average value of overall luminances Yo of the entire image (S103), and dividing the plurality of window regions (W1 to Wn) The respective luminance average values Y1 to Yn are calculated (S104).

The luminance average values Y1 to Yn for each of the plurality of window regions are compared with the total luminance average values Yo (S105), and among the plurality of luminance average values Y1 to Yn for each of the window regions, a window region having a total luminance average value (Yo) or more is high. The area is detected as an area (S106), and a window area less than the overall average value Yo is detected as the low luminance area among the plurality of brightness average values Y1 to Yn for each window area (S107).

The number of high luminance regions is counted (S108), and the number of high luminance regions is compared with the set reference number (S109).

If the number of the high luminance areas is equal to or greater than the reference number, it is determined that the backlight is generated in the image (S110), and the detecting of the person area is performed (S200).

However, if the number of high luminance areas is less than the reference number, it is determined that no backlight is generated in the image (S111) and the image is output to the display unit (not shown) (S112).

4 is a flowchart illustrating an operation S200 of detecting a person area according to an exemplary embodiment.

When the number of the high luminance areas is equal to or greater than the reference number (shown in FIG. 2, the backlight image), the luminance average values Y1 to Yn of the plurality of window regions are compared with the set first reference luminance range (S201). A window region in which Y1 to Yn) is included in the first reference luminance range is detected as an intermediate luminance region (S202).

Then, the saturation of the plurality of pixels included in the intermediate luminance region is compared with the set reference saturation range (S203), and the pixels included in the reference saturation range are detected as the face region (S204). If there is no pixel included in the reference saturation range, it is determined that the saturation is not a portrait and outputs an image to the display unit (S205).

In this case, the reference saturation range is a saturation range indicating the flesh color, and a saturation signal Cb is within a range of 69 to 114 and a saturation signal Cr is within a range of 119 to 177.

Next, the luminance of the pixels included in the face area is compared with the set second reference luminance range (S206), and pixels less than an upper limit of the second reference luminance range are detected as the iris region (S207). In this case, when there is no pixel less than the upper limit value of the second reference luminance range, it is determined that the image is not a portrait and outputs an image to the display unit (S208).

The second reference luminance range is a luminance range indicating black and is a value included in a range in which the luminance signal Y is less than ten.

More specifically, the detecting of the iris region may be performed by modeling a luminance histogram of pixels included in the face region as a mixed model of N rectification distribution functions, and extracting pixels having a luminance less than an upper limit of the second reference luminance range among the mixed models. Detect with iris area.

If a face region is detected and an iris region of the face region is detected, this means that a person is included in the image.

Therefore, a plurality of edges are detected using the luminance difference between two adjacent pixels included in the intermediate luminance area (S209), and a person area whose boundary is the edge closest to the edge of the intermediate luminance area among the detected plurality of edges is detected. (S210).

In this case, the plurality of edges may be detected using a haar wavelet transform technique.

Finally, the luminance of the pixels included in the person area is increased by the set luminance level (S211), and the luminance of the pixels included in the area except the person area among the intermediate luminance areas is lowered by the set luminance level (S212).

In this case, the luminance level for increasing the luminance of the pixel and the luminance level for lowering the luminance of the pixel are values that are corrected so that the boundary between the human area and the non-human area is clear and can be arbitrarily adjusted by the user.

Then, the backlight generated in the human area can be corrected. In addition, by correcting the area of the person and the area around the person separately in the backlit image, the distortion of the image data caused by the backlight can be corrected, and the boundary between the area of the person and the area around the person becomes clearer, thereby improving image quality. can do.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements of those skilled in the art using the basic concepts of the present invention defined in the following claims are also provided. It belongs to the scope of rights.

1 is a flowchart illustrating a person photographing method according to an exemplary embodiment of the present invention.

2 is a flowchart illustrating a backlight image determination step according to an embodiment of the present invention.

3 is a diagram illustrating a method of segmenting an image, according to an exemplary embodiment.

4 is a flowchart illustrating an operation of detecting a person area according to an exemplary embodiment of the present invention.

Claims (7)

Dividing an input image into a plurality of window regions; Calculating total luminance average values of the plurality of window regions, and calculating luminance average values of the plurality of window regions; Counting the number of the high luminance regions which are window regions which are equal to or greater than the overall luminance average value among the luminance average values of the plurality of window regions; If the number of the high luminance regions is equal to or greater than a reference number, detecting the window region included in the first reference luminance range in which the luminance average value is set as an intermediate luminance region, Detecting pixels included in a reference saturation range from which a saturation is set among the plurality of pixels included in the intermediate luminance area as a face area; Detecting pixels less than an upper limit of a set second reference luminance range among luminance of pixels included in the face region as an iris region;  When the iris region is detected in the intermediate luminance region, detecting a plurality of edges by using a luminance difference between two adjacent pixels included in the intermediate luminance region, Detecting a person area having an edge closest to an edge of the intermediate luminance area among the plurality of edges, and  And setting the luminance of the pixels included in the human area to be increased by a predetermined level. The method of claim 1, And setting the luminance of the pixels excluding the human area among the intermediate luminance areas by lowering the luminance by a predetermined level. The method of claim 1, The detecting of the edges may include detecting an edge using a haar wavelet transform technique. The method of claim 1, The detecting of the iris region may include modeling luminance histograms of pixels included in the face region as a mixed model of N normal distribution functions, extracting pixels having luminance less than a lower limit of the second reference luminance range among the mixed models. The person photographing method for detecting the iris area. The method of claim 1, Converting the R, G, and B data of the image into a luminance signal Y and a chroma signal Cb and Cr; And the first reference luminance range is within a range of 140 to 180 of the luminance signal (Y). The method of claim 5, The reference saturation range is within the range of 69 ~ 114 of the saturation signal (Cb) and within the range of 119 ~ 177 of the saturation signal (Cr). The method of claim 5, And the second reference luminance range is less than 10 of the luminance signal (Y).

Images