KR101448537B1 - Apparatus and method for braketing capture based on face detection in digital image processing device - Google Patents

Abstract

The present invention relates to a digital image processing apparatus and method, and more particularly, to a bracketing photographing apparatus and method based on face recognition in a digital image processor for performing exposure bracketing photographing by estimating exposure of a live image recognized as a face will be. In the digital image processor, the bracketing device based on face recognition is a digital image processor. When a plurality of people are searched for face recognition result of live view image, the exposure is compared with the average luminance value of the detected multiple faces, And digital signal processing means for performing digital signal processing.

Face Recognition, Average Luminance Value, Exposure Adjustment, Exposure Bracketing

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to an apparatus and a method for bracket capturing based on face recognition in a digital image processor,

The present invention relates to a digital image processing apparatus and method, and more particularly, to a bracketing photographing apparatus and method based on face recognition in a digital image processor for performing exposure bracketing photographing by estimating exposure of a live image recognized as a face will be.

Currently, the digital image processing apparatus is equipped with a face recognition algorithm as a basic feature. And the automatic exposure and the automatic exposure are performed by using this technique. In the case of automatic exposure, the exposure value is determined based on the exposure evaluation data. Since the exposure evaluation value is generally based on the brightness of the ideal gray state, if the exposure evaluation data is different from the reference data on which the algorithm is designed There is a disadvantage in that there is an error.

For example, if an algorithm is created with a person with a common skin color in the Asian world, if the face is evaluated as an exposed person, then the under-exposure phenomenon occurs. If the face is evaluated based on the black person, I can not help but notice the phenomenon. However, since it is difficult for a digital camera to determine which color of a person who is a subject at the time of photographing has the skin, it is difficult to avoid the above phenomenon when the conventional algorithm is used.

Referring to FIG. 5, after the face detection and the exposure evaluation data are acquired with respect to the detected face, an average is taken on the basis of the luminance data, and compared with the Natural Gray, then -Ev when the general exposure evaluation value data is large, When the evaluation data is small, + Ev is applied, and the degree is determined according to the difference in brightness is the conventional face recognition based exposure system.

Because conventional digital image processing device makers are based on Japan, many algorithms have been made based on a person with a skin color of Asian skin color. This is because the skin color reflectance of Oriental people is close to Natural Gray. However, it is important to catch the reference point because the subject of the digital image processing apparatus can be not only Asian but also white and black skin color person. Furthermore, when two or more subjects are photographed, it is disadvantageous that the exposure fails if the color of the face differs significantly (for example, black and white), or both. Also, if the person is in the sunny and shaded areas at the time of shooting a large number of people, then this also has a disadvantage that the exposure fails because of the difference in exposure.

The technical problem to be solved by the present invention is to measure the exposure of the face after recognizing the face among the persons at the time of photographing multiple persons and to perform bracketing photography based on the average exposure value The present invention also provides an apparatus and method for photographing a face based on face recognition in a digital image processor capable of reducing an exposure failure by acquiring an image having an exposure value.

According to an aspect of the present invention, there is provided a digital image processor for processing a face image based on face recognition in a digital image processor. In the digital image processor, when a plurality of persons are searched for face recognition results of a live view image, And digital signal processing means for calculating an exposure to the average luminance value to perform exposure bracketing photographing.

In the present invention, the digital signal processing means may include a face recognition unit for performing face recognition on the live view image; A luminance detector for calculating an average luminance value of the multiple faces retrieved as the face recognition result and calculating a difference value? L for a face having the maximum luminance value among the retrieved faces and a face having the minimum luminance value; An exposure adjustment unit for calculating an exposure to the average luminance value and adjusting an exposure calculated by the difference value? L; And a control unit for controlling the bracketing shooting based on the exposure estimation value and the exposure adjustment value.

In the present invention, the exposure adjustment unit may adjust the exposure estimated by the difference value (? L) / 2 and the difference value (? L) / 2.

According to an aspect of the present invention, there is provided a method of operating a digital image processor, the method comprising: (a) performing face recognition of a live view image; (b) calculating an exposure for an average luminance value of the searched multiple persons when multiple faces are searched as a result of performing the face recognition; And (c) performing bracketing photographing by adjusting the calculated exposure value.

In the present invention, the step (c) includes: (c-1) photographing the live view image based on the calculated exposure value; (c-2) calculating a difference value? L for a face having the maximum luminance value among the searched faces and a face having the minimum luminance value; And (c-3) photographing the live view image by adjusting an exposure estimated by the difference value? L.

In the present invention, in step (c-3), the exposure calculated by the difference value (? L) / 2 and the difference value? L / 2 is adjusted to photograph the live view image.

As described above, according to the present invention, when multiple persons are photographed, a face is recognized after a face is recognized and a face exposure is measured. When an exposure difference of a certain level or more occurs, bracketing is performed based on an average exposure value of the persons, The effect of reducing the exposure failure due to the difference in the reflectance of the face is generated.

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

BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 is a perspective view showing the front and top contours of a digital image processor.

The shutter-release button 11 is opened and closed to expose the CCD or film to light for a predetermined time, and the image is recorded on the CCD by appropriately exposing the subject in cooperation with the aperture (not shown).

The shutter-release button 11 generates the first and second image pickup signals by the photographer input. When the first shutter-release button 11 is input as a half-shutter signal, the digital image processor focuses and adjusts the amount of light. At this time, the display unit 25 lights green. When the focus of the first shutter-release button 11 is focused and the amount of light is adjusted, a second shutter-release button 11 as a full shutter signal is input to capture an image.

The power button 13 is input for supplying power to the digital image processor and operating it.

The flash 15 illuminates bright light momentarily when shooting in a dark place. The flash mode includes auto flash, forced flash, no flash, red-eye reduction, and slow synchro flash.

The auxiliary light 17 supplies light to the subject so that the digital image processor automatically catches the focus quickly and accurately at the time of lack of light or at night.

The lens unit 19 receives light from an external light source and processes the image.

FIG. 2 is a rear view showing the rear external appearance of the digital image processor shown in FIG. 1. The wide-angle zoom button 21w, the telephoto-zoom button 21t, the display unit 23, Input buttons B1 to B14 (hereinafter referred to as buttons B1 to B14).

The wide-angle zoom button 21w or the telephoto-zoom button 21t widens the view angle or narrows the view angle depending on the input, in particular, when the size of the selected exposure area is to be changed. When the wide angle-zoom button 21w is input, the size of the selected exposure area is reduced, and when the telephoto-zoom button 21t is input, the size of the selected exposure area is increased.

The buttons B1 to B14 are provided in the rows and columns of the display unit 23. The buttons B1 to B14 provided in the row and column of the display unit 23 are provided with a touch sensor (not shown) or a contact type switch (not shown).

That is, the touch sensors are provided on the buttons B1 to B14 to move up / down / left / right while touching the buttons B1 to B7 of the horizontal row or the buttons B8 to B14 of the vertical row, It is possible to select any value (e.g., color or brightness) of the items, or activate a submenu icon included in the main menu icon.

In addition, the buttons B1 to B14 are provided with a contact type switch, so that the main menu icon and the sub menu icon can be directly selected to execute the corresponding function. The touch sensor requires a relatively weak touch compared to the contact switch input, but the contact switch input requires a relatively strong touch compared to the touch sensor input.

FIG. 3 is a block diagram showing a configuration of a bracketing photographing apparatus based on face recognition in the digital image processor according to the present invention, which includes a display unit 23, a user input unit 31, an image pickup unit 33, ), A storage unit 37, and a digital signal processing unit 39.

The user input unit 31 includes a shutter-release button 11 that is opened and closed to expose a CCD or a film to light for a predetermined period of time, a power button 13 that inputs power to supply power, A wide angle-zoom button 21w and a telephoto-zoom button 21t for narrowing the angle of view and a touch sensor or a contact-type switch provided in the horizontal and vertical columns around the display unit 23 for character input or menu selection and execution, And buttons B1 to B14 provided with buttons.

The imaging section 33 includes a shutter, a lens section, a diaphragm, and a charge coupled device (CCD) and an ADC (not shown). The shutter is a mechanism that adjusts the amount of light that is exposed with the iris. The lens unit receives light from an external light source and processes the image. At this time, the diaphragm adjusts the amount (light amount) of the incident light according to the degree of opening and closing. The opening / closing degree of the diaphragm is controlled by the digital signal processing section 39. [

The CCD accumulates the amount of light input through the lens unit and outputs the image captured by the lens unit according to the accumulated light amount in accordance with the vertical synchronization signal. Image acquisition by a digital image processor is performed by a CCD which converts the light reflected from the subject into an electrical signal. In order to obtain a color image using a CCD, a color filter is required. Mostly, a filter (not shown) called a CFA (color filter array) is employed. CFA has a regularly arranged structure that passes only light that represents one color per pixel, and it has various forms according to the arrangement structure. The ADC converts the analog video signal output from the CCD into a digital signal.

The image processing unit 35 processes the digitally converted RAW data so that it can be displayed. The image processing unit 35 removes a black level due to the dark current generated in the CCD and the CFA filter which are full of temperature change. The image processing unit 35 performs gamma correction to encode information in accordance with the nonlinearity of human vision. The image processing unit 35 performs CFA interpolation for interpolating a Bayer pattern implemented with RGA and RGB lines of gamma-corrected predetermined data into RGB lines. The image processing unit 35 converts the interpolated RGB signals into YUV signals, performs edge compensation for filtering the Y signals by a high-pass filter, and calculates color values of the U and V signals using a standard color coordinate system Corrects the color correction, and removes these noises. The image processing unit 35 compresses and processes the Y, U, and V signals from which the noise has been removed to generate a JPEG file, and the generated JPEG file is displayed on the display unit 23 and stored in the storage unit 37 . All the operations of the image processing unit 35 operate under the control of the digital signal processing unit 39. [

When a plurality of persons are searched for as a result of face recognition of the live view image, the digital signal processing unit 39 calculates the exposure for the average luminance value of the plurality of searched persons to perform exposure bracketing photography.

To this end, the digital signal processing unit 39 includes a face recognizing unit 39-1, a brightness calculating unit 39-2, an exposure adjusting unit 39-3, and a controlling unit 39-4.

The face recognition unit 39-1 detects at least one face information, that is, the face size, position and direction, from an arbitrary live view image under the control of the control unit 39-4. The facial recognition unit 39-1 can detect the face area based on the color or detect the face area based on the edge at the time of detecting the size of the face, and at the time of detecting the face position, And the center of the display unit 23, and the face direction can be detected in the form of a triangle composed of the eyes and mouth from the extracted face at the time of detecting the direction of the face. Since details of the face information detection by the face recognition unit 39-1 are well known in the art, a detailed description thereof will be omitted.

The brightness calculating unit 39-2 calculates an average brightness value of the multiple faces retrieved based on the face recognition result of the face recognizing unit 39-1. For example, when two face detection result faces of the face recognition unit 39-1 are detected, the average luminance value of the first face is calculated, the average luminance value of the second face is calculated, And calculates an average luminance value of the second face.

The luminance calculator 39-2 calculates the difference value between the face having the maximum luminance value and the face having the minimum luminance value among the multiple faces searched for by the face recognition unit 39-1 as DELTA L do.

The exposure adjusting unit 39-3 calculates the exposure adjustment value EV for the average brightness value of the recognized faces calculated by the brightness calculating unit 39-2.

Further, the exposure adjusting section 39-3 adjusts the exposure value calculated by the difference value? L calculated by the brightness calculating section 39-2. At this time, the exposure adjustment unit 39-3 adjusts the exposure calculated by the difference value? L / 2 and the difference value? L / 2.

The control unit 39-4 controls the bracketing shooting with the exposure estimation value EV and the exposure adjustment value (-ΔL / 2 * EV, + ΔL / 2 * EV). The control unit 39-4 receives the face recognition result of the face recognition unit 39-1, and performs control so that normal shooting is performed when the recognized face is one. However, when the number of recognized faces is two or more, the exposure estimation value EV and the exposure adjustment values (-ΔL / 2 * EV, + ΔL / 2 * EV) are received from the exposure adjustment unit 39-4 Perform exposure bracketing shooting.

Here, exposure bracketing is performed by adjusting the shutter speed, aperture value, and ISO based on the current exposure value, adjusting the exposure map, and performing additional shooting with + EV and -EV values in the current exposure map, , The probability of acquiring an image having an optimal exposure value is increased.

For example, if the current exposure value is ISO 100, shutter speed is 1/60 sec, ISO 100 with -1EV, shutter speed 1/125 sec at F4, shutter at F4 at ISO 100 with + 1EV value Speed is 1/30 second, three images having 0 EV, -1 EV, and +1 EV are photographed with respect to the current exposure indication value.

Hereinafter, a method for photographing a bracketing based on face recognition in a digital image processor according to the present invention will be described in detail with reference to FIG. The bracketing method based on face recognition in the digital image processor according to the present invention can be performed in the digital image processor as shown in FIG. 3. According to the embodiment, May be performed in the digital signal processing unit 39 with the help of the components.

If the digital image processor is set to the face recognition based exposure bracketing mode (step 401), the digital signal processor 39 displays the live view image on the display unit 23 (step 403).

When the first shutter-release button 11 input is received from the user (step 405), the digital signal processing unit 39 performs AF based on face recognition (step 407). The digital signal processing unit 39 detects at least one face information, that is, the size, position, and direction of a face from the live view image, and performs AF based on the detected size, position, and direction. The details of the face detection are described above and will be omitted here.

When the second shutter release button 11 is input from the user, the digital signal processing unit 39 determines whether there are two or more recognized faces (step 411).

If the recognized face is a single person, the digital signal processing unit 39 controls the automatic exposure adjustment based on the face of the person 1 to perform a normal photographing operation in step 413.

However, if there are two or more recognized faces, the digital signal processor 39 calculates the average brightness value of the recognized faces (step 415). For example, when two faces are detected, the average luminance value of the first face is calculated, the average luminance value of the second face is calculated, and then the average luminance value of the first and second faces is calculated.

The digital signal processing unit 39 calculates the exposure evaluation value EV based on the calculated average luminance value and performs automatic exposure photographing (step 417).

Then, the digital signal processor 39 calculates a difference value between the face having the maximum luminance value and the face having the minimum luminance value among the multiple faces detected as DELTA L (step 419).

When the difference value DELTA L is calculated, the digital signal processing section 39 adjusts the exposure with -ΔL / 2 * EV and shoots it (step 421).

Thereafter, the digital signal processing unit 39 adjusts the exposure with + DELTA L / 2 * EV and takes an image (step 423).

Here, exposure bracketing is performed by adjusting the shutter speed, aperture value, and ISO based on the current exposure value, adjusting the exposure map, and performing additional shooting with + EV and -EV values in the current exposure map, , The probability of acquiring an image having an optimal exposure value is increased.

For example, if the current exposure value is ISO 100, shutter speed is 1/60 sec, ISO 100 with -1EV, shutter speed 1/125 sec at F4, shutter at F4 at ISO 100 with + 1EV value Speed is 1/30 second, three images having 0 EV, -1 EV, and +1 EV are photographed with respect to the current exposure indication value.

The digital signal processing unit 39 stores the photographed exposure bracketing images in the storage unit 37 (step 425).

By performing exposure bracketing at the time of shooting multiple persons, it is possible to acquire an image having an optimal exposure value, thereby reducing the exposure failure due to the difference in the reflectance of the face.

In another embodiment, it can also be used for AWB (auto white balance) performance. For example, if a person is under different lighting conditions, for example, a person under the sunlight and a person under the sun in daytime sunlight conditions will experience a difference in color temperature, so that if one criterion is met, An error in color may occur. In this case as well, the same method as in the present invention can be performed to reduce the error. In this case, it is possible to perform AWB bracketing photographing based on ΔK (maximum color temperature-minimum color temperature) instead of ΔL.

In the case of AWB bracketing, since AWB is applied after image capture, a plurality of images can be acquired by performing WB algorithm with one piece of RAW data without performing additional photography.

In another embodiment of the present invention, a digital image processing apparatus capable of composing an image may perform a bracketing photographing operation and then synthesize a face portion of the bracketing image on a face portion where an exposure difference occurs, Can be made. If the time difference of the bracketed images is small, there is almost no difference in the images, so the image synthesis can be performed more easily. Since the image synthesis algorithm is a well known technique, detailed description thereof will be omitted.

BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 is a perspective view showing the front and top contours of a digital image processor.

FIG. 2 is a rear view showing the rear external shape of the digital image processor shown in FIG. 1; FIG.

3 is a block diagram showing a configuration of a bracketing photographing apparatus based on face recognition in a digital image processor according to the present invention.

4 is a flowchart illustrating an operation of a bracketing shooting method based on face recognition in a digital image processor according to the present invention.

5 is a view for explaining exposure adjustment based on face recognition according to the related art.

Claims (6)

As a digital image processor, And a digital signal processing means for performing an exposure bracketing photographing by calculating an exposure for an average luminance value of the searched multiple faces when a plurality of persons are searched for the face recognition result of the live view image, . The digital signal processing apparatus according to claim 1, wherein the digital signal processing means A face recognition unit for performing face recognition on the live view image; A luminance detector for calculating an average luminance value of the multiple faces retrieved as the face recognition result and calculating a difference value? L for a face having the maximum luminance value among the retrieved faces and a face having the minimum luminance value; An exposure adjustment unit for calculating an exposure to the average luminance value and adjusting an exposure calculated by the difference value? L; And And a control unit for controlling the bracketing shooting based on the calculated exposure value and the exposure adjustment value. 3. The apparatus of claim 2, wherein the exposure adjustment unit - the exposure calculated by the difference value (? L) / 2 and the difference value (? L) / 2 is adjusted. As an operation method of a digital image processor, (a) performing face recognition of a live view image; (b) calculating an exposure for an average luminance value of the searched multiple persons when multiple faces are searched as a result of performing the face recognition; And and (c) performing bracketing photographing by adjusting an estimated value of the exposure. 5. The method of claim 4, wherein step (c) (c-1) photographing the live view image based on the estimated value of the exposure; (c-2) calculating a difference value? L for a face having the maximum luminance value among the searched faces and a face having the minimum luminance value; And (c-3) photographing the live view image by adjusting exposure estimated by the difference value? L. 6. The method of claim 5, wherein in step (c-3) And adjusting the exposure calculated by the difference value (? L) / 2 and the difference value (? L) / 2 so that the live view image is photographed.

Images