KR20090035851A - Apparatus and method for slideshow play still image sampled from moving picture in digital image processing device - Google Patents

Abstract

A slide show reproducer and a method of static images extracted from a digital image processor from a moving picture are provided to search a character from a video by using a face verification technology and extract static image. An image processing part(35) processes RAW data converted in a digital format. The image processing part removes a black level by dark current generated in CCD(Charge Coupled Device) and CFA(Color Filter Array). The image process part performs gamma correction fit for encoding information. The video color deflection performs the gamma correction fit to the non-linearity of the human the sense of sight and encodes the information. A digital signal processor(39) controls the bundle-branch block. The digital signal processor reproduces as the slide show.

Description

Apparatus and method for slideshow play still image sampled from moving picture in digital image processing device}

The present invention relates to a digital image processor and a method of operating the same, and more particularly, to search for a character from an arbitrary video using face recognition technology, extract only a scene in which a specific character appears as a still image slide The present invention relates to an apparatus and a method for reproducing a slideshow of a still image extracted from a moving image in a digital image processor that reproduces a show.

With the development and rapid spread of digital image processor, many people own digital image processor and live in an environment where they can easily acquire digital image anytime and anywhere.

In particular, in recent years, the development of user created contents (UCC) is almost revolutionary, and video is quite widespread as a digital image such as a music video or a movie.

Users using these digital image processors not only capture still images, but also record a lot of videos with different concepts (storys) .These videos are meaningful in their own right, but users who enjoy various fun and decorating are gradually spreading. It is becoming.

Conventionally, there is a method of obtaining a still image by setting a video at a predetermined time interval, and there is a problem in that a still image for each specific character cannot be obtained and applied to a slide show.

Accordingly, the present invention reflects the needs of users who want to edit and express digital images in various ways as described above.

The technical problem to be achieved by the present invention is to search for a character from an arbitrary video using a face recognition technology, extract only a scene in which a specific character appeared as a still image and play the video in a digital video processor Disclosed is a slideshow reproduction apparatus and method for a still image extracted from the same.

The slide show playback apparatus of a still image extracted from a video in a digital image processor for solving the technical problem to be achieved by the present invention is a digital image processor, extracts and displays character information from an arbitrary video, and from the video It is preferable to include a digital signal processing means for extracting a still image for the characters to reproduce the slide show.

In the present invention, the video is an entire section or a selected section.

In the present invention, the specific character is characterized in that at least one or more.

In the present invention, the digital signal processing means includes a face recognition unit for searching for a character through the face recognition for the video; A person information extracting unit which extracts an appearance section and an appearance time of the found character; A still image extraction unit which extracts a still image of a specific character selected from the video; And a controller configured to control face recognition control, person information, and still image extraction for the video, and to control storage and playback of the extracted still image.

In the present invention, it characterized in that it further comprises a shake determination unit for determining the shake of the still image of the extracted specific character.

In the present disclosure, the control unit may set a still image extraction interval of the selected specific character, and the still image extracting unit may extract a still image of the specific character from the video at the set extraction interval.

The slideshow reproduction method of a still image extracted from a video in a digital image processor for solving the technical problem to be achieved by the present invention is an operation method of the digital image processor, (a) extracts the character information from any video and display Doing; And (b) extracting a still image of a specific character from the video and playing the same in a slide show.

In the present invention, step (a) comprises the steps of (a-1) searching for a character from the video through face recognition; (a-2) calculating a time when the searched character appears in the video; And (a-3) displaying the searched character and the appearance time calculated for the same.

In the present invention, step (b) comprises the steps of: (b-1) selecting a specific character as the displayed character; (b-2) setting a still image extraction interval of the selected specific character; (b-3) extracting and storing a still image of the specific character from the video at the set extraction interval; And (b-4) playing the still image of the stored specific character as a slide show.

In the present invention, in the step (b), it is possible to determine the shake of the still image of the extracted specific person can be excluded from the still image.

According to the present invention, using a face recognition technology to search for a character from any video, extract only the scene in which a specific character appeared as a still image, create and play a slide show with various effects to play another fun You can enjoy

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

1 is a perspective view showing the front and top appearance 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 records the image on the CCD by properly exposing the subject in conjunction with an aperture (not shown).

The shutter release button 11 generates the first and second image capturing signals by a photographer input. When the first shutter release button 11 as a half shutter signal is input, the digital image processing apparatus focuses and adjusts the amount of light, and when the focus is achieved, the green light is turned on in the display unit 25. . When focus is achieved by the input of the first shutter release button 11 and the amount of light is adjusted, the second shutter release button 11 as a full shutter signal is input to capture an image.

The power button 13 is input to supply power to and operate the digital image processing apparatus.

The flash 15 brightens the bright light instantly when shooting in a dark place. Flash modes include auto flash, forced flash, flash off, red-eye reduction, and slow synchro.

The auxiliary light 17 supplies light to the subject so that the digital image processing apparatus automatically focuses quickly and accurately when the amount of light is insufficient or at night.

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

FIG. 2 is a rear view illustrating a rear shape of the digital image processor illustrated in FIG. 1, and includes a wide-angle zoom button 21w, a telephoto-zoom button 21t, a display unit 23, and a touch sensor or a contact switch. Input buttons B1 to B14 (hereinafter referred to as buttons B1 to B14).

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

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

That is, the buttons B1 to B14 are provided with a touch sensor to move up / down / left / right in a state where the buttons B1 to B7 in the horizontal row or the buttons B8 to B14 in the vertical row are touched. You can select any value (eg, color or brightness) from the items, or activate the submenu icons included in the main menu icon.

In addition, the button frame (B1 ~ B14) is provided with a contact switch, it is possible to directly select the main menu icon and sub-menu icon to execute the corresponding function. The touch sensor requires only a weak touch relative to the contact switch input, but the contact switch input requires a relatively strong touch compared to the touch sensor input.

3 is a block diagram showing the configuration of a slideshow playback apparatus for a still image extracted from a video by a digital image processor, including a display unit 23, a user input unit 31, an imaging unit 33, an image processing unit 35, And a storage unit 37 and a digital signal processing unit 39.

The user input unit 31 has a shutter release button 11 that opens and closes to expose the CCD or film to light for a predetermined time, a power button 13 that inputs to supply power, and widens the angle of view according to the input, Wide-zoom button 21w and tele-zoom button 21t for narrowing the distance, and touch sensors or contact switches provided in horizontal and vertical columns around the display unit 23 for character input or menu selection and execution. There are buttons provided with a button frame (B1 ~ B14).

The imaging unit 33 includes a shutter, a lens unit, an aperture, a charge coupled device (CCD), and an ADC, which are not shown in the figure. The shutter is a mechanism for adjusting the amount of light exposed together with the aperture. The lens unit receives light from an external light source and processes an image. At this time, the iris adjusts the amount of light incident (light quantity) according to the degree of opening and closing. The opening and closing degree of the iris is controlled by the digital signal processing unit 39.

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

The image processor 35 performs signal processing to display the digitally converted RAW data. The image processor 35 removes the black level caused by the dark current generated by the CCD and the CFA filter that are sensitive to the temperature change. The image processor 35 performs gamma correction to encode information according to nonlinearity of human vision. The image processor 35 performs CFA interpolation to interpolate the Bayer pattern implemented by the RGRG line and the GBGB line of the gamma corrected predetermined data into the RGB line. The image processing unit 35 converts the interpolated RGB signal into a YUV signal and filters the Y signal by a high band filter to clearly process the image, and uses the standard color coordinate system to adjust the color values of the U and V signals. Perform color correction to correct and remove their noise. The image processor 35 generates a JPEG file by compressing and signal-processing Y, U, and V signals from which noise is removed, and the generated JPEG file is displayed on the display unit 23 and stored in the storage unit 37. do. All of the operations of the image processor 35 operate under the control of the digital signal processor 39.

The digital signal processor 39 controls each block of FIG. 3, extracts and displays character information from an arbitrary video, and extracts a still image, that is, a slide, for a specific character from the video and plays the slideshow. do.

To this end, the digital signal processor 39 may include a face recognition unit 39-1, a person information extractor 39-2, a still image extractor 39-3, a shake determination unit 39-4, and a controller 39. -5).

FIG. 4A illustrates a video file titled <Winter Story> having a playing time of 5 minutes. For convenience of explanation, it is divided into (a), (b), (c), (d), and (e) sections by 1 minute unit.

The face recognition unit 39-1 searches for a character through face recognition in an entire video section or a selected video section.

The face recognition unit 39-1 detects face information, that is, a face size, a face position, and a face direction in the display unit 23 from the video displayed on the display unit 23. When detecting the size of the face, the face recognizing unit 39-1 uses a method such as detecting a face region based on color or a face region based on an edge, and the face size detection is already known. Many details are given, so detailed description is omitted. When detecting the position of the face, the face recognizing unit 39-1 may calculate the face position based on a distance between the center of the extracted face and a predetermined center of the display unit 23. The face recognizing unit 39-1 may detect a face direction in the form of a triangle composed of eyes and mouth from the extracted face at the time of detecting the direction of the face. Detailed description will be omitted.

Generally, a video is classified into 30 frames per second and 15 frames per second. If the 5-minute video is obtained at 30 frames per second as shown in FIG. 4A, the number of frames included in the 5-minute video is 5 (Minutes) x 60 (seconds) x 30 (frames) = 9000 frames.

Ideally, it is desirable to find a person appearing in the 9000 frame by using the face recognition unit 39-1 with the image of the 9000 frame. However, it is more preferable to consider the driving time and the efficiency of the face recognition unit 39-1. For example, when extracting one frame per 15 frames, the number of frames applied to the face recognition unit 39-1 will be 9000 frames / 15 frames = 600 frames, and extract one frame per 30 frames. Assume that the number of frames applied to the face recognition unit 39-1 is 9000 frames / 30 frames = 300 frames, so that the time required for face recognition processing can be appropriately adjusted.

4B illustrates a result of extracting a character as a face recognition result of the face recognition unit 39-1. In the <Winter Story> video of FIG. 4A, four characters were searched for [Gun, Bin, Younghee, and Cheolsoo]. The name of the searched face may be directly input by the user, or, if there is a face previously searched and registered in the address book, the name may be automatically input to the face.

When the person information extracting unit 39-2 extracts the appearance section and the appearance time of the character found by the face recognition unit 39-1 and transmits it to the control unit 39-5, the control unit 39-5 processes it. To display on the display unit 23. As shown in FIG. 4C, the person information extracting unit 39-2 searches for a section and a time at which the character searched by the face recognition unit 39-1 appears, and is displayed under the control of the controller 39-5. It can display in the part 23. 4D illustrates that even when two or more people are extracted, the person information extracting unit 39-2 extracts a section and a time at which the character searched by the face recognition unit 39-1 appears and displays the unit under the control of the controller 39-5. (23) shows that it can be displayed.

As such, the character list of the video searched by the face recognition unit 39-1 and the appearance period and appearance time of the character extracted by the person information extracting unit 39-2 are controlled by the controller 39-5. After saving the work in (37), the work can be completed more quickly than the first time by reading the character list, the appearance section, and the appearance time that have been saved.

The still image extracting unit 39-3 extracts a still image of the selected specific character. As shown in FIG. 4B, when the character is [Gun, Bin, Alice, and withdrawal], the still image extracting unit 39-3 may extract the still image in each combination. However, if there are more than a certain number of characters appearing in a video, the number of combinations may be so large that displaying all of them may be inconvenient to see. Therefore, only a certain number of characters are shown, not combinations, and the user adds more combinations. If desired, the user directly selects a character to determine a particular combination. This means that it is not necessary to display all combinations at once.

When the user selects a specific character through the user input unit 31, the controller 39-5 sets a still image extraction interval, and displays how many still images are extracted for the specific character. The display unit 23 is controlled to be displayed together to help the user's selection.

For example, in the case of setting the still image extraction interval for 30 minutes for 3 minutes in FIG. 4C, the total number of frames for 3 minutes is 5400 frames (3 (minutes) × 60 (seconds) × 30 (frame)}, and when the still image extraction interval is set to 30 seconds, the total number of still images extracted by the still image extraction unit 39-3 is 180 frames (5400 frames / 30 seconds), which is a control unit. Under control of 39-5, the display unit 23 is displayed together with the specific characters.

The controller 39-5 collects and stores the still image extracted by the still image extracting unit 39-3, and controls to reproduce the slide image by applying various effects set by the user. Here, the slideshow playback is a function of continuously playing back the still image photographed by the digital image processing apparatus at a set time interval, and the controller 39-5 receives the slideshow playback setting time interval of the still image extracted from the video. Controls playback of slideshows of still images.

In addition, a shake determination unit 39-4 may further include a still image that is out of focus from the extracted still image, that is, the shaking still image. The shake still image may be excluded while the user directly looks at the still image, but when selecting the automatic mode, the shake determination unit 39-4 may automatically exclude the shake still image which is not in focus.

The shake determination unit 39-4 may detect a shake by using an edge extraction of a still image for extracting a still image that is not in focus, and relates to a shake determination for a still image. The content is omitted since many known techniques.

In the present invention, a face recognition technique is used to search for a character from an arbitrary video, and extracts only a scene in which a specific character appears as a still image and reproduces it as a slide show.

In another embodiment, when the user has already stored a still image for a specific person in the digital image processing apparatus, the facial feature information is extracted from the still image through face recognition and stored in the specific person. By using the stored characteristic of the specific person and the set still image extraction interval, the still image of the specific person can be easily extracted from the video and played as a slide show. In this case, since the digital image processing apparatus already stores facial feature information on a specific person, it is possible to reduce the character searching time through face recognition from the selected video, thereby enabling more efficient processing.

Hereinafter, a slideshow reproduction method of a still image extracted from a moving image in the digital image processor according to the present invention will be described in detail with reference to FIG. 5. In the digital image processor according to the present invention, the slideshow reproduction method of the still image extracted from the moving image may be performed in the digital image processor as shown in FIG. 3. It may be performed inside the digital signal processor 39 with the help of peripheral components.

When an arbitrary video is selected by the user (step 501), the digital signal processor 39 determines whether to apply the entire section of the video (step 503) or determines whether to apply a partial section of the video (step 505). ).

When a partial section of the video is applied, a section selection signal is received from the user (step 507).

The digital signal processing unit 39 searches for the list of characters through the face recognition program in the entire video and the partial section of the video, and displays the searched section and the appearance time of the searched character on the display unit 23 (509). step). Searching for the character list, the appearance period and the appearance time of the character is omitted because it is described above.

The character list of the video searched by the digital signal processor 39, the appearance section and the appearance time of the characters are stored in the storage unit 37, and the additional character list, appearance section, and appearance that have been stored in the subsequent work are stored. By reading the time, the task can be completed faster than the first.

The digital signal processing unit 39 receives a specific character selection signal from among the characters displayed on the display unit 23 from the user (step 511).

In addition, the digital signal processor 39 receives and sets a still image extraction interval of a specific character selected by the user (step 513). When the user selects a specific character through the user input unit 31, the digital signal processor 39 sets a still image extraction interval and displays how many still images are extracted for the specific character. The display unit 23 is controlled to be displayed together to help the user's selection.

Thereafter, the digital signal processor 39 extracts a still image of the specific character selected according to the still image interval from the moving image (step 515).

When the still image extraction is completed, the digital signal processor 39 selects the still image that is shaken, that is, out of focus, from the extracted whole still image (step 517). The shake still image may be excluded while the user directly views the still image, but when the automatic mode is selected, the digital signal processor 39 may automatically exclude the shake still image that is not in focus. The digital signal processing unit 39 has a method for discriminating a still image having a shake by using an edge extraction of the still image. There are many known techniques for determining a shake with respect to a still image. Therefore, it will be omitted.

The digital signal processing unit 39 determines whether to delete the entire still image shaken (step 519), and if the user selects it, deletes the whole still image shaken from the extracted still image (step 521).

Alternatively, the digital signal processor 39 determines whether to delete part of the still image shaken (step 523), and if the user selects it, selects the still image to be deleted (step 525), and the digital signal processor 39 selects the selected still image. Delete (step 527).

Subsequently, the digital signal processing unit 39 deletes all or part of the still image shaken from the extracted still image or stores the extracted still image in the storage unit 37 regardless of the shaken still image (step 529).

Thereafter, the digital signal processor 39 reproduces the still image of the specific person whose various effects are set according to the user's selection using the slideshow function (step 531). The slide show playback is a function of continuously playing back a still image photographed by a digital image processing apparatus at a set time interval, and the digital signal processing unit 39 receives a slide show playback setting time interval of a still image extracted from a video and stops it. Control to play slideshow of video.

1 is a perspective view showing the front and top appearance of a digital image processor.

FIG. 2 is a rear view illustrating a rear shape of the digital image processor illustrated in FIG. 1.

3 is a block diagram showing the configuration of a slide show playback apparatus of a still image extracted from a video in the digital image processor according to the present invention.

4 is a view for explaining a still image conversion of a video in FIG.

5 is a flowchart illustrating an operation of a slideshow reproduction method of a still image extracted from a moving image in the digital image processor according to the present invention.

Claims (10)

As a digital image processor, And digital signal processing means for extracting and displaying character information from an arbitrary video, and extracting and displaying a still image of a specific character from the video and playing the same as a slideshow. The method of claim 1, wherein the video Slide show playback device of a still image extracted from a video, characterized in that the entire section or selected partial section. The method of claim 1, wherein the specific character is A slide show playback apparatus for still images extracted from a moving picture, characterized in that there is at least one person. The method of claim 1, wherein the digital signal processing means A face recognition unit searching for a character through face recognition of the video; A person information extracting unit which extracts an appearance section and an appearance time of the found character; A still image extraction unit which extracts a still image of a specific character selected from the video; And And controlling a face recognition control, person information and still image extraction for the video, and controlling the storage and playback of the slideshow of the extracted still image. Device. The method of claim 4, wherein And a shake determination unit for determining a shake of the still image of the extracted specific character. The method of claim 4, wherein The control unit sets a still image extraction interval of the selected specific character, And the still image extracting unit extracts a still image of the specific character from the moving image at the set extraction interval. As an operation method of a digital image processor, (a) extracting and displaying character information from an arbitrary video; And (b) extracting a still image of a specific character from the video and playing the slideshow as a slide show. The method of claim 7, wherein step (a) (a-1) searching for a character from the video through face recognition; (a-2) calculating a time when the searched character appears in the video; And (a-3) displaying the searched character and the appearance time calculated for the same together. The method of claim 7, wherein step (b) (b-1) selecting a specific character as the displayed character; (b-2) setting a still image extraction interval of the selected specific character; (b-3) extracting and storing a still image of the specific character from the video at the set extraction interval; And and (b-4) playing the still image of the stored specific character as a slide show. The method of claim 7, wherein in step (b), And determining the shaking of the extracted still image of the particular person to exclude the still image from the still image.

Images