Clothes and accessories fitting method, display system and computer-readable recording medium thereof

1. A clothes and accessories fitting method, applicable to a display system having an image capturing device and a screen, comprising:

capturing a plurality of images of a user wearing a first apparel appearing in front of the screen continuously or intermittently by using the image capturing device;

in response to a determination that a pose of the user of a first image of the plurality of images matches a particular pose, shooting the first image by using the image capturing device;

segmenting a foreground region and a background region in the first image, and processing the background region to generate a processed background region, wherein the step of segmenting the foreground region and the background region in the first image comprises:

perfonning facial detection on the first image to define a facial region;

defining a foreground segmented region in the first image according to the facial region;

obtaining a depth image corresponding to the first image;

perfonning binarization on the depth image to accordingly generate a plurality of foreground depth pixels;

defining and setting a plurality of foreground plane pixels corresponding to the foreground depth pixels in the foreground segmented region as the foreground region; and

setting a region outside the foreground region in the first image as the foreground region; and

generating a first preview image according to the foreground region and the processed background region, and displaying the preview image on the screen.

2. The method according to claim 1 , wherein during the step of capturing the images of the user wearing the first apparel appearing in front of the screen continuously or intermittently by using the image capturing device, the method further comprises:

presetting the display system to enter a mirror mode so as to allow the images captured by the image capturing device to be displayed on the screen in real time;

determining whether there exists a potential user in the images; and

in response that the potential user is determined to be existed in the images, setting the display system to enter a video mode so as to allow the images captured by the image capturing device to be displayed on the screen and recording the images to generate a recorded video.

3. The method according to claim 2 further comprising:

in response that the potential user in the images is determined to leave, setting the display system to leave the video mode and to return to the mirror mode and deleting the recorded video.

4. The method according to claim 2 further comprising:

in response that the potential user is determined to be an authorized user of the display system, setting the display system to leave the video mode and storing the recorded video in a database.

5. The method according to claim 1 , wherein before the determination that the pose of the user of the first image of the plurality of images matches the particular pose, the method further comprises:

setting the display system to enter a try-on mode;

wherein while the display system is in the try-on mode, after the step of generating the first preview image, the method further comprises:

setting the display system to leave the try-on mode and displaying the first preview image on the screen.

6. The method according to claim 5 , wherein while the display system is in the try-on mode, after the step of generating the first preview image, the method further comprises:

capturing at least one other first image of the user wearing the first apparel in other poses by using the image capturing device; and

processing the at least one other first image to generate at least one other first preview image.

7. The method according to claim 6 , wherein after the step of generating the first preview image and the at least one other first preview image, the method further comprises:

storing the first preview image and the at least one other first preview image in a database; and

setting the display system to leave the try-on mode and enter a lookbook mode.

8. The method according to claim 7 , wherein the database further comprises at least one preview image corresponding to at least one other apparel, and wherein in response that the display system enters the lookbook mode, the method further comprises:

detecting a selection operation performed by the user on a designated pose among a plurality of poses; and

displaying a plurality of designated preview images corresponding to the designated pose on the screen, wherein each of the designated preview images is associated with a processed image of the user wearing a different apparel in the same designated pose.

9. The method according to claim 1 , wherein the step of defining the foreground segmented region in the first image according to the facial region comprises:

defining a head region of the user according to the facial region;

calculating a height of the user according to the head region; and

defining a boundary of the foreground segmented region according to the facial region and the height of the user.

10. The method according to claim 1 , wherein the step of performing binarization on the depth image to accordingly generate the foreground depth pixels comprises:

performing binarization on the depth image to generate a plurality of foreground pixels; and

performing erosion, dilation, and blur processing on the foreground pixels to generate the foreground depth pixels.

11. The method according to claim 10 , wherein the step of generating the foreground depth pixels further comprises:

setting a background depth pixel neighboring to and having a similar pixel value to the foreground depth pixels as one of the foreground depth pixels.

12. The method according to claim 10 , wherein the step of generating the foreground depth pixels further comprises:

obtaining a distance range of the user with respect to the image capturing device;

obtaining a depth information range corresponding to the distance range according to a depth-distance relationship table; and

filtering out the foreground depth pixels with depth information being greater than the depth information range.

13. The method according to claim 1 , wherein the step of processing the background region to generate the processed background region comprises:

performing blur processing on the background region to generate the processed background region.

14. The method according to claim 1 , wherein the step of processing the background region to generate the processed background region comprises:

setting a preset background as the processed background region.

15. A clothes and accessories fitting method, applicable to a display system having an image capturing device and a screen comprising:

capturing a plurality of images of a user wearing a first apparel appearing in front of the screen continuously or intermittently by using the image capturing device;

in response to a determination that a pose of the user of a first image of the plurality of images matches a particular pose, shooting the first image by using the image capturing device;

segmenting a foreground region and a background region in the first image, and processing the background region to generate a processed background region, wherein the step of processing the background region to generate the processed background region comprises:

scanning an identification code of the first apparel to obtain related information of the first apparel and thereby obtaining a color shade of the first apparel from the related information;

generating a corresponding background related to a contrasting color of the color shade of the first apparel; and

setting the corresponding background as the processed background; and

generating a first preview image according to the foreground region and the processed background region, and displaying the preview image on the screen.

16. The method according to claim 15 , wherein the step of segmenting the foreground region and the background region in the first image comprises:

performing facial detection on the first image to define a facial region;

defining a foreground segmented region in the first image according to the facial region;

obtaining a depth image corresponding to the first image;

performing binarization on the depth image to accordingly generate a plurality of foreground depth pixels;

defining and setting a plurality of foreground plane pixels corresponding to the foreground depth pixels in the foreground segmented region as the foreground region; and

setting a region outside the foreground region in the first image as the foreground region.

17. The method according to claim 16 , wherein the step of defining the foreground segmented region in the first image according to the facial region comprises:

defining a head region of the user according to the facial region;

calculating a height of the user according to the head region; and

defining a boundary of the foreground segmented region according to the facial region and the height of the user.

18. The method according to claim 16 , wherein the step of performing binarization on the depth image to accordingly generate the foreground depth pixels comprises:

performing binarization on the depth image to generate a plurality of foreground pixels; and

performing erosion, dilation, and blur processing on the foreground pixels to generate the foreground depth pixels.

19. The method according to claim 18 , wherein the step of generating the foreground depth pixels further comprises:

setting a background depth pixel neighboring to and having a similar pixel value to the foreground depth pixels as one of the foreground depth pixels.

20. The method according to claim 18 , wherein the step of generating the foreground depth pixels further comprises:

obtaining a distance range of the user with respect to the image capturing device;

obtaining a depth information range corresponding to the distance range according to a depth-distance relationship table; and

filtering out the foreground depth pixels with depth information being greater than the depth information range.

21. A display system comprising:

an image capturing device, configured to capture images;

a screen, configured to display images, wherein a capturing direction of the image capturing device is the same as a display direction of the screen;

a data storage device, configured to store data; and

a processor, coupled to the image capturing device, the screen, and the data storage device, and configured to:

capture a plurality of images of a user wearing a first apparel appearing in front of the screen continuously or intermittently by using the image capturing device;

in response to a determination that a pose of the user of a first image of the plurality of images matches a particular pose, shoot the first image by using the image capturing device;

segment a foreground region and a background region in the first image, and process the background region to generate a processed background region, wherein the processor is further configured to:

perform facial detection on the first image to define a facial region;

define a foreground segmented region in the first image according to the facial region;

obtain a depth image corresponding to the first image;

perform binarization on the depth image to accordingly generate a plurality of foreground depth pixels;

define and setting a plurality of foreground plane pixels corresponding to the foreground depth pixels in the foreground segmented region as the foreground region; and

set a region outside the foreground region in the first image as the foreground region; and

generate a first preview image according to the foreground region and the processed background region, and display the preview image on the screen.

22. A non-transitory computer-readable recording medium, recording computer programs to be loaded and executed by a processor of a display system having an image capturing device and a screen to perform steps of:

capturing a plurality of images of a user wearing a first apparel appearing in front of the screen continuously or intermittently by using the image capturing device;

in response to a determination that a pose of the user of a first image of the plurality of images matches a particular pose, shooting the first image by using the image capturing device;

segmenting a foreground region and a background region in the first image, and processing the background region to generate a processed background region, wherein the step of segmenting the foreground region and the background region in the first image comprises:

performing facial detection on the first image to define a facial region;

defining a foreground segmented region in the first image according to the facial region;

obtaining a depth image corresponding to the first image;

performing binarization on the depth image to accordingly generate a plurality of foreground depth pixels;

defining and setting a plurality of foreground plane pixels corresponding to the foreground depth pixels in the foreground segmented region as the foreground region; and

setting a region outside the foreground region in the first image as the foreground region; and

generating a first preview image according to the foreground region and the processed background region, and displaying the preview image on the screen.