Method for generating a slide show of an image
View Patent ↗The present invention discloses methods for generating a slide show of an image. With the methods, every still image could be displayed with the vivid effect of a dynamic video. The steps of one method according to the present invention comprise: performing a semantic analysis of a image for detecting semantic regions; selecting a first region and a second region from the semantic regions; determining a first and a second zooming levels of the first and second regions, respectively; and generating a slide show of the image by panning the image from the first region to the second region while zooming the image from the first zooming level to the second zooming level, gradually.
1. A method for generating a slide show of a still image by executing computer-executable instructions stored in a computer-readable storage medium, said method comprising:
performing a semantic analysis of said still image to detect semantic regions of the still image;
selecting a first region and a second region from among said semantic regions of the still image, wherein said first region and said second region are different regions of the still image;
determining a first zooming level of said first region and a second zooming level of said second region, wherein the first zooming level is different from the second zooming level; and
generating said slide show of said still image to simulate video effect by panning across said still image from said first region to said second region while gradually zooming said still image from said first zooming level of said first region to said second zooming level of said second region.
2. The method as set forth in claim 1 , wherein said semantic analysis includes human face detection.
3. The method as set forth in claim 1 , wherein each of said semantic regions further comprises a neighborhood with a predetermined area surrounding a focus of said still image, and information of said focus is recorded in the tag of said still image in Exif format.
4. The method as set forth in claim 1 , wherein panning said still image from said first region to said second region includes panning along a panning path across at least two of said semantic regions.
5. The method as set forth in claim 1 , wherein said first zooming level is determined according to a first ratio of said first region area to said still image area and a first distance between said first region center and said still image center, and said second zooming level is determined according to a second ratio of said second region area to said still image area and a second distance between said second region center and said still image center.
6. The method as set forth in claim 1 , which further comprises the step of determining a zooming status of said still image according to the zooming status of at least one former still image.
7. A method as set forth in claim 1 , wherein a portion of said first region overlaps with a portion of said second region.
8. A method for generating a slide show of a still image by executing computer-executable instructions stored in a computer-readable storage medium, said method comprising:
performing a semantic analysis of said still image to detect a semantic region of the still image, said still image having a still image area and a still image center, and said semantic region having a semantic region area and a semantic region center;
establishing a zooming code by determining a first number of zoom-in times indicative of the number of zoom-in times of at least one former still image, determining a second number of zoom-out times indicative of the number of zoom-out times of at least one former still image, determining a ratio of said semantic region area to said still image area, and determining a distance between said semantic region center and said still image center;
determining a zooming level of said semantic region and a zooming stats of said still image according to the zooming code; and
generating said slide show of said still image to simulate video effect by zooming said still image centered on said semantic region according to said zooming level and said zooming status.
9. The method as set forth in claim 8 , wherein said semantic analysis includes human face detection.
10. A method for generating a slide show of a still image by executing computer-executable instructions stored in a computer-readable storage medium, said method comprising:
performing non-semantic analysis of said still image to detect non-semantic regions of the still image;
selecting a first region and a second region from among said non-semantic regions of the still image, wherein said first region and said second region are different regions of the still image;
determining a first zooming level of said first region and a second zooming level of said second region, wherein the first zooming level is different from the second zooming level; and
generating said slide show of said still image to simulate video effect by panning across said still image from said first region to said second region while gradually zooming said still image from said first zooming level of said first region to said second zooming level of said second region.
11. The method as set forth in claim 10 , wherein said non-semantic analysis includes symmetric region detection.
12. The method as set forth in claim 10 , wherein each of said non-semantic regions further comprises a neighborhood with a predetermined area surrounding a focus of said still image, and information of said focus is recorded in the tag of said still image in Exif format.
13. The method as set forth in claim 10 , wherein panning said still image from said first region to said second region includes panning along a panning path across at least two of said non-semantic regions.
14. The method as set forth in claim 10 , wherein said first zooming level is determined according to a first ratio of said first region area to said still image area and a first distance between said first region center and said stilt image center, and said second zooming level is determined according to a second ratio of said second region area to said still image area and a second distance between said second region center and said still image center.
15. The method as set forth in claim 10 , which further comprises the step of determining a zooming status of said still image according to the zooming status of at least one former still image.
16. A method as set forth in claim 10 , wherein a portion of said first region overlaps with a portion of said second region.
17. A computer-readable storage medium having computer-executable instructions for generating a slide show of a still image by performing the following, comprising:
performing a semantic analysis of said still image to detect semantic regions of the still image;
selecting a first region and a second region from among said semantic regions of the still image, wherein said first region and said second region are different regions of the still image;
determining a first zooming level of said first region and a second zooming level of said second region, wherein the first zooming level is different from the second zooming level; and
generating said slide show of said still image to simulate video effect by panning across said still image from said first region to said second region while gradually zooming said still image from said first zooming level of said first region to said second zooming level of said second region.
18. The computer-readable storage medium as set forth in claim 17 , wherein said semantic analysis includes human face detection.
19. The computer-readable storage medium as set forth in claim 17 , wherein each of said semantic regions further comprises a neighborhood with a predetermined area surrounding a focus of said still image, and information of said focus is recorded in the tag of said still image in Exif format.
20. The computer-readable storage medium as set forth in claim 17 , wherein panning said still image from said first region to said second region includes panning along a panning path across at least two of said semantic regions.
21. The computer-readable storage medium as set forth in claim 17 , wherein said first zooming level is determined according to a first ratio of said first region area to said still image area and a first distance between said first region center and said still image center, and said second zooming level is determined according to a second ratio of said second region area to said still image area and a second distance between said second region center and said still image center.
22. The computer-readable storage medium as set forth in claim 17 , which further comprises the step of determining a zooming status of said still image according to the zooming stats of at least one former still image.
23. A computer-readable storage medium having computer-executable instructions for generating a slide show of a still image by performing the following, comprising:
performing a semantic analysis of said still image to detect a semantic region of the still image, said still image having a still image area and a still image center, and said semantic region having a semantic region area and a semantic region center;
establishing a zooming code by determining a first number of zoom-in times indicative of the number of zoom-in times of at least one former still image, determining a second number of zoom-out times indicative of the number of zoom-out times of at least one former still image, determining a ratio of said semantic region area to said still image area, and determining a distance between said semantic region center and said still image center; and
determining a zooming level of said semantic region and a zooming status of said still image according to the zooming code; and
generating said slide show of said still image to simulate video effect by zooming said still image according to said zooming level and said zooming status.
24. The computer-readable storage medium as set forth in claim 23 , wherein said semantic analysis includes human face detection.
25. A computer-readable storage medium having computer-executable instructions for generating a slide show of a still image by performing the following, comprising:
performing non-semantic analysis of said still image to detect non-semantic regions of the still image;
selecting a first region and a second region from among said non-semantic regions of the still image, wherein said first region and said second region are different regions of the still image;
determining a first zooming level of said first region and a second zooming level of said second region, wherein the first zooming level is different from the second zooming level; and
generating said slide show of said still image to simulate video effect by panning across said still image from said first region to said second region while gradually zooming said still image from said first zooming level of said first region to said second zooming level of said second region.
26. The computer-readable storage medium as set forth in claim 25 , wherein said non-semantic analysis includes symmetric region detection.
27. The computer-readable storage medium as set forth in claim 25 , wherein each of said non-semantic regions further comprises a neighborhood with a predetermined area surrounding a focus of said still image, and information of said focus is recorded in the tag of said still image in Exif format.
28. The computer-readable storage medium as set forth in claim 25 , wherein panning said still image from said first region to said second region includes panning along a panning path across at least two of said non-semantic regions.
29. The computer-readable storage medium as set forth in claim 25 , wherein said first zooming level is determined according to a first ratio of said first region area to said still image area and a first distance between said first region center and said still image center, and said second zooming level is determined according to a second ratio of said second region area to said still image area and a second distance between said second region center and said still image center.
30. The computer-readable storage medium as set forth in claim 25 , which further comprises the step of determining a zooming status of said still image according to the zooming status of at least one former still image.
31. A computer-readable storage medium storing computer-executable instructions for generating a slide show of a still image, said computer-readable storage medium including:
at least an analysis module comprising computer executable instructions for performing a semantic analysis of said still image to detect semantic regions of the still image and selecting a first region and a second region from among said semantic regions of the still image, wherein said first region and said second region are different regions of the still image;
a zooming level/status determining module comprising computer executable instructions for determining a first zooming level of said first region and a second zooming level of said second region, wherein the first zooming level is different from the second zooming level; and
a slide show generating module comprising computer executable instructions for generating said slide show of said still image to simulate video effect by panning across said still image from said first region to said second region while gradually zooming said still image from said first zooming level of said first region to said second zooming level of said second region.
32. The computer-readable storage medium as set forth in claim 31 comprising a second analysis module comprising computer executable instructions for performing non-semantic analysis of said still image and detecting non-semantic regions thereof and selecting a first region Thereof and a second region from among said non-semantic regions.
33. The computer-readable storage medium as set forth in claim 31 , wherein said semantic analysis includes human face detection, default object detection or user-defined object detection.
34. The computer-readable storage medium as set forth in claim 31 , wherein each of said semantic regions further comprises a neighborhood with a predetermined area surrounding a focus of said still image, and information of said focus is recorded in the tag of said still image in Exif format.
35. The computer-readable storage medium as set forth in claim 31 , wherein panning of said still image from said first region to said second region includes panning along a panning path across at least two of said semantic regions.
36. The computer-readable storage medium as set forth in claim 31 , wherein said first zooming level is determined according to a first ratio of said first region area to said still image area and a first distance between said first region center and said still image center, and said second zooming level is determined according to a second ratio of said second region area to said still image area and a second distance between said second region center and said still image center.
37. The computer-readable storage medium as set forth in claim 31 , wherein said zooming level/status determining module may be employed for determining a zooming status of said still image according to the zooming status of at least one former still image.
38. A computer-readable storage medium as set forth in claim 31 , wherein a portion of said first region overlaps with a portion of said second region.
39. A computer-readable storage medium storing computer-executable instructions for generating a slide show of a still image, said computer-readable storage medium including:
a first analysis module comprising computer executable instructions for performing a semantic analysis of said still image to detect a semantic region of the still image;
a second analysis module comprising computer executable instructions for performing non-semantic analysis of said still image, detecting non-semantic regions of the still image and selecting a first region and a second region from said non-semantic regions of the still image, wherein said first region and said second region are different regions of the still image;
a zooming code determining module comprising computer executable instructions for establishing a zooming code by determining a first number of zoom-in times indicative of the number of zoom-in times of at least one former still image, determining a second number of zoom-out times indicative of the number of zoom-out times of at least one former still image, determining a ratio of said semantic region area to said still image area, and determining a distance between said semantic region center and said still image center; and
a zooming level/status determining module comprising computer executable instructions for determining a zooming level of said semantic region and a zooming status of said still image according to the zooming code; and
a slide show generating module comprising computer executable instructions for generating said slide show of said still image to simulate video effect by zooming said still image centered on said semantic region according to said zooming level and said zooming status.
40. The computer-readable storage medium as set forth in claim 39 , wherein said semantic analysis includes human face detection, default object detection or user-defined object detection.
41. A computer-readable storage medium as set forth in claim 39 , wherein a portion of said first region overlaps with a portion of said second region.
42. A computer-readable storage medium storing computer-executable instructions for generating a slide show of a still image, said computer-readable storage medium including:
at least an analysis module comprising computer executable instructions for performing non-semantic analysis of said still image and detecting non-semantic regions of the still image and selecting a first region and a second region from among said non-semantic regions of the still image, wherein said first region and said second region are different regions of the still image;
a zooming level/status determining module comprising computer executable instructions for determining a first zooming level of said first region and a second zooming level of said second region, wherein the first zooming level is different from the second zooming level; and
a slide show generating module comprising computer executable instructions for generating said slide show of said still image to simulate video effect by panning across said still image from said first region to said second region while gradually zooming said still image from said first zooming level of said first region to said second zooming level of said second region.
43. The computer-readable storage medium as set forth in claim 42 comprising a second analysis module comprising computer executable instructions for performing non-semantic analysis of said still image and detecting non-semantic regions thereof and selecting a first region and a second region from among said non-semantic regions.
44. The computer-readable storage medium as set forth in claim 42 , wherein said non-semantic analysis includes symmetric region detection.
45. The computer-readable storage medium as set forth in claim 42 , wherein each of said non-semantic regions further comprises a neighborhood with a predetermined area surrounding a focus of said still image, and information of said focus is recorded in the tag of said still image in Exif format.
46. The computer-readable storage medium as set forth in claim 42 , wherein panning of said still image from said first region to said second region includes panning along a panning path across at least two of said non-semantic regions.
47. The computer-readable storage medium as set forth in claim 42 , wherein said first zooming level is determined according to a first ratio of said first region area to said still image area and a first distance between said first region center and said still image center, and said second zooming level is determined according to a second ratio of said second region area to said still image area and a second distance between said second region center and said still image center, wherein said first zooming level may be larger than, equal to or smaller than said second zooming level.
48. The computer-readable storage medium as set forth in claim 42 , wherein said zooming level/status determining module may be employed for determining a zooming stabs of said still image according to the zooming status of at least one former still image.
49. A computer-readable storage medium as set forth in claim 42 , wherein a portion of said first region overlaps with a portion of said second region.