Computerized system and method for automatically generating high-quality digital content thumbnails from digital video
Disclosed are systems and methods for improving interactions with and between computers in content searching, generating, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods automatically generate a thumbnail image from a frame of a video file, where the thumbnail image displays content of a selected frame determined to be high-quality and highly-relevant to the content of the video file. Frames of a video file are analyzed, and the frame that is the most contextually relevant to the video and of the highest visual quality is selected, where a thumbnail image is generated and displayed on a site or application over a network.
1. A method comprising:
identifying, via a computing device, a video comprising a plurality of video frames, each frame comprising an image;
parsing, via the computing device, selected video frames of said plurality, and based on said parsing, identifying content features of each selected frame, the content features corresponding to an aesthetic of content depicted by each frames' image;
filtering, via the computing device, the video based on the content features, and based on said filtering, identifying a frame set with content features having aesthetic values above a quality threshold, said quality threshold set such that a frame's image content within a type of frame depicts content at a predetermined visual aesthetic value, said content features of the identified frame set having aesthetic values above said quality threshold;
analyzing, via the computing device, said frame set, and based on said analysis, determining a stillness value of each frame in said frame set;
extracting, via the computing device performing keyframe extraction, a subset from said frame set based on the determined stillness values, said subset comprising a portion of frames within said frame set that have a stillness value at or below a threshold corresponding to a predetermined motion entry value of frame content, such that frames in said frame set with stillness values above said threshold are discarded; and
generating, via the computing device, a graphics interchange format (GIF) file from said subset.
2. The method of claim 1 , further comprising:
receiving, over a network, a request for a webpage; and
in response to said request, communicating said webpage, said communicated webpage comprising said GIF file such that upon display of said webpage, said GIF file is rendered causing the subset of frames to sequentially render.
3. The method of claim 1 , wherein said filtering further comprises:
analyzing the frames of the video, and based on said analysis, determining a type of each frame; and
discarding, based on said quality threshold, a frame from said video frames when said frame type is a transition frame.
4. The method of claim 1 , wherein said filtering further comprises:
analyzing the frames of the video, and based on said analysis, determining a quality value of each frame's content depicted in the respective image;
discarding, based on said quality threshold, a frame from said video frames when said quality value indicates the frame is a low-quality frame.
5. The method of claim 4 , wherein said low-quality frames comprise content that is dark, blurry or uniform-colored.
6. The method of claim 1 , wherein said aesthetic values correspond to at least one of a brightness value, sharpness value, colorfulness value and stillness value.
7. The method of claim 1 , further comprising:
ranking the frames within said subset based on said visual similarity, wherein said GIF file is based on a second subset of frames selected from said subset, said second subset comprising frames having a predetermined similarity value above a predetermined level.
8. The method of claim 1 , wherein said subset of frames extracted for said GIF file generation are sequentially located within said video.
9. A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions, that when executed by a computing device, perform a method comprising:
identifying, via the computing device, a video comprising a plurality of video frames, each frame comprising an image;
parsing, via the computing device, selected video frames of said plurality, and based on said parsing, identifying content features of each selected frame, the content features corresponding to an aesthetic of content depicted by each frames' image;
filtering, via the computing device, the video based on the content features, and based on said filtering, identifying a frame set with content features having aesthetic values above a quality threshold, said quality threshold set such that a frame's image content within a type of frame depicts content at a predetermined visual aesthetic value, said content features of the identified frame set having aesthetic values above said quality threshold;
analyzing, via the computing device, said frame set, and based on said analysis, determining a stillness value of each frame in said frame set;
extracting, via the computing device performing keyframe extraction, a subset from said frame set based on the determined stillness values, said subset comprising a portion of frames within said frame set that have a stillness value at or below a threshold corresponding to a predetermined motion entry value of frame content, such that frames in said frame set with stillness values above said threshold are discarded; and
generating, via the computing device, a graphics interchange format (GIF) file from said subset.
10. The non-transitory computer-readable storage medium of claim 9 , further comprising:
receiving, over a network, a request for a webpage; and
in response to said request, communicating said webpage, said communicated webpage comprising said GIF file such that upon display of said webpage, said GIF file is rendered causing the subset of frames to sequentially render.
11. The non-transitory computer-readable storage medium of claim 9 , wherein said filtering further comprises:
analyzing the frames of the video, and based on said analysis, determining a type of each frame; and
discarding, based on said quality threshold, a frame from said video frames when said frame type is a transition frame.
12. The non-transitory computer-readable storage medium of claim 9 , wherein said filtering further comprises:
analyzing the frames of the video, and based on said analysis, determining a quality value of each frame's content depicted in the respective image;
discarding, based on said quality threshold, a frame from said video frames when said quality value indicates the frame is a low-quality frame.
13. The non-transitory computer-readable storage medium of claim 12 , wherein said low-quality frames comprise content that is dark, blurry or uniform-colored.
14. The non-transitory computer-readable storage medium of claim 9 , wherein said aesthetic values correspond to at least one of a brightness value, sharpness value, colorfulness value and stillness value.
15. The non-transitory computer-readable storage medium of claim 9 , further comprising:
ranking the frames within said subset based on said visual similarity, wherein said GIF file is based on a second subset of frames selected from said subset, said second subset comprising frames having a predetermined similarity value above a predetermined level.
16. The non-transitory computer-readable storage medium of claim 9 , wherein said subset of frames extracted for said GIF file generation are sequentially located within said video.
17. A computing device comprising:
a processor; and
a non-transitory computer-readable storage medium for tangibly storing thereon program logic for execution by the processor, the program logic comprising:
logic executed by the processor for identifying, via the computing device, a video comprising a plurality of video frames, each frame comprising an image;
logic executed by the processor for parsing, via the computing device, selected video frames of said plurality, and based on said parsing, identifying content features of each selected frame, the content features corresponding to an aesthetic of content depicted by each frames' image;
logic executed by the processor for filtering, via the computing device, the video based on the content features, and based on said filtering, identifying a frame set with content features having aesthetic values above a quality threshold, said quality threshold set such that a frame's image content within a type of frame depicts content at a predetermined visual aesthetic value, said content features of the identified frame set having aesthetic values above said quality threshold;
logic executed by the processor for analyzing, via the computing device, said frame set, and based on said analysis, determining a stillness value of each frame in said frame set;
logic executed by the processor for extracting, via the computing device performing keyframe extraction, a subset from said frame set based on the determined stillness values, said subset comprising a portion of frames within said frame set that have a stillness value at or below a threshold corresponding to a predetermined motion entry value of frame content, such that frames in said frame set with stillness values above said threshold are discarded; and
logic executed by the processor for generating, via the computing device, a graphics interchange format (GIF) file from said subset.
18. The computing device of claim 17 , further comprising:
receiving, over a network, a request for a webpage; and
in response to said request, communicating said webpage, said communicated webpage comprising said GIF file such that upon display of said webpage, said GIF file is rendered causing the subset of frames to sequentially render.