Method for producing framing information for a set of images
View Patent ↗A method for producing framing information for a set of N source images, each comprising an object region R, comprises scaling, translating and/or rotating images of the source images so that the object region is aligned. For a given image of the object aligned source images, at a given frame size, a given frame angle for a frame relative to the object aligned images and at a first candidate boundary position for the frame, the method determines if there is at least one position for a second boundary of the frame orthogonal to the first boundary where the frame lies within the image and the frame encloses the object region. If so, counters associated with the first candidate boundary position are incremented. Responsive to any counter meeting a threshold value,K≤N, for the source images, framing is indicated as possible at the given frame size, frame angle, first candidate boundary position and any position for the second boundary associated with the threshold meeting counter. Otherwise, another image can be chosen and the process repeated.
1. A method for producing framing information for a set of source images, each comprising an object region, comprising the steps of:
a) one or more of: scaling, translating and rotating images of said set of N source images so that said object region is aligned within said set of source images;
b) for a given image of said set of object aligned source images, at a given frame size, a given frame angle for a frame relative to said set of object aligned images and at a first candidate boundary position for said frame, determining if there is at least one position for a second boundary of said frame orthogonal to said first boundary where said frame lies within said image and said frame encloses said object region;
c) responsive to said determining, incrementing counters associated with said first candidate boundary position for each position for said second boundary where said frame lies within said image and said frame encloses said object region;
d) responsive to any counter meeting a threshold value,K≤N, for said set of source images, indicating that framing is possible at said given frame size, said frame angle, said first candidate boundary position and any position for said second boundary associated with said threshold meeting counter; and
e) responsive to no counter meeting said threshold value, K, repeating steps b) to e) for another image of said set of source images.
2. A method according to claim 1 wherein said first boundary is one of a top boundary or a side boundary for a frame and wherein said second boundary is the other of said top boundary or said side boundary.
3. A method according to claim 1 wherein said method is responsive to indicating that framing is possible to increase said given width and to repeat steps b) to e).
4. A method according to claim 1 wherein step e) is responsive to no further images being available to either: reduce said frame size; or change said given angle before repeating steps b) to e).
5. A method according to claim 4 wherein step e) is responsive to no further images, no further frame sizes and no further angles being available to reduce said threshold value K by a fraction f, before repeating steps b) to e).
6. A method according to claim 1 wherein said frame has a fixed aspect ratio.
7. A method according to claim 1 further comprising selecting said frame size using a binary search.
8. A method according to claim 1 wherein said incrementing counters comprises incrementing a counter for a first position for said second boundary of said frame orthogonal to said first boundary where said frame lies within said image and said frame encloses said object region and decrementing a counter after a second position for said second boundary of said frame orthogonal to said first boundary where said frame lies within said image and said frame encloses said object region.
9. A method according to claim 1 wherein said step b) of determining comprises:
determining a first intersecting portion of said first candidate boundary position for said frame with said given image;
determining a second intersecting portion of a boundary position for said frame parallel to said first candidate boundary position with said given image;
determining a first extreme position in a direction parallel to said first candidate boundary of said second boundary for said frame so that said frame encloses said object region; and
determining a second opposite extreme position in said direction parallel to said first candidate boundary of said second boundary for said frame so that said frame encloses said object region;
wherein said at least one position for a second boundary comprises an intersection of said first intersecting portion, said second intersecting portion and a portion between said first extreme position and said second extreme position.
10. A method according to claim 1 wherein step a) further comprises down-sampling said set of source images.
11. A method according to claim 1 further comprising preparing a time-lapse sequence of at least P≤K framed images based on images from said set of source images each image containing said object region at a common alignment, scale and angle and at a given frame size, frame angle, first candidate boundary position and second boundary position at which framing is determined to be possible.
12. An image processing comprising image processing means arranged for executing the steps of claim 1 .
13. A computer program product comprising a non-transitory computer readable medium on which instructions are stored which, when executed on a computer system, are configured for performing the steps of claim 1 .