Methods and apparatus for category selective representation of occluding contours for images
OwnerTianlong Cheninventor
Life of this patent
Estimating the term…
Abstract
The present invention discloses methods and apparatuses of coding category-selective representation of occluding contours on an image with or without border-ownership; the invention further discloses methods and apparatuses for generating such category-selective representation of occluding contours on an image with or without border-ownership for a given image by training and using neural networks.
Claims5
A method for representing category-selective occluding contours of objects from an image, where a said object in said image belongs to one of a plurality of different categories, at least comprising:
- (a) using a plurality of first channels to represent said category-selective occluding contours of objects, where said occluding contours of said objects belonging to a said category are put into a said first channel, and a said category is associated with only one said first channel,
- wherein each said first channel represents occluding contours of objects of the corresponding category, rather than classification results.
A method for generating category-selective occluding contours of objects from a given source image, where one said object in said image belonging to one of a plurality of different categories, using a neural network substantially comprising:
- (a) training said neural network with a plurality of ground truth groups, where each said ground truth group is comprised of at least a ground truth image and a ground truth category-selective occluding contour representation associated with said ground truth image, wherein in said category-selective occluding contour representation a plurality of first channels is used to represent said category-selective occluding contours of objects in said category-selective occluding contour representation, and said occluding contours of said objects belonging to a said category are put into a said first channel, and a said category is associated with only one said first channel;
- and
- (b) after said training, input a said source image to trained said neural network, a said category-selective occluding contour representation can be produced as output from trained said neural network,
- wherein said representation comprises channel-based grouping of occluding contours rather than classification results.
Dependencies are inferred from the claim text.