Method and apparatus for identifying a desired object of an image using a suggestive marking

摘要

A computer implemented method and apparatus for identifying a desired object of an image by using a suggestive marking. The method comprises receiving a first marking to an image, the first marking suggesting a desired object of the image and the desired object being defined by a boundary; generating, based on the first marking, a plurality of output images, wherein each image of the plurality of output images indicates a computer-identified object; and displaying the plurality of output images.

主权项

1. A computer implemented method comprising:
recognizing user input indicating a first marking to an image, the first marking being in relation to a visual object in the image, the object having a boundary, wherein the object is non-predefined; performing edge detection about the first marking to detect a first potential boundary in the image for the object; performing edge detection at a predefined increment from the first potential boundary for the object to detect a second potential boundary for the object; generating, based on the detected first and second potential boundaries, a plurality of output images, wherein each output image of the plurality of output images includes one of the first or second potential boundaries for the object; and providing the plurality of output images to allow for selection of an output image of the plurality of output images with a potential boundary that corresponds with the boundary of the object.