Methods and Systems for Detecting Pictorial Regions in Digital Images
First Claim
Patent Images
1. A method for detecting a pictorial region in a digital image, said method comprising:
- a) calculating a masked entropy value for each of a plurality of pixels in a digital image;
b) determining a confidence level for each of said plurality of pixels based on said masked entropy values;
c) determining a seed region based on said masked entropy values wherein said seed region comprises seed-region pixels from said plurality of pixels; and
d) growing said seed region based on said confidence levels thereby producing a pictorial region wherein said pictorial region comprises pictorial-region pixels from said plurality of pixels.
2 Assignments
0 Petitions
Accused Products
Abstract
Embodiments of the present invention comprise systems, methods and devices for detection of pictorial regions in an image using a masking condition, an entropy measure, and region growing.
105 Citations
20 Claims
-
1. A method for detecting a pictorial region in a digital image, said method comprising:
-
a) calculating a masked entropy value for each of a plurality of pixels in a digital image; b) determining a confidence level for each of said plurality of pixels based on said masked entropy values; c) determining a seed region based on said masked entropy values wherein said seed region comprises seed-region pixels from said plurality of pixels; and d) growing said seed region based on said confidence levels thereby producing a pictorial region wherein said pictorial region comprises pictorial-region pixels from said plurality of pixels. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A system for detecting a pictorial region in a digital image, said system comprising:
-
a) a calculator for calculating a masked entropy value for each of a plurality of pixels in a digital image; b) a first determiner for determining a confidence level for each of said plurality of pixels based on said masked entropy values; c) a second determiner for determining seed regions based on said masked entropy values; and d) a region grower for growing said regions based on said confidence levels. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17, 18)
-
-
19. A method for detecting a pictorial region in a digital image, said method comprising:
-
a) calculating a masked entropy value for each of a plurality of pixels in a digital image; b) determining a confidence level for each of said plurality of pixels based on said masked entropy values; c) determining a seed region based on said masked entropy values wherein said seed region comprises seed-region pixels from said plurality of pixels; d) obtaining a labeled background map for said digital image wherein said labeled background map comprises a label corresponding to pictorial content; and e) growing said seed region based on said confidence levels and said labeled background map thereby producing a pictorial region wherein said pictorial region comprises pictorial-region pixels from said plurality of pixels. f) refining said pictorial region thereby producing a refined pictorial region; and g) verifying said refined pictorial region thereby producing a verified pictorial region. - View Dependent Claims (20)
-
Specification