Image analysis based on pixel brightness grouping
AssigneeHewlett-Packard Development Company, L.P.
InventorsFeng Tang, Suk Hwan Lim
Life of this patent
Estimating the term…
Abstract
A method and system for analyzing an image made up of a plurality of pixels includes identifying a subset of the pixels, and for each identified pixel a local patch of pixels surrounding the identified pixel is defined and the pixels in the local patch are grouped into bins. The local patch is divided into a plurality of sub-patches, and for each sub-patch the method includes determining how many pixels in each sub-patch fall into each of the bins to create an intermediate vector, and the intermediate vectors are concatenated to form a feature vector and describe the local patch.
Claims20
A method of analyzing an image made up of a plurality of pixels, each pixel having a brightness intensity, the method comprising:
- identifying a subset of the pixels;
- for each identified pixel:
- defining a local patch of pixels surrounding the identified pixel;
- and
- grouping the pixels in the local patch into a number of bins based on the brightness intensities of the pixels;
- dividing the local patch into a plurality of sub-patches;
- determining, for each sub-patch, how many pixels in each sub-patch fall into each of the bins;
- creating an intermediate vector for each sub-patch based upon how many pixels in each sub-patch fall into each of the bins;
- and
- concatenating the intermediate vectors to form a feature vector and to describe the local patch.
A system for analyzing an image, comprising:
- a processor to:
- receive an image comprising a plurality of pixels;
- identify a subset of the pixels, each pixel having a brightness intensity;
- for each identified pixel of the subset of pixels:
- define a local patch of pixels surrounding the identified pixel;
- group the pixels in the local patch into a number of bins based on the brightness intensities of the pixels;
- divide the local patch into a plurality of sub-patches;
- determine how many pixels in each sub-patch fall into each of the bins;
- create an intermediate vector for each sub-patch based upon how many pixels in each sub-patch fall into each of the bins;
- and
- concatenate the intermediate vectors to form a feature vector and to describe the local patch.
A non-transitory computer-readable storage medium storing instructions that when executed cause a processor to:
- identify a subset of pixels of an image, each pixel having a brightness intensity;
- for each identified pixel of the subset of pixels:
- define a local patch of pixels the identified pixel;
- and
- group the pixels in the local patch into a number of bins based on the brightness intensities of the pixels;
- divide the local patch into a plurality of sub-patches;
- determine how many pixels in each sub-patch fall into each of the bins;
- create an intermediate vector for each sub-patch based upon how many pixels in each sub-patch fall into each of the bins;
- and
- concatenate the intermediate vectors to form a feature vector and to describe the local patch.
Dependencies are inferred from the claim text.