Feature extraction and use with a probability density function (PDF) divergence metric
First Claim
1. A method of symbol recognition, the method comprising:
- receiving a portion of an image of a scene of real world;
traversing at least the portion of the image to;
identify changes in intensities of pixels in the image; and
generate a group of counts based on the changes, without encoding positions at which the changes occur in the image;
wherein an intensity of each pixel in the portion of the image is used to generate at least one count in the group of counts;
wherein a size of the group of counts is predetermined;
wherein at least a first count in the group of counts is incremented, when an intensity change between two pixels, in a direction of traversal, exceeds a predetermined threshold;
wherein at least a second count in the group of counts is incremented, when the intensity change is positive and the intensity change does not exceed the predetermined threshold;
using a measure of difference between two probability distributions, to compare a vector that is based on at least the group of counts with a plurality of predetermined vectors of corresponding symbols in a set, to identify a specific symbol therein; and
storing the specific symbol in a memory, as being recognized in the image;
wherein the memory is coupled to one or more processors; and
wherein the traversing and the using are performed by the one or more processors.
1 Assignment
0 Petitions
Accused Products
Abstract
An image of real world is processed to identify blocks as candidates to be recognized. Each block is subdivided into sub-blocks, and each sub-block is traversed to obtain counts, in a group for each sub-block. Each count in the group is either of presence of transitions between intensity values of pixels or of absence of transition between intensity values of pixels. Hence, each pixel in a sub-block contributes to at least one of the counts in each group. The counts in a group for a sub-block are normalized, based at least on a total number of pixels in the sub-block. Vector(s) for each sub-block including such normalized counts may be compared with multiple predetermined vectors of corresponding symbols in a set, using any metric of divergence between probability density functions (e.g. Jensen-Shannon divergence metric). Whichever symbol has a predetermined vector that most closely matches the vector(s) is identified and stored.
-
Citations
23 Claims
-
1. A method of symbol recognition, the method comprising:
-
receiving a portion of an image of a scene of real world; traversing at least the portion of the image to; identify changes in intensities of pixels in the image; and generate a group of counts based on the changes, without encoding positions at which the changes occur in the image; wherein an intensity of each pixel in the portion of the image is used to generate at least one count in the group of counts; wherein a size of the group of counts is predetermined; wherein at least a first count in the group of counts is incremented, when an intensity change between two pixels, in a direction of traversal, exceeds a predetermined threshold; wherein at least a second count in the group of counts is incremented, when the intensity change is positive and the intensity change does not exceed the predetermined threshold; using a measure of difference between two probability distributions, to compare a vector that is based on at least the group of counts with a plurality of predetermined vectors of corresponding symbols in a set, to identify a specific symbol therein; and storing the specific symbol in a memory, as being recognized in the image; wherein the memory is coupled to one or more processors; and wherein the traversing and the using are performed by the one or more processors. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. A mobile device to perform symbol recognition, the mobile device comprising:
-
one or more memories comprising a plurality of portions identified from an image of a scene of real world, as candidates to be recognized; one or more processors configured to traverse at least one portion of the image to; identify changes in intensities of pixels in the image; and generate a group of counts based on the changes, without encoding positions at which the changes occur in the image; wherein an intensity of each pixel in the at least one portion of the image is used to generate at least one count in the group of counts; wherein a size of the group of counts is predetermined; wherein at least a first count in the group of counts is incremented, when an intensity change between two pixels, in a direction of traversal, exceeds a predetermined threshold; wherein at least a second count in the group of counts is incremented, when the intensity change is positive and the intensity change does not exceed the predetermined threshold; wherein the one or more processors are configured to use a measure of difference between two probability distributions, to compare a vector based on at least the group of counts with a plurality of predetermined vectors of corresponding symbols in a set, to identify a specific symbol therein; and wherein the one or more processors are configured to store the specific symbol in a memory, as being recognized in the image; wherein the memory is coupled to the one or more processors. - View Dependent Claims (14, 15, 16, 17)
-
-
18. One or more non-transitory storage media comprising instructions, which, when executed in a mobile device, cause one or more processors in the mobile device to perform operations, the instructions comprising:
-
instructions to receive a portion of an image of a scene of real world; instructions to traverse at least the portion of the image to; identify changes in intensities of pixels in the image; and generate a group of counts based on the changes, without encoding positions at which the changes occur in the image; wherein an intensity of each pixel in the portion of the image is used to generate at least one count in the group of counts; wherein a size of the group of counts is predetermined; wherein at least a first count in the group of counts is incremented, when an intensity change between two pixels, in a direction of traversal, exceeds a predetermined threshold; wherein at least a second count in the group of counts is incremented, when the intensity change is positive and the intensity change does not exceed the predetermined threshold; instructions to use a measure of difference between two probability distributions, to compare a vector based on at least the group of counts with a plurality of predetermined vectors of corresponding symbols in a set, to identify a specific symbol therein; and instructions to store the specific symbol in a memory, as being recognized in the image; wherein the memory is coupled to the one or more processors. - View Dependent Claims (19, 20)
-
-
21. An apparatus for symbol recognition, the apparatus comprising:
-
means for receiving a portion of an image of a scene of real world; means for traversing the portion of the image to; identify changes in intensities of pixels in the image; and generate a group of counts based on the changes, without encoding positions at which the changes occur in the image; wherein an intensity of each pixel in the portion of the image is used to generate at least one count in the group of counts; wherein a size of the group of counts is predetermined; wherein at least a first count in the group of counts is incremented, when an intensity change between two pixels, in a direction of traversal, exceeds a predetermined threshold; wherein at least a second count in the group of counts is incremented, when the intensity change is positive and the intensity change does not exceed the predetermined threshold; means for using a measure of difference between two probability distributions, to compare a vector based on at least the group of counts with a plurality of predetermined vectors of corresponding symbols in a set, to identify a specific symbol therein; and means for storing the specific symbol in a memory, as being recognized in the image; wherein the memory is coupled to one or more processors. - View Dependent Claims (22, 23)
-
Specification