Methods and apparatus for centroid based object segmentation in object recognition-type image processing system

Claim 1

A method of establishing the boundaries of an object in an input image including a plurality of image pixels having gradient values predetermined gray scale, wherein the object includes a centroid, the method, performed by a signal processing system, comprising the steps of: deciding on a perimeter surrounding the object in the input image; repeatedly searching, from an image pixel corresponding to the centroid of the object to image pixels of the perimeter, for an image pixel having a highest gradient value of the gradient values of the searched pixels; marking, as an edge pixel, the image pixel having the highest gradient value for each of the repeated searches when said highest gradient value exceeds a predetermined threshold; and locating and connecting gaps, if any are located between marked edge pixels.

Claim 2

A method of establishing the boundaries of an object in an input image including a plurality of image pixels having gradient values predetermined gray scale, wherein the object includes a centroid, the method, performed by a signal processing system, comprising the steps of: deciding on a perimeter surrounding the object in the input image; repeatedly searching, from an image pixel corresponding to the centroid of the object to image pixels of the perimeter, for an image pixel having a highest gradient value of the gradient values of the searched pixels; marking, as an edge pixel, the image pixel having the highest gradient value for each of the repeated searches when said highest gradient value exceeds a predetermined threshold; and locating and connecting gaps, if any are located between marked edge pixels.

Claim 3

A method of determining whether a pixel of an input image corresponds to part of an object, wherein the input image includes a plurality of image pixels having gradient values of a predetermined gray scale, wherein the object includes a centroid, the method, performed by a signal processing system, comprising the steps of; deciding on a perimeter surrounding the object in the input image; deciding on a minimum object area of the input image around a pixel of the input image corresponding to the centroid; repeatedly searching, along a sweep hand extending from the pixel corresponding to the centroid of the object to the perimeter, for an image pixel having a highest gradient value of the gradient values of the searched pixels; marking, as an edge pixel, the image pixel having the highest gradient value for each of the repeated searches when said highest gradient value exceeds a predetermined threshold and provided the image pixel is outside the minimum object area: and locating and connecting gaps, if any are located between marked edge pixels.

Claim 4

A method of determining whether a pixel of an input image corresponds to part of an object, wherein the input image includes a plurality of image pixels having gradient values of a predetermined gray scale, wherein the object includes a centroid, the method, performed by a signal processing system, comprising the steps of; deciding on a perimeter surrounding the object in the input image; deciding on a minimum object area of the input image around a pixel of the input image corresponding to the centroid; repeatedly searching, along a sweep hand extending from the pixel corresponding to the centroid of the object to the perimeter, for an image pixel having a highest gradient value of the gradient values of the searched pixels; marking, as an edge pixel, the image pixel having the highest gradient value for each of the repeated searches when said highest gradient value exceeds a predetermined threshold and provided the image pixel is outside the minimum object area: and locating and connecting gaps, if any are located between marked edge pixels.

Claim 5

A method of determining whether a pixel of an input image corresponds to part of an object, wherein the input image includes a plurality of pixels, each of the pixels having a gradient value of a predetermined gray scale, and wherein the object includes a centroid, the method, performed by a signal processing system, comprising the steps of: receiving the input image and a location of a pixel corresponding to the centroid of the object within the input image; sweeping an imaginary clock hand fixed an the location of the pixel corresponding to the centroid of the object around the input image to locate a pixel underneath each position of the imaginary clock hand that has a highest gradient value of the gradient values of the pixels underneath each position of the imaginary clock hand; marking, as an edge pixel, the pixel having the highest gradient value for each position of the imaginary clock hand when said highest gradient value exceeds a predetermined threshold; and locating and connecting gaps, if any are located between marked edge pixels.

Claim 6

A method of determining whether a pixel of an input image corresponds to part of an object, wherein the input image includes a plurality of pixels, each of the pixels having a gradient value of a predetermined gray scale, and wherein the object includes a centroid, the method, performed by a signal processing system, comprising the steps of: receiving the input image and a location of a pixel corresponding to the centroid of the object within the input image; sweeping an imaginary clock hand fixed an the location of the pixel corresponding to the centroid of the object around the input image to locate a pixel underneath each position of the imaginary clock hand that has a highest gradient value of the gradient values of the pixels underneath each position of the imaginary clock hand; marking, as an edge pixel, the pixel having the highest gradient value for each position of the imaginary clock hand when said highest gradient value exceeds a predetermined threshold; and locating and connecting gaps, if any are located between marked edge pixels.

Claim 15

A method of establishing a perimeter of an object in an input image including a plurality of pixels having gradient values of a predetermined gray scale, wherein a subset of the pixels establishes a boundary of the input image and each of the pixels has a gradient value, and wherein one of the pixels identifies a centroid of the object, the method, performed by a signal processing system comprising the steps of: receiving data identifying a minimum object pixel subset of the pixels within both the pixels of the boundary input image and the pixels of the image that correspond to the object; repeatedly scanning the pixels outside the pixels of the minimum object pixel subset but within the pixels of the boundary of the input image to identify high-gradient pixels having a gradient value that exceed a predetermined threshold level; marking the identified high-gradient pixels as edge pixels; and locating and connecting gaps, if any are located between marked sage pixels.

Claim 16

A method of establishing a perimeter of an object in an input image including a plurality of pixels having gradient values of a predetermined gray scale, wherein a subset of the pixels establishes a boundary of the input image and each of the pixels has a gradient value, and wherein one of the pixels identifies a centroid of the object, the method, performed by a signal processing system comprising the steps of: receiving data identifying a minimum object pixel subset of the pixels within both the pixels of the boundary input image and the pixels of the image that correspond to the object; repeatedly scanning the pixels outside the pixels of the minimum object pixel subset but within the pixels of the boundary of the input image to identify high-gradient pixels having a gradient value that exceed a predetermined threshold level; marking the identified high-gradient pixels as edge pixels; and locating and connecting gaps, if any are located between marked sage pixels.

Claim 19

A method of determining whether a pixel of an input image corresponds to part of an object, wherein the input image includes a plurality of pixels, each of the pixels having a gradient value, and wherein the object includes a centroid, the method, performed by a signal processing system, comprising the steps of: receiving the input image and a location of the centroid within the input image; fixing an imaginary clock hand fixed at the location of the centroid; sweeping, beginning at a first position, the imaginary clock hand clockwise or counterclockwise around the input image to locate a pixel underneath each position of the imaginary clock hand that has a highest gradient value; determining whether the highest gradient value exceeds a predetermined threshold gradient value; and marking the pixel having the highest gradient value that exceeds the predetermined threshold gradient value as an edge pixel; repeatedly performing the sweeping step, the determining step, and the marking step on successive positions of the imaginary clock hand until reaching the first position; and locating and connecting gaps, if any are located between marked edge pixels.

Claim 20

A method of determining whether a pixel of an input image corresponds to part of an object, wherein the input image includes a plurality of pixels, each of the pixels having a gradient value, and wherein the object includes a centroid, the method, performed by a signal processing system, comprising the steps of: receiving the input image and a location of the centroid within the input image; fixing an imaginary clock hand fixed at the location of the centroid; sweeping, beginning at a first position, the imaginary clock hand clockwise or counterclockwise around the input image to locate a pixel underneath each position of the imaginary clock hand that has a highest gradient value; determining whether the highest gradient value exceeds a predetermined threshold gradient value; and marking the pixel having the highest gradient value that exceeds the predetermined threshold gradient value as an edge pixel; repeatedly performing the sweeping step, the determining step, and the marking step on successive positions of the imaginary clock hand until reaching the first position; and locating and connecting gaps, if any are located between marked edge pixels.