Back to results
US 9,070,015 B2Granted
System and method for iris detection in digital images
AssigneeIttiam Systems (P) Ltd.
InventorsHamsalekha Sridhara, Srinivasan Ekabaram, Omkar Kedarnath Sastry, Murali Babu Muthukrishnan
Life of this patent
Estimating the term…
Abstract
A system and a method for iris detection in a face region of a digital image are disclosed. In one embodiment, iris is detected in the face region of the digital image using eye features, such as a shape of the iris and/or luminance values of a sclera region.
Claims30
A method for iris detection in a digital image, comprising:
- detecting iris in a face region of the digital image using eye features including a shape of using including the iris and luminance values of a sclera region, comprising
- detecting edges in a predetermined region of the face region;
- detecting eye regions in the predetermined region based on the detected edges;
- detecting sclera pixels in the eye regions using an adaptive threshold value derived from a histogram of luminance values within the eye regions;
- identifying sclera edge pixels as sclera pixels that are next to the edges from the detected sclera pixels;
- identifying one or more sets of continuous sclera edge pixels that are next to the detected edges in the eye regions from the identified sclera edge pixels;
- and
- detecting the iris in the predetermined region using the one or more identified sets of continuous sclera edge pixels.
5 more elements
A method for iris detection in a digital image, comprising:
- detecting iris in a face region of the digital image using eye features including a shape of the iris and luminance values of a sclera region, comprising:
- detecting edges in a predetermined region of the face region;
- detecting eye regions in the predetermined region based on the detected edges;
- detecting sclera pixels in the eye regions;
- identifying sclera edge pixels as sclera pixels that are next to the edges from the detected sclera;
- identifying the one or more sets of continuous sclera edge pixels that are next to the detected edges in the eye regions from the identified sclera edge pixels;
- drawing chords starting from edges that are adjacent to the one or more identified sets of continuous sclera edge pixels and ending on edges;
- grouping the chords which are adjacent to each other;
- identifying and declaring the chords with a maximum length in each of the groups as iris diameters;
- determining a number of chords subtending candidate iris circles associated with each of the iris diameters;
- and
- declaring each candidate iris circle as the iris, if the candidate iris circle includes a maximum number of subtended chords which exceeds a first predetermined value and a percentage of edges on its circumference exceeds a second predetermined value.
9 more elements
An iris detection system, comprising:
- a processor;
- and
- memory coupled to the processor, wherein the memory includes an iris detection module to:
- detect iris in a face region of a digital image using eye features including a shape of the iris and luminance values of a sclera region, wherein the iris detection module is configured to:
- detect edges in a predetermined region of the face region;
- detect eye regions in the predetermined region based on the detected edges;
- detect sclera pixels in the eye regions using an adaptive threshold value derived from a histogram of luminance values within the eye regions;
- identify sclera edge pixels as sclera pixels that are next to the edges from the detected sclera pixels;
- identify one or more sets of continuous sclera edge pixels that are next to the detected edges in the eye regions from the identified sclera edge pixels;
- and
- detect the iris in the predetermined region using the one or more identified sets of continuous sclera edge pixels.
8 more elements
An iris detection system, comprising:
- a processor;
- and
- memory coupled to the processor, wherein the memory includes an iris detection module to:
- detect iris in a face region of a digital image using eye features including a shape of the iris and luminance values of a sclera region, wherein the iris detection module is configured to:
- detect edges in a predetermined region of the face region;
- detect eye regions in the predetermined region based on the detected edges;
- detect sclera pixels in the eye regions;
- identify sclera edge pixels as sclera pixels that are next to the edges from the detected sclera pixels;
- identify one or more sets of continuous sclera edge pixels that are next to the detected edges in the eye regions from the identified sclera edge pixels;
- draw chords starting from edges that are adjacent to the one or more identified sets of continuous sclera edge pixels and ending on edges;
- group the chords which are adjacent to each other;
- identify and declare the chords with a maximum length in each of the groups as iris diameters;
- determine a number of chords subtending candidate iris circles associated with each of the iris diameters;
- and
- declare each candidate iris circle as the iris, if the candidate iris circle include a maximum number of subtended chords which exceeds a first predetermined value and a percentage of edges on its circumference exceeds a second predetermined value.
12 more elements
A non-transitory computer-readable storage medium having instructions that, when executed by a computing device, cause the computing device to:
- detect iris in a face region of a digital image using eye features including a shape of the iris and luminance values of a sclera region, comprising:
- detect edges in a predetermined region of the face region;
- detect eye regions in the predetermined region based on the detected edges;
- detecting sclera pixels in the eye regions using an adaptive threshold value derived from a histogram of luminance values within the eye regions;
- identifying sclera edge pixels as sclera pixels that are next to the edges from the detected sclera pixels;
- identify one or more sets of continuous sclera edge pixels that are next to the detected edges in the eye regions from the identified sclera edge pixels;
- and
- detect the iris in the predetermined region using the one or more identified sets of continuous sclera edge pixels.
5 more elements
A method for detecting, iris iii a face region of a digital image, comprising:
- detecting edges in a predetermined region of the face region;
- detecting eye regions in the predetermined region based on the detected edges;
- identifying one or more sets of continuous sclera edge pixels that are next to the detected edges in the eye regions;
- drawing chords starting from edges that are adjacent to the one or more identified sets of continuous sclera edge pixels and ending on edges;
- grouping the chords which are adjacent to each other;
- identifying and declaring the chords with a maximum length in each of the groups as iris diameters;
- determining a number of chords subtending candidate iris circles associated with each of the iris diameters;
- and
- declaring each candidate iris circle as the iris, when the candidate iris circle includes a maximum number of subtended chords which exceeds a first predetermined value and a percentage of edges on its circumference exceeds a second predetermined value.
6 more elements
An iris detection system for detecting iris in a face region of a digital image, comprising:
- a processor;
- and
- memory coupled to the processor, wherein the memory includes an iris detection module to:
- detect edges in a predetermined region of the face region;
- detect eye regions in the predetermined region based on the detected edges;
- identify one or more sets of continuous sclera edge pixels that are next to the detected edges in the eye regions;
- draw chords starting from edges that are adjacent to the one or more identified sets of continuous sclera edge pixels and ending on edges;
- group the chords which are adjacent to each other;
- identify and declare the chords with a maximum length in each of the groups as iris diameters;
- determine a number of chords subtending candidate iris circles associated with each of the iris diameters;
- and
- declare each candidate iris circle as the iris, when the candidate iris circle include a maximum number of subtended chords which exceeds a first predetermined value and a percentage of edges on its circumference exceeds a second predetermined value.
9 more elements
A non-transitory computer-readable storage medium having instructions that, when executed by a computing device, cause the computing device to perform a method for detecting iris in a face region of a digital image, the method comprising:
- detecting edges in a predetermined region of the face region;
- detecting eye regions in the predetermined region based on the detected edges;
- identifying one or more sets of continuous sclera edge pixels that are next to the detected edges in the eye regions;
- drawing chords starting from edges that are adjacent to the one or more identified sets of continuous sclera edge pixels and ending on edges;
- grouping the chords which are adjacent to each other;
- identifying and declaring chords with a maximum length in each of the groups as iris diameters;
- determining a number of chords subtending candidate iris circles associated with each of the iris diameters;
- and
- declaring each candidate iris circle as the iris, when the candidate iris circle includes a mum number of subtended chords which exceeds a first predetermined value and a percentage of edges on its circumference exceeds a second predetermined value.
6 more elements
Dependencies are inferred from the claim text.