20240029269. NEURAL NETWORK FOR EYE IMAGE SEGMENTATION AND IMAGE QUALITY ESTIMATION simplified abstract (Magic Leap, Inc.)

From WikiPatents
Jump to navigation Jump to search

NEURAL NETWORK FOR EYE IMAGE SEGMENTATION AND IMAGE QUALITY ESTIMATION

Organization Name

Magic Leap, Inc.

Inventor(s)

Alexey Spizhevoy of Novgorod (RU)

Adrian Kaehler of Los Angeles CA (US)

Vijay Badrinarayanan of Los Altos CA (US)

NEURAL NETWORK FOR EYE IMAGE SEGMENTATION AND IMAGE QUALITY ESTIMATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240029269 titled 'NEURAL NETWORK FOR EYE IMAGE SEGMENTATION AND IMAGE QUALITY ESTIMATION

Simplified Explanation

The patent application describes systems and methods for eye image segmentation and image quality estimation. Here is a simplified explanation of the abstract:

  • The invention involves using a convolutional neural network with a merged architecture to process an eye image and generate both a segmented eye image and a quality estimation of the eye image.
  • The segmented eye image can include different regions such as the background, sclera, iris, or pupil.
  • The device can also determine eye contours, such as the pupil contour and iris contour, using the segmented eye image.
  • The device can create a polar image of the iris region using the eye contours, which can be used for computing an iris code or biometric authentication.

Potential Applications:

  • Biometric authentication systems: The technology can be used in systems that require iris recognition for secure access control or identification purposes.
  • Medical imaging: The segmentation and quality estimation techniques can be applied in medical imaging applications, such as diagnosing eye diseases or monitoring eye health.
  • Augmented reality devices: The technology can be integrated into augmented reality devices to enhance eye tracking capabilities and improve user experience.

Problems Solved:

  • Accurate eye image segmentation: The invention solves the problem of accurately segmenting different regions of the eye, such as the iris and pupil, from an eye image.
  • Image quality estimation: The technology addresses the challenge of estimating the quality of an eye image, which can be useful in various applications, including biometric authentication.

Benefits:

  • Improved biometric authentication: The invention can enhance the accuracy and reliability of iris recognition systems, making them more secure for authentication purposes.
  • Enhanced medical diagnosis: The segmentation and quality estimation techniques can assist medical professionals in accurately diagnosing eye conditions and monitoring changes over time.
  • Enhanced user experience in augmented reality: By improving eye tracking capabilities, the technology can enhance the user experience in augmented reality applications, such as gaming or virtual simulations.


Original Abstract Submitted

systems and methods for eye image segmentation and image quality estimation are disclosed. in one aspect, after receiving an eye image, a device such as an augmented reality device can process the eye image using a convolutional neural network with a merged architecture to generate both a segmented eye image and a quality estimation of the eye image. the segmented eye image can include a background region, a sclera region, an iris region, or a pupil region. in another aspect, a convolutional neural network with a merged architecture can be trained for eye image segmentation and image quality estimation. in yet another aspect, the device can use the segmented eye image to determine eye contours such as a pupil contour and an iris contour. the device can use the eye contours to create a polar image of the iris region for computing an iris code or biometric authentication.

Retrieved from "http://wikipatents.org/index.php?title=20240029269._NEURAL_NETWORK_FOR_EYE_IMAGE_SEGMENTATION_AND_IMAGE_QUALITY_ESTIMATION_simplified_abstract_(Magic_Leap,_Inc.)&oldid=29251"