18514325. IMAGE PROCESSING APPARATUS CONFIGURED TO PERFORM FACE RECOGNITION, IMAGE PROCESSING METHOD, AND STORAGE MEDIUM simplified abstract (CANON KABUSHIKI KAISHA)

From WikiPatents
Jump to navigation Jump to search

IMAGE PROCESSING APPARATUS CONFIGURED TO PERFORM FACE RECOGNITION, IMAGE PROCESSING METHOD, AND STORAGE MEDIUM

Organization Name

CANON KABUSHIKI KAISHA

Inventor(s)

SHUNTA Tate of Tokyo (JP)

YASUHIRO Okuno of Tokyo (JP)

HIDEKI Sorakado of Tokyo (JP)

IMAGE PROCESSING APPARATUS CONFIGURED TO PERFORM FACE RECOGNITION, IMAGE PROCESSING METHOD, AND STORAGE MEDIUM - A simplified explanation of the abstract

This abstract first appeared for US patent application 18514325 titled 'IMAGE PROCESSING APPARATUS CONFIGURED TO PERFORM FACE RECOGNITION, IMAGE PROCESSING METHOD, AND STORAGE MEDIUM

Simplified Explanation

The patent application describes an image processing apparatus that can determine if objects in two images are the same.

  • First acquisition unit acquires feature amount from first image using first trained model.
  • Second acquisition unit acquires feature amount from second image using second trained model.
  • Verification unit determines if objects in images are the same based on feature amounts.
  • Second trained model learns feature amounts in same feature space as first trained model.

Potential Applications

  • Image recognition and comparison in security systems.
  • Object tracking in surveillance cameras.
  • Quality control in manufacturing processes.

Problems Solved

  • Efficient and accurate object identification in images.
  • Reduction of human error in manual image comparison tasks.

Benefits

  • Increased automation in image processing tasks.
  • Improved accuracy in object recognition.
  • Enhanced security measures through reliable image comparison.


Original Abstract Submitted

An image processing apparatus includes a first acquisition unit configured to acquire a first feature amount from a first image based on a first trained model configured to extract a feature from an image, a second acquisition unit configured to acquire a second feature amount from a second image based on a second trained model determined based on a state of the second image and configured to extract a feature from an image, and a verification unit configured to determine, based on the first feature amount and the second feature amount, whether an object in the first image and an object in the second image are the same. The second trained model is a model having learned the second feature amount in a same feature space as that for the first trained model.