IDENTIFYING NON-OCCLUDED FACES BY LEARNING FROM PARTIALLY OCCLUDED FACES

Patent №

US 9,704,025

Granted

2017-07-11

Filed 2015

Owner

KING ABDULAZIZ CITY FOR SCIENCE AND TECHNOLOGY

Lab

AI components

2

ml · vision

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

14815108

Systems and methods of facial recognition of non-occluded or non-obstructed faces is provided. The method includes generating a skin mask based on an occluded image of an individual and removing occluded areas for the occluded image using the skin mask so that skin areas remain. The method further includes generating a correlation filter based on the occluded image. The method further includes applying the skin mask and correlation filter to a non-occluded input image of an individual. The method further includes generating a correlation output based on applying the skin mask and correlation filter to the non-occluded input image. The correlation output may indicate a likelihood that the second individual in the non-occluded input image is of the first individual in the occluded image.

Machine learningVisionG06V 40/168G06F 18/214G06V 40/172

AI classification

Vision1.00
Machine learning0.68
Knowledge representation0.09
Natural language0.08
AI hardware0.04
Evolutionary computation0.02
Planning0.00
Speech0.00

Ownership

KING ABDULAZIZ CITY FOR SCIENCE AND TECHNOLOGY

assignment · 362300049

Assignors

AL-QUNAIEER, FARES SALEH, ALKANHAL, MOHAMED IBRAHIM

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC