IP Library Granted Patent US 11,744,464
Granted Patent B2
US 11,744,464 · App. 17/649,452 · Granted Sep 5, 2023

Methods for visual identification of cognitive disorders

Inventors: Baruch Schler (Petach Tikwa, IL); Jonathan Schler (Petach Tikwa, IL)
Assignees: Baruch Schler; Jonathan Schler
A61B5/0022A61B5/4082A61B5/4088G06N3/044G06N3/08G06V10/764G06V10/82G06V40/171G16H30/40G16H40/67G16H50/20G16H50/30G06V10/32
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,744,464
App. No.
17/649,452
Granted
Sep 5, 2023
Kind
B2
Abstract

A method and system for generating a classifier to classify facial images for cognitive disorder in humans. The system comprises receiving a labeled dataset including set of facial images, wherein each of the facial image is labeled depending on whether it represents a cognitive disorder condition; extracting, from each facial image in the set of facial images, at least one learning facial feature indicative of a cognitive disorder; and feeding the extracted facial features into a to produce a machine learning trained model to generate a classifier, wherein the classifier is generated and ready when the trained model includes enough facial features processed by a machine learning model.

Claims (24)

1. A method for generating a classifier to classify facial images for cognitive disorder in humans, comprising:

receiving a labeled dataset including set of facial images, wherein each of the facial image is labeled depending on whether it represents a cognitive disorder condition;

extracting, from the each of the facial image in the set of facial images, at least one learning facial feature indicative of a cognitive disorder;

feeding the at least one extracted facial feature to produce a machine learning trained model, wherein the at least one extracted facial feature is identified to represent a human face; and

generating a classifier based on the machine learning trained model, wherein the classifier is generated and ready when the trained model includes enough facial features processed by a machine learning model, wherein the classifier is configured to map a detection facial feature from a detection facial image to a score and output a plurality of scores indicating a stage of a cognitive decline.

2. The method of claim 1 , wherein the classifier is generated per type of the cognitive disorder.

3. The method of claim 1 , wherein the cognitive disorder further includes illnesses including at least one of: dementia, Parkinson, and anxiety.

4. The method of claim 1 , wherein the machine learning model is a deep neural network.

5. The method of claim 1 , further comprising:

converting the each of the facial image in the received learning dataset into numerical descriptors reflecting attributes of the human face.

6. A non-transitory computer readable medium having stored thereon instructions for a processing circuitry to execute a process for generating a classifier to classify facial images for cognitive disorder in humans, the process comprising:

receiving a labeled dataset including set of facial images, wherein each of the facial image is labeled depending on whether it represents a cognitive disorder condition;

extracting, from the each of the facial image in the set of facial images, at least one learning facial feature indicative of a cognitive disorder;

feeding the at least one extracted facial feature to produce a machine learning trained model, wherein the at least one extracted facial feature is identified to represent a human face; and

generating a classifier based on the machine learning trained model, wherein the classifier is generated and ready when the trained model includes enough facial features processed by a machine learning model, wherein the classifier is configured to map a detection facial feature from a detection facial image to a score and output a plurality of scores indicating a stage of a cognitive decline.

7. A system for generating a classifier to classify facial images for cognitive disorder in humans, comprising:

a processing circuitry; and

a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

receive a labeled dataset including set of facial images, wherein each of the facial image is labeled depending on whether it represents a cognitive disorder condition;

extract, from the each of the facial image in the set of facial images, at least one learning facial feature indicative of a cognitive disorder; and

feed the at least one extracted facial feature into a to produce a machine learning trained model, wherein the at least one extracted facial feature is identified to represent a human face; and

generate a classifier based on the machine learning trained model, wherein the classifier is generated and ready when the trained model includes enough facial features processed by a machine learning model, wherein the classifier is configured to map a detection facial feature from a detection facial image to a score and output a plurality of scores indicating a stage of a cognitive decline.

8. The system of claim 7 , wherein the classifier is generated per type of the cognitive disorder.

9. The system of claim 7 , wherein the cognitive disorder further includes illnesses including at least one of: dementia, Parkinson, and anxiety.

Continuity (2)
Division 16880683 · May 21, 2020
Related Publication 20220165425A1 · May 26, 2022