Camera-Based Eye-Gaze Detection for Neurological Disease Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye-gaze tracking solutions require dedicated hardware like infrared cameras, making them costly and inaccessible for most patients and clinical units, and often necessitate professional operators for neurological condition assessment.
Innovation Solution
A method using a camera-equipped electronic device displays stimulus videos and films the user's face to generate videos, employing machine learning models to detect neurological diseases by analyzing eye gaze-pattern abnormalities through tasks like fixation, pro-saccade, and anti-saccade, without requiring additional tracking devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If dedicated hardware like infrared cameras is used for eye-gaze tracking, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent uses a standard camera to capture images of the eye instead of requiring specialized infrared cameras. The system creates a digital copy of the eye's appearance under normal lighting conditions and processes this copy through image analysis algorithms to determine gaze direction, achieving functional equivalence without specialized hardware
Solution Approach 2:
The patent replaces the optical-mechanical infrared camera system with a standard digital camera and computational image processing system. Instead of using infrared illumination and specialized sensors, the system uses visible light capture combined with machine learning algorithms to extract gaze information, substituting hardware complexity with software-based solutions
2Reliability
If professional operators are used to determine neurological conditions, then reliability of diagnosis is improved, but ease of operation deteriorates
Solution Approach 1:
The system enables automatic detection of neurological conditions through machine learning models that analyze eye movement patterns without requiring professional operators. The algorithm independently processes the captured video data, extracts relevant features, and generates diagnostic information, allowing the system to serve itself rather than requiring expert human intervention
Solution Approach 2:
The system incorporates machine learning models that learn from training data and provide feedback-based improvement. The models are trained on datasets of eye movement patterns associated with various neurological conditions, allowing them to automatically adapt and improve diagnostic accuracy without requiring continuous professional oversight during operation
3Measurement precision
If bulky tracking devices are used, then measurement precision is improved, but portability and accessibility deteriorate
Solution Approach 1:
The patent makes the eye-tracking system universal by using a standard camera that can be found in most electronic devices rather than specialized equipment. This allows the same system to be deployed across diverse settings including clinical units, home environments, and research laboratories, greatly increasing accessibility and adaptability while maintaining measurement capabilities
Data Source
AI summary
The present disclosure relates to a method and a system for detecting a neurological disease and an eye gaze-pattern abnormality related to the neurological disease of a user. The method comprises displaying stimulus videos on a screen of an electronic device and simultaneously filming with a camera of the electronic device to generate a video of the user's face for each one of the stimulus videos, each one of the stimulus videos corresponding to a task. The method further comprises providing a machine learning model for gaze predictions, generating the gaze predictions for each video frame of the recorded video, and determining features for each task to detect the neurological disease using a pre-trained machine learning model.