Image Subject Classification via Temporal Facial and Contour Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional image processing systems fail to distinguish between active and passive subjects in digital images, often misidentifying facial data from non-active subjects as active, leading to incorrect processing and requiring subjective user analysis.
Innovation Solution
A system and method that detect facial information by capturing images at two points in time, determining objective difference values in facial expressions and contours, and classifying subjects as active or passive based on threshold values, enabling automatic classification and processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional face detection is used to process images, then active subjects can be identified, but passive subjects are misidentified as active subjects leading to incorrect processing
Solution Approach 1:
The patent applies dynamics by capturing multiple images at different time points and analyzing temporal changes in facial expressions and body contours. Active subjects exhibit dynamic changes while passive subjects remain static, allowing the system to distinguish between them through time-based analysis rather than relying solely on static facial detection.
Solution Approach 2:
The system uses feedback by comparing facial data across multiple time points and using the detected changes to refine subject classification. The objective difference values calculated from temporal comparisons provide feedback that enables accurate distinction between active and passive subjects, correcting the misidentification problem.
2Reliability
If users manually sort through images to remove passive subjects, then processing correctness can be maintained, but user time and processing efficiency are reduced
Solution Approach 1:
The system performs self-service by automatically detecting and classifying subjects as active or passive without requiring user intervention. The automated classification based on temporal analysis of facial expressions and body contours enables the system to handle subject differentiation independently, eliminating the need for manual sorting while maintaining accuracy.
Solution Approach 2:
The patent replaces the mechanical manual sorting process with an automated computational system. Instead of users manually reviewing and sorting images, the system uses objective difference value calculations and automated classification algorithms to distinguish between active and passive subjects, significantly improving processing efficiency.
3Measurement precision
If multiple images are captured at different time points for analysis, then subject classification accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The system applies partial action by capturing a limited number of images (at least two) at different time points rather than continuous streaming. This provides sufficient temporal data for accurate classification while avoiding excessive processing time. The threshold-based comparison of objective difference values enables accurate classification with minimal image sets.
Data Source
AI summary
Described herein is a system and techniques for classification of subjects within image information. In some embodiments, a set of subjects may be identified within image data obtained at two different points in time. For each of the subjects in the set of subjects, facial landmark relationships may be assessed at the two different points in time to determine a difference in facial expression. That difference may be compared to a threshold value. Additionally, contours of each of the subjects in the set of subjects may be assessed at the two different points in time to determine a difference in body position. That difference may be compared to a different threshold value. Each of the subjects in the set of subjects may then be classified based on the comparison between the differences and the threshold values.