Face Age Estimation Using Contourlet Appearance Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Face age-estimation is challenging due to large variations in human faces, influenced by factors like gender, ethnicity, and environmental conditions, making it difficult for both humans and computing devices to accurately estimate age from facial images, especially in real-time applications without user cooperation.
Innovation Solution
The use of a contourlet appearance model (CAM) algorithm to extract feature vectors from facial images, combined with age classifiers and aging functions, allows for accurate age estimation by distinguishing between different age groups and accounting for unique aging mechanisms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If exhaustive comparison methods are used to extract unique information from each image for accurate age-estimation, then measurement precision is improved, but computing time increases significantly
Solution Approach 1:
The patent segments the complex task of age estimation into distinct phases: face detection, feature extraction using contourlet transform, and classification. This segmentation allows each component to be optimized independently, achieving accurate age estimation without requiring exhaustive comparison of all image features.
Solution Approach 2:
The patent extracts only the most relevant features from facial images using contourlet transform, rather than performing exhaustive analysis of all image data. This selective extraction of key features (such as facial contours, textures, and structural characteristics) maintains measurement precision while significantly reducing computation time.
2Measurement precision
If multiple factors including uncontrollable environmental factors are considered in age-estimation, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent introduces contourlet transform as an intermediary processing step that converts complex facial image data into a standardized feature representation. This intermediary transformation handles the complexity of multiple influencing factors (gender, ethnicity, environmental conditions) by converting them into comparable feature vectors, thereby improving measurement precision without increasing the apparent system complexity.
Solution Approach 2:
The patent changes the parameter representation from raw pixel data to contourlet transform coefficients, which better capture the essential characteristics of facial features across different age groups. This parameter transformation allows the system to account for various influencing factors (lighting, pose, ethnicity) while maintaining a consistent and manageable system structure.
Data Source
AI summary
Age-estimation of a face of an individual is represented in image data. In one embodiment, age-estimation techniques involves combining a Contourlet Appearance Model (CAM) for facial-age feature extraction and Support Vector Regression (SVR) for learning aging rules in order to improve the accuracy of age-estimation over the current techniques. In a particular example, characteristics of input facial images are converted to feature vectors by CAM, then these feature vectors are analyzed by an aging-mechanism-based classifier to estimate whether the images represent faces of younger or older people prior to age-estimation, the aging-mechanism-based classifier being generated in one embodiment by running Support Vector Machines (SVM) on training images. In an exemplary binary youth/adult classifier, faces classified as adults are passed to an adult age-estimation function and the others are passed to a youth age-estimation function.