Auto-focus Method Using Dynamic Eye Distance for False Face Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing methods face challenges in maintaining proper focus when detecting faces that do not conform to common anthropometric rules, leading to incorrect focus and potential loss of focus in cameras, as 'false faces' can mislead the auto-focusing system.
Innovation Solution
An image processing method that performs a focus sweep to determine the optimal lens displacement for detected faces, using a temporary eye distance calculation to differentiate between true and false faces, ensuring accurate focus by calculating the DAC Code for the correct eye distance, even if the detected face does not conform to standard dimensions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If face detection is based on common anthropometric rules, then rapid auto-focus can be achieved, but false faces (non-conforming faces) cause incorrect focus and loss of focus capability
Solution Approach 1:
The system dynamically adjusts the eye distance parameter based on detected face characteristics. Instead of using a fixed anthropometric eye distance value, the system performs a focus sweep to determine the actual eye distance for each detected face, allowing adaptation to both normal and false faces. This dynamic adjustment resolves the contradiction by maintaining rapid focusing capability while ensuring accuracy for varying face types.
Solution Approach 2:
The invention changes the eye distance parameter from a fixed value based on common anthropometric rules to a variable value determined through focus sweep. By modifying this key parameter dynamically based on actual detection results rather than assuming standard dimensions, the system achieves both speed and reliability in auto-focus operation.
2Measurement precision
If a focus sweep is performed to determine optimal lens displacement, then accurate focus is achieved for both true and false faces, but processing time increases
Solution Approach 1:
The system performs a focus sweep as a preliminary action to determine the actual eye distance before using it for subsequent focusing operations. This preliminary measurement, though time-consuming initially, establishes an accurate reference value that can be used for rapid focusing in later operations, reducing overall time loss.
Solution Approach 2:
The focus sweep process is self-adapting - it automatically determines the correct eye distance for each detected face without requiring external intervention or manual adjustment. The system serves itself by using the focus sweep results to calibrate its own focusing parameters, achieving precision without requiring additional complex external systems.
Data Source
AI summary
A method of processing an image comprises: acquiring an image of a scene including an object having a recognizable feature. A lens actuator setting providing a maximum sharpness for a region of the image including the object and a lens displacement corresponding to the lens actuator setting are determined. A distance to the object based on the lens displacement is calculated. A dimension of the feature as a function of the distance to the object, the imaged object size and a focal length of a lens assembly with which the image was acquired, is determined. The determined dimension of the feature is employed instead of an assumed dimension of the feature for subsequent processing of images of the scene including the object.