Human Eye Size Recognition via Face Key Point Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image processing applications lack accuracy in recognizing and magnifying human eye sizes from human-face images, as they rely on inefficient methods that do not effectively utilize key point data to determine eye size.
Innovation Solution
A method and apparatus that obtain human-face key point data, extract human-eye feature data, and input it into a pre-trained human-eye size recognition model to determine a degree value characterizing the eye size, allowing for improved accuracy in recognizing and magnifying human eyes based on the obtained degree value.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional image processing methods are used to recognize eye size, then the processing can be performed, but the recognition accuracy is insufficient
Solution Approach 1:
The patent segments the eye region into multiple key points (at least three key points per eye) and processes each key point individually to calculate eye size. This segmentation approach improves measurement precision by capturing detailed geometric information from different locations on the eye, rather than relying on a single measurement point.
Solution Approach 2:
The patent introduces key point data as an intermediary between the original image and the final eye size measurement. By extracting key points from the eye region and using these points as intermediate data, the system achieves more accurate and reliable eye size recognition through geometric calculations based on key point coordinates.
2Measurement precision
If key point data is extracted and processed through multiple steps, then the accuracy improves, but the processing complexity increases
Solution Approach 1:
The patent performs preliminary extraction of eye key points from the input image before conducting size measurements. By pre-processing the image to identify and extract key point coordinates of the eye region, the system simplifies subsequent measurement operations and improves accuracy without requiring complex real-time processing during the measurement phase.
Solution Approach 2:
The patent transforms the eye size measurement problem from direct pixel measurement to geometric parameter calculation based on key point coordinates. By changing the measurement parameters from raw image pixels to calculated distances and ratios between key points, the system achieves higher precision while maintaining manageable processing complexity.
Data Source
AI summary
A method and an apparatus for outputting data are provided. The method includes: obtaining a set of human-face key point data, where the human-face key point data characterizes a position of a key point of a human face in a target human-face image; determining human-eye feature data for characterizing a shape feature of a human eye, based on the set of the human-face key point data; and inputting the human-eye feature data into a human-eye size recognition model obtained by pre-training to obtain a degree value for characterizing a size of the human eye, and outputting the degree value. The human-eye size recognition model characterizes a correspondence between human-eye feature data and a degree value. With the above method, the human-face key point data is effectively utilized to determine the size of the human eye, improving the accuracy of recognizing the size of the human eye.