Image Quality Evaluation for Continuous Shooting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile devices with continuous-shooting functions lack the ability to evaluate and recommend high-quality images from multiple shots taken, especially when the subject is not a person, due to limited display screens and restricted evaluation methods using single criteria like face detection, which fail to assess image quality comprehensively.
Innovation Solution
An electronic device and method that evaluates images using face region evaluation scores and clarity evaluation scores, considering factors like red eye, facial expression, and image clarity, to recommend high-quality images, even when the subject is not a person, by detecting face regions and assigning weights to different image regions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If single criteria like face detection is used for image evaluation, then the evaluation process is simple, but the image quality assessment is insufficient especially when the subject is not a person
Solution Approach 1:
The patent changes the evaluation parameters from single-criteria face detection to multi-criteria assessment including face region evaluation score, clarity evaluation score, and overall image quality score. This allows comprehensive image quality assessment across different subject types while maintaining systematic evaluation process
Solution Approach 2:
The evaluation system is designed to be universal by handling both human subjects (using face detection and expression analysis) and non-human subjects (using clarity and overall quality assessment). The multi-functional evaluation framework adapts to different subject types without requiring completely different evaluation methods
2Measurement precision
If multiple evaluation elements are used to assess image quality, then the image quality assessment becomes comprehensive, but the processing complexity increases
Solution Approach 1:
The patent segments the image evaluation process into distinct modules: face region detection, face region evaluation (for facial expressions, eye blinking, mouth opening), clarity evaluation (for overall image sharpness and focus), and overall image quality assessment. Each module independently evaluates specific aspects and contributes to the final comprehensive score, making the complex process manageable and systematic
3Measurement precision
If comprehensive image evaluation is performed on all continuous shots, then the recommendation accuracy improves, but the processing time increases
Solution Approach 1:
The patent performs preliminary face region detection and evaluation on each continuously captured image immediately after capture. By pre-processing and evaluating each image's face region characteristics (facial expressions, eye blinking, mouth opening) and clarity metrics in real-time during the shooting sequence, the system prepares evaluation data beforehand, enabling faster final selection and recommendation without requiring post-processing of all images
Solution Approach 2:
The patent replaces manual image selection with an automated electronic evaluation and selection system. The processor automatically calculates face region evaluation scores, clarity scores, and overall image quality scores for each captured image, then selects the highest-quality image without human intervention, significantly reducing the time required compared to manual review
Data Source
AI summary
An electronic device is disclosed. The electronic device includes an image capturing unit configured to obtain a plurality of images upon receiving one or more user inputs, a processor configured to process one or more of the plurality of images, and a display configured to display the one or more of the plurality of images, where the processor is further configured to select at least one image from the plurality of images, based on a facial expression of one or more objects recognized on the one or more of the plurality of images and a clarity of at least a portion of the one or more of the plurality of images.