Object Detection in Electronic Devices Using Optical Feature Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image capturing systems, such as digital cameras, face challenges in accurately detecting faces in specific functions like the smile shutter function, especially when faces are partially obscured or three-dimensionally formed, leading to lowered object detection accuracy and unintended photographing.
Innovation Solution
An electronic device with a detection unit, evaluation unit, and control unit that uses a learning model to differentiate between intended and unintended objects by evaluating feature values such as gloss of hair, shade of a face, and brightness of a pupil, and excludes objects not meeting predetermined criteria from the specific function's execution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If face detection is performed based on area and distance alone, then detection simplicity is maintained, but detection accuracy deteriorates when faces are planar or three-dimensionally formed
Solution Approach 1:
The patent introduces new evaluation parameters (gloss of hair, shade of face, brightness of pupil) to complement the existing area and distance parameters. This multi-parameter evaluation approach resolves the contradiction by maintaining the simplicity of automated detection while significantly improving accuracy in distinguishing real faces from planar or three-dimensional representations.
Solution Approach 2:
The patent replaces simple geometric detection (area and distance measurements) with a more sophisticated evaluation system that analyzes optical properties (gloss, shade, brightness). This substitution transforms the detection mechanism from basic spatial measurement to optical characteristic analysis, improving accuracy without substantially increasing system complexity.
2Speed
If automated object detection is performed without additional evaluation, then processing speed is maintained, but object identification accuracy deteriorates
Solution Approach 1:
The patent performs preliminary detection using simple criteria (area and distance) to identify candidate objects, then applies additional evaluation (gloss, shade, brightness) only to these candidates. This two-stage approach maintains processing speed by avoiding full evaluation of all objects while improving identification accuracy through targeted additional analysis.
Solution Approach 2:
The patent segments the detection process into two distinct stages: initial detection based on area and distance, and subsequent evaluation based on optical properties. This segmentation allows the system to maintain speed through efficient preliminary filtering while achieving high accuracy through focused detailed evaluation of promising candidates.
3Device complexity
If simple detection criteria are used, then system complexity is reduced, but detection reliability deteriorates in challenging scenarios
Solution Approach 1:
The patent enhances detection reliability by introducing optical property parameters (gloss of hair, shade of face, brightness of pupil) that provide robust discrimination between real faces and representations. These additional parameters create multiple independent verification points, significantly improving reliability without requiring complex system architecture.
Solution Approach 2:
The patent introduces an intermediate evaluation layer that assesses optical properties between the simple initial detection and the final identification decision. This intermediary evaluation acts as a reliable filter that validates detections without requiring the full complexity of advanced recognition systems, thereby improving reliability while controlling overall system complexity.
Data Source
AI summary
An electronic device that is improved in object detection performance exhibited when executing a specific function. A system controller detects one or more objects from image data, evaluates feature values of the one or more detected objects, and identifies an object out of the one or more objects, that satisfies a predetermined criterion related to execution of a specific function, based on a result of the evaluation. The specific function is executed in a case where it is determined that the identified object satisfies an execution condition of the specific function.