Face Detection Unit Dynamic Range Switching for Power and Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Electronic apparatuses in public places face challenges in accurately detecting the presence of the intended user while minimizing power consumption and preventing accidental activation by non-users, as well as reducing the risk of peeping through face detection.
Innovation Solution
The apparatus employs a face detection unit that switches between full and half detection ranges based on the operating state, stopping face orientation detection in standby mode and reducing display brightness when a side profile is detected, to conserve power and prevent false activations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If face detection is performed with high detection performance to detect peeping by other persons, then detection accuracy is improved, but power consumption increases
Solution Approach 1:
The patent applies dynamics by switching between two detection modes (first mode with full detection range and orientation detection, second mode with limited detection range and no orientation detection) based on the current operating state. This dynamic adjustment allows the system to optimize power consumption while maintaining detection accuracy when needed.
Solution Approach 2:
The patent changes detection parameters (detection range and orientation detection) based on operating state. In the first operating state, the system performs comprehensive face detection with orientation analysis, while in the second operating state, it performs only basic face detection without orientation analysis, thereby reducing power consumption.
2Measurement precision
If face detection is performed in public places to detect user presence, then user detection accuracy is improved, but false detection by non-users increases
Solution Approach 1:
The system dynamically adjusts detection behavior based on operating state. When in the second operating state (lower power mode), the detection range is limited and orientation detection is disabled, reducing the likelihood of false detection by non-users while maintaining sufficient user detection capability.
Solution Approach 2:
The patent applies local quality by performing different levels of detection analysis on different regions or contexts. In the second operating state, the system performs only basic face detection without orientation analysis, creating a localized reduction in detection complexity that prevents false positives while maintaining user detection.
3Measurement precision
If comprehensive face detection including orientation is performed, then detection performance is improved, but system complexity increases
Solution Approach 1:
The system dynamically switches between comprehensive detection (first mode with orientation detection) and simplified detection (second mode without orientation detection) based on operating state, managing system complexity adaptively rather than maintaining fixed high complexity throughout.
Solution Approach 2:
The patent applies partial action by performing only the necessary level of detection analysis for each operating state. In the second operating state, orientation detection is omitted when full detection performance is not required, reducing system complexity while maintaining sufficient detection capability for basic user presence detection.
Data Source
AI summary
An electronic apparatus includes a processing unit, a memory, a processor, and an operation control unit. The processing unit executes system processing based on a system. The memory temporarily stores image data of an image captured by an imaging device. The processor processes image data stored in the memory. The operation control unit controls an operating state of the system. The processor includes a face detection unit that processes image data of an image obtained by the imaging device capturing a predetermined imaging range and stored in the memory to perform detection of a face area with a face captured therein and an orientation of the face from the image. The operation control unit controls, according to a detection result by the face detection unit, the operating state of the system to be a first operating state or a second operating state.