Mobile Terminal Face Recognition Region Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing display devices face issues with incorrect user input execution due to misrecognition of user motions or voices, leading to inconvenient repeated operations and unintentional function activation, especially when motion recognition technologies are applied, making it difficult to select appropriate commands.
Innovation Solution
A display apparatus with a recognition unit that includes face, gaze, and voice recognition capabilities, utilizing distinct interactive modes and regions on the display to accurately determine user intentions, such as motion, voice, or gaze recognition, to execute commands intuitively and correctly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If motion recognition technology is applied to enable intuitive user interaction, then user convenience is improved, but the risk of incorrect input execution and unintentional function activation increases
Solution Approach 1:
The patent combines multiple recognition technologies (motion recognition, voice recognition, and gaze recognition) into a unified recognition unit. This fusion allows the system to cross-validate inputs and distinguish between intentional commands and unintentional motions, thereby maintaining ease of operation while improving input accuracy and reducing incorrect executions.
Solution Approach 2:
The system implements a feedback mechanism where the recognition unit processes multiple types of input signals and provides confirmation or correction capabilities. When a motion is detected, the system can verify it through additional sensors (voice, gaze) before execution, allowing users to correct misrecognized inputs and preventing unintentional activations.
2Measurement precision
If multiple recognition technologies are integrated to improve command accuracy, then input precision is improved, but device complexity increases
Solution Approach 1:
The recognition unit is designed as a multi-functional module that handles motion recognition, voice recognition, and gaze recognition through a unified architecture. This universal design allows the system to process multiple types of inputs without requiring separate complex processing systems for each technology, thereby improving command accuracy while controlling overall device complexity.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
A mobile communication terminal has a front side with a first region where an image is displayable and a second region where an image is not displayable. The terminal further comprises a display panel (111) to display an image in the first region; an image collection unit (220) provided at the second region; a cover (121) protecting the display panel, a controller (134), between the display panel and the cover, configured to determine whether a face of a user of the mobile communication terminal is within a predetermined recognition region of the image collection unit, and in response to determining that the face of the user of the mobile communication terminal is within the predetermined recognition region, recognize the face of the user, and in response to recognizing the face of the user, control operations of the mobile communication terminal.