Image Orientation Definition Using User Facial Proxy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Portable electronic devices, such as smartphones and tablets, face challenges in accurately determining the orientation of images when scanning documents, especially when held horizontally, as existing orientation sensors fail to detect the device's orientation relative to the document, leading to incorrect image rotation and user frustration.
Innovation Solution
The method involves capturing an image of the user with a second image capture device on the electronic device, determining the user's image orientation, and using this information to define the image orientation of the scanned object, thereby ensuring proper image orientation without relying on text detection or multiple language programming, and working effectively with documents containing little or no text.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional orientation sensors (accelerometer, gyroscope) are used to determine device orientation, then the device can detect its spatial orientation, but it fails to accurately determine the orientation of the document relative to the device when held horizontally
Solution Approach 1:
The patent introduces an intermediary approach by capturing an image of the user's face and using facial feature orientation (eyes, nose, mouth alignment) as a mediator to infer document orientation. This intermediary facial orientation serves as a proxy that bridges the gap between device orientation sensing and actual document orientation, especially in horizontal positioning where traditional sensors fail.
2Measurement precision
If text detection methods are used to determine document orientation, then orientation can be accurately determined for documents with text, but it becomes computationally intensive and fails for documents with little or no text
Solution Approach 1:
The patent creates a copy of the user's face in the captured image and analyzes the orientation of facial features (eyes, nose, mouth) to determine orientation. This copying approach replaces the need for text detection on the document itself, providing a lighter computational path that works for all document types including those without text, while maintaining accurate orientation determination.
3Reliability
If the device captures an image of the user's face to determine orientation, then accurate orientation can be determined for horizontal positions, but an additional image capture device and processing step are required
Solution Approach 1:
The patent makes the front-facing camera serve multiple functions: it captures user images for authentication purposes and simultaneously captures facial orientation data for determining document orientation. This multi-functionality approach increases reliability for horizontal orientation detection without requiring a separate dedicated camera, as the same camera performs both authentication and orientation sensing.
Data Source
AI summary
An electronic device includes a device housing having a front side and a rear side, a first image capture device positioned on the front side, and a second image capture device positioned on the rear side. One or more processors of the electronic device cause, in response to user input received at a user interface requesting the second image capture device capture an image of an object, the first image capture device to capture another image of a user delivering the user input. The one or more processors then define an image orientation of the image of the object to be the same as another image orientation of the other image of the user.