Multi-Angle Camera Screen-Type Detection for Contextual Image Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic apparatuses struggle to accurately determine the type of screen in an image due to limited angle of view and difficulty in recognizing multiple objects, often providing inappropriate filters or failing to provide any filters, leading to misrecognition and suboptimal image correction.
Innovation Solution
The electronic apparatus employs multiple lenses with different angles of view, utilizing neural network models to analyze depth maps, saliency information, and object relationships to identify the screen type accurately and apply corresponding filters for image correction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single lens is used to capture the image, then the device complexity is reduced, but the measurement precision of screen type identification deteriorates due to limited angle of view
Solution Approach 1:
The camera system is segmented into multiple lenses with different angles of view (first lens with narrower angle, second lens with wider angle). Each lens captures images of different fields of view, allowing the system to analyze both detailed and contextual information for accurate screen type identification.
Solution Approach 2:
The system adds a spatial dimension by incorporating multiple lenses with different angles of view. This allows simultaneous capture of narrow-angle detailed views and wide-angle contextual views, providing multi-dimensional information for more accurate screen type determination.
2Loss of information
If multiple objects are included in the captured image, then the scene context is improved, but the reliability of screen type determination deteriorates due to difficulty in identifying the main subject
Solution Approach 1:
The system applies different processing qualities to different regions of the image. The narrow-angle image provides detailed local information about the main subject, while the wide-angle image provides contextual information about the surrounding environment. By weighting and combining these differently, the system reliably identifies screen type even when multiple objects are present.
Solution Approach 2:
The processor acts as an intermediary that analyzes both narrow-angle and wide-angle images, using neural network models to determine saliency and segment objects. It combines the detailed subject information from the narrow-angle view with the contextual information from the wide-angle view to reliably identify the screen type.
3Device complexity
If a narrow area is used for image capturing, then the device simplicity is maintained, but the productivity of screen type identification deteriorates due to limited angle of view
Solution Approach 1:
The system performs preliminary action by capturing both narrow-angle and wide-angle images simultaneously before screen type identification. This allows the neural network models to process both detailed and contextual information in advance, improving the speed and accuracy of subsequent screen type determination.
Solution Approach 2:
The system merges the information from narrow-angle and wide-angle images through neural network processing. By combining the detailed subject information with the contextual background information, the system achieves faster and more accurate screen type identification than would be possible with a single lens.
Data Source
AI summary
An electronic apparatus includes a camera including a first lens and a second lens capable of obtaining an image having an angle of view different from the first lens, a display, a memory, and a processor. To perform a controlling method, the processor is configured to provide a first image obtained using the first lens to the display as a live view, obtain a second image using the second lens, obtain image information regarding the second image and object information regarding at least one object depicted in the second image using at least one neural network model, identify a screen type of the second image based on the image information and the object information, identify a set of filters corresponding to the screen type of the second image, and correct the first image based on the identified set of filters to provide a corrected first image as the live view.