Video Object Recognition and Online Information Linking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current consumer electronics devices lack the capability to seamlessly link touch-sensitive displays and face/image recognition software with online stores or websites, preventing users from easily accessing additional information about selected video objects, such as people or products, during video playback.
Innovation Solution
A consumer electronics device with a processor that controls a display and network interface, enabling image recognition to identify objects within a selected area, correlating this information with basic details and presenting options for further research or purchase through a user interface, directly connecting the device to the internet for search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Difficulty of detecting and measuring
If touch sensitive displays and face/image recognition software are used independently, then object identification capability is improved, but the ability to access online information about identified objects remains unavailable
Solution Approach 1:
The patent combines touch-sensitive display technology, face/image recognition software, and online information access capabilities into a unified system. The recognition engine identifies objects in video frames, the touch display allows users to select areas of interest, and the network interface enables direct access to online stores and websites, creating an integrated solution that resolves the fragmentation between these separate technologies
Solution Approach 2:
The processor acts as an intermediary that receives input from the touch display, processes images through the recognition engine, and mediates the connection to online resources. This intermediary component coordinates the flow of information between the display, recognition system, and network, enabling seamless transitions between local video viewing and online information access
2Loss of information
If users manually search for information about video objects using traditional methods, then information accuracy is improved, but time consumption and operational complexity increase
Solution Approach 1:
The system performs preliminary actions by automatically recognizing and identifying objects in the video before the user needs information about them. The recognition engine continuously analyzes video frames, and when an object is identified, the system proactively presents relevant information or search options, eliminating the need for users to manually search through multiple sources
Solution Approach 2:
The system provides feedback by presenting basic information about identified objects directly on the display, allowing users to verify accuracy and access additional details. This feedback loop enables users to quickly confirm object identification and proceed to more detailed information or purchases without time-consuming manual searches
3Ease of operation
If basic object information is displayed immediately, then ease of access to information is improved, but the ability to provide customized search results deteriorates
Solution Approach 1:
The information presentation is segmented into multiple levels: basic information is displayed immediately for quick access, while additional customized information can be accessed through user interface elements. This segmentation allows the system to provide simple, immediate feedback while maintaining the capability to deliver tailored search results when requested
Solution Approach 2:
The user interface dynamically adapts based on user interactions. The system presents basic information by default but can transition to more customized search options when users interact with UI elements. This dynamic behavior allows the system to maintain ease of access while providing versatility based on user needs
Data Source
AI summary
The user of an Internet-enabled CE device such as a TV can select an object in a video presented on the display of the CE device by either touch sensitive screen or input device. The processor of the CE device can then determine the boundaries of the object, identify it using face/image recognition software, search for information/websites related to the object, and present those information/websites to the viewer on the display screen.