Electronic Apparatus Content Identification via Audio Video Fingerprinting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face difficulties in accurately identifying and specifying game content being displayed, as they rely on comparing frames stored in a database, which is ineffective due to varying play images resulting from user manipulation.
Innovation Solution
An electronic apparatus and method that captures video and audio feature information at regular intervals, transmitting this information to a server for comparison with stored data to identify the content, using video and audio fingerprints to distinguish and identify the content, and adjust settings such as enabling automatic low-latency mode for game content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If frame comparison method is used to identify content, then identification can be achieved for continuous frame content like movies, but it fails to accurately identify game content with varying play images
Solution Approach 1:
The patent applies universality by creating a content identification system that works for both continuous frame content (movies, dramas) and variable frame content (games). The system extracts feature information from video and audio signals that can represent both types of content, making the identification method universally applicable across different content formats rather than being limited to specific content types.
Solution Approach 2:
The patent changes the identification parameters from static frame comparison to dynamic feature information extraction. By extracting temporal and spectral features from audio signals and spatial-temporal features from video signals, the system adapts to content that changes over time, such as games with varying play images, while maintaining accuracy for continuous frame content.
2Measurement precision
If multiple features are extracted and analyzed to improve identification accuracy, then content recognition becomes more precise, but system complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the content identification process into distinct modules: video signal processing module, audio signal processing module, feature information extraction module, and identification module. Each module handles specific tasks independently, making the complex system more manageable and easier to implement while maintaining high identification accuracy through coordinated operation of these segmented components.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An electronic apparatus includes a communication interface, a display, and a processor configured to, based on a content being received from a source apparatus via the communication interface, obtain feature information of the received content, and transmit the obtained feature information to an external server, receive, from the external server, identification information of the content, the identification information being obtained based on the transmitted feature information, based on a predetermined mode of the display being turned on according to a signal that is received from the source apparatus via the communication interface, obtain information regarding a first time point when the predetermined mode is turned on, and based on the predetermined mode of the display being turned off, obtain information regarding a second time point when the predetermined mode is turned off after the first time point.