Personal Media Broadcaster Attribute Extraction via Banner OCR
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users find it inconvenient and time-consuming to manually determine the attributes of media items accessed via a personal media broadcaster, leading to potential errors in identifying copyrighted content and incorrect metadata entry, which can impact value-added services and unauthorized distribution prevention.
Innovation Solution
A system and method for automatically determining media item attributes by extracting information from banner images using optical character recognition and processing electronic program guide data, closed caption data, and XDS data, which are then used to identify and store the media item's attributes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users manually indicate the identity or attributes of media items, then the process allows user control and verification, but it becomes inconvenient and time-consuming
Solution Approach 1:
The system extracts and determines media item attributes in advance during the clipping process, before the user needs to share or store the media item. The attribute extractor automatically obtains attributes such as title, genre, and synopsis from the media source or metadata, eliminating the need for users to manually enter this information later.
Solution Approach 2:
The system performs self-service by automatically determining its own media item attributes without requiring user intervention. The personal media broadcaster extracts attributes from the media content itself or from associated metadata, allowing the system to serve itself rather than relying on manual user input.
2Reliability
If users manually enter media item attributes, then they can provide accurate information, but users may omit or enter false attributes due to inconvenience
Solution Approach 1:
The system automatically extracts and determines media item attributes without requiring user input, making the process as convenient as simply clipping the media item. The attribute extractor obtains information such as title, genre, and synopsis automatically from the media source or metadata, ensuring both reliability and ease of operation.
Solution Approach 2:
The system introduces an intermediary attribute extractor that bridges the media item and the user, automatically obtaining attributes from the media content or metadata and providing them to the system without requiring direct user input. This intermediary handles the tedious task of attribute determination while ensuring accuracy.
3Productivity
If the system automatically determines attributes, then it reduces manual effort and time, but it requires additional processing steps and complexity
Solution Approach 1:
The system introduces an attribute extractor as an intermediary component that automatically determines media item attributes. This extractor can obtain information from various sources such as metadata, electronic program guide data, or by analyzing the media content itself, providing accurate attributes without requiring complex user input processes.
Solution Approach 2:
The attribute extractor is designed to obtain attributes from multiple sources including metadata, electronic program guide data, and media content analysis, making it a universal solution that can handle different types of media items and sources with a single component rather than requiring separate systems for each source.
Data Source
AI summary
Systems, devices and methods are described for determining attributes identifying media items from other media items. A first video sequence of a first media item is received from a media source, the video sequence including one or more images having first banner information embedded therein. The attributes of the first media item are determined. The determined attributes of the first media item can then be stored or otherwise processed as desired.