Contextual Image Text Lookup for More Relevant Search Results
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional search engines fail to provide relevant search results when looking up text from images due to a lack of contextual information, often returning unrelated results when the text is not specific enough.
Innovation Solution
The technology enhances search results by using contextual information derived from the image, such as additional text, object types, application information, location, and depth information, to improve the relevance of search outcomes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional search engines perform text lookup using only the extracted text from images, then the search process is simple and fast, but the search results are not relevant when the text is not specific enough
Solution Approach 1:
The patent segments the search process into multiple components: text extraction from image, contextual information extraction (objects, attributes, relationships), and multi-factor search query construction. This segmentation allows the system to handle complexity in a structured way while improving search relevance through comprehensive analysis of multiple image elements
Solution Approach 2:
The patent merges multiple types of information (extracted text, detected objects, image attributes, and contextual relationships) into a unified search query. This combination of diverse data sources enhances search result relevance by providing the search engine with rich contextual information beyond just the text string
2Reliability
If the search system incorporates contextual information from the image, then the search results become more relevant, but the processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary actions by extracting and analyzing contextual information from the image before initiating the search process. Objects, attributes, and relationships are identified and stored in advance, so when a text lookup is requested, the system can immediately combine this pre-processed contextual data with the search query, reducing actual search processing time
Solution Approach 2:
The system selectively applies contextual analysis based on the specific image and search needs. Not all image elements are processed with the same depth - the system performs partial analysis focusing on the most relevant contextual elements, balancing processing effort with search result quality
Data Source
AI summary
The subject technology provides for contextual text lookup for images. When a request is received by an electronic device to perform a lookup or search for text in an image that is displayed at the electronic device, the electronic device may obtain one or more search results, based on the text itself and based on contextual information derived, by the electronic device, from the image. In one or more implementations, application information associated with an application that displays the image may also be used as contextual metadata for enhancing the results of the search for the text from the image.