Image Recognition Commodity Data Extraction Mobile Ordering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face difficulty in efficiently searching and ordering commodities due to the need to manually search and image multiple items from catalogs, which is time-consuming and effort-intensive.
Innovation Solution
An information processing device that acquires video data of multiple items, recognizes pre-registered images, extracts and displays corresponding appended data, and presents it in a mobile terminal, improving visibility and accessibility of commodity information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If users manually search and image multiple items from catalogs, then commodity information can be retrieved, but the process becomes time-consuming and effort-intensive
Solution Approach 1:
The patent replaces manual mechanical operations (searching, capturing images) with automated image recognition technology. The terminal device automatically recognizes multiple commodity images from a single captured image, extracts commodity information, and presents it to the user, eliminating the need for manual searching and multiple image captures.
Solution Approach 2:
The system performs preliminary actions by pre-storing commodity template images and their associated information in the terminal device. When a user captures an image, the system immediately compares it against the pre-stored templates to rapidly identify and retrieve commodity information, significantly reducing the time required for information retrieval.
2Loss of information
If a terminal device displays multiple commodity images and their information, then information visibility is improved, but the terminal screen space becomes insufficient
Solution Approach 1:
The patent extracts and displays only the most relevant commodity information (such as commodity names, prices, and key attributes) while keeping the full image visible in the background. This selective extraction of information allows the system to present essential details without completely obscuring the visual content, optimizing the use of limited screen space.
Solution Approach 2:
The system overlays commodity information in a multi-dimensional layout on the terminal screen, using different spatial zones and transparency levels to display multiple pieces of information simultaneously. This allows comprehensive information presentation while maintaining image visibility and efficient use of the two-dimensional screen space.
Data Source
AI summary
This information processing device (100) comprises: a video data acquisition unit (102) that sequentially acquires video data resulting from at least a portion of an imaging subject presenting a plurality of items being imaged by an imaging unit; an image recognition unit (104) that detects that at least a portion of a pre-registered image is contained in the video data, and recognizes the image; an appended data extraction unit (108) that extracts the respective appended data of each image from an appended data storage unit (106) that stores appended data corresponding to each of a plurality of recognized images; and an appended data display unit (110) that displays the extracted appended data of each image.