Digital Flyer Price Region Detection With Two-Color Text
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods struggle to efficiently extract price information from digital flyers due to their complex formats, color schemes, font styles, and random text placements, making manual extraction cumbersome and automated extraction ineffective.
Innovation Solution
A system and method that converts text regions into two-color images, uses bounding boxes to detect and merge adjacent text regions, and employs a price tag flag status and extraction technique to accurately identify and extract price regions from digital flyers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional methods are used to extract price information from digital flyers, then the extraction process can be performed, but the accuracy is insufficient due to complex formats, color schemes, font styles, and random text placements
Solution Approach 1:
The patent segments the price extraction process into distinct modules: text region detection, two-color conversion, price region detection, and price extraction. Each module handles a specific aspect of the complex extraction task, improving accuracy while managing system complexity through functional decomposition
Solution Approach 2:
The patent transforms the input image through parameter changes: converting to grayscale, applying histogram analysis to identify two dominant colors, and converting to a two-color binary image. These parameter transformations simplify the complex visual information into a format where price regions can be detected with higher accuracy
2Measurement precision
If manual extraction of price information is performed, then accurate price data can be obtained, but the process is cumbersome and time-consuming
Solution Approach 1:
The system performs self-service automated extraction using algorithms that automatically detect text regions, convert images to two-color format, identify price regions, and extract price information without manual intervention, achieving both high accuracy and high productivity
Solution Approach 2:
The patent replaces the mechanical manual extraction process with an automated computational system that uses image processing algorithms, histogram analysis, and connected component analysis to automatically identify and extract price information, dramatically improving extraction speed while maintaining accuracy
3Productivity
If automated extraction methods are implemented, then extraction speed is improved, but the methods fail to handle complex flyer formats, color schemes, and text placements effectively
Solution Approach 1:
The patent performs preliminary actions by first detecting text regions and converting the image to a two-color binary format before attempting price region detection. This preliminary processing simplifies the subsequent price extraction task and ensures high accuracy even when processing speed is prioritized
Solution Approach 2:
The system applies parameter changes by transforming the complex color and font information into a simplified two-color binary representation, where price regions can be reliably identified through connected component analysis, maintaining both speed and accuracy
4Measurement precision
If the system processes all text regions in detail, then extraction accuracy is improved, but the processing time and computational resources increase
Solution Approach 1:
The patent extracts only the price-related information from the flyer by using price region detection algorithms that identify and isolate price text from other content. This selective extraction approach maintains high accuracy while minimizing processing time by avoiding detailed analysis of non-price text regions
Solution Approach 2:
The system applies partial action by focusing computational resources only on regions identified as potential price regions, rather than processing the entire flyer uniformly. This approach achieves high accuracy for price detection while reducing overall processing time
Data Source
AI summary
This disclosure relates generally to method and system for detecting and extracting price region from digital flyers and promotions. In retail business, extracting price information from digital flyers is crucial for complex nature of flyers having large variety of formats, color scheme, font styles, variable text information and thereof. The method of the present disclosure detects a text region comprising a price information from a set of digital flyers and promotions received as input images. Further, each text region is converted into a two-color text comprising of a set of white pixels and a set of black pixels. Further, underlying price from the price region of the two-color text is detected and price is extracted from the price region of each input image. Additionally, the price region detection function detects price region accurately and extracts price values having an irregular font size.