Bill Identification via Boundary Line Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies can only identify one bill at a time, making it inefficient for processing multiple bills in an image, which is a common scenario in financial and accounting tasks.
Innovation Solution
A method and device that acquire an image containing multiple bills, process it to obtain boundary lines perpendicular to the bill arrangement direction, generate a long line segment parallel to the bill arrangement direction, and determine the number of bills based on sub-line segment lengths between intersection points, allowing for simultaneous identification of multiple bills.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple bills are collected in a single image to save time and effort, then processing efficiency is improved, but the ability to identify the number of bills and separate bill areas becomes insufficient in existing technology
Solution Approach 1:
The patent applies segmentation by dividing the image processing task into distinct stages: first identifying approximate bill areas using machine vision algorithms, then refining boundary detection through edge detection and line segment analysis. This multi-stage segmentation approach enables accurate identification of multiple bills within a single image, resolving the contradiction between processing efficiency and identification precision.
2Measurement precision
If separate images are collected for each bill to ensure accurate identification, then identification accuracy is maintained, but time and effort are significantly increased
Solution Approach 1:
The patent merges multiple bill identification tasks into a single image processing operation. By developing algorithms that can detect and separate multiple bill areas within one image, the system maintains high identification accuracy while eliminating the need to collect and process separate images for each bill, thus significantly reducing time loss.
Solution Approach 2:
The patent performs preliminary action by first identifying approximate bill areas and generating candidate regions before final identification. This preliminary segmentation and boundary detection prepare the data structure in advance, enabling efficient and accurate identification of multiple bills in a single processing pass, thereby saving time compared to sequential processing of individual bills.
3Measurement precision
If existing bill identification technology is used, then single bill identification is accurate, but it cannot handle multiple bills simultaneously requiring multiple separate operations
Solution Approach 1:
The patent enhances universality by developing a multi-functional bill identification system that can handle both single bill and multiple bill scenarios within the same image processing framework. The system automatically adapts to detect the number of bills present and applies appropriate processing strategies, making it versatile for various billing scenarios without requiring separate specialized systems.
Data Source
AI summary
The invention provides a method and a device for identifying the number of bills and multiple bill areas in an image. The method comprises the following steps: acquiring the image containing a plurality of bills arranged in sequence; processing the image to obtain a plurality of boundary lines of each bill in the image; wherein the boundary lines comprise a first type of boundary lines which are substantially perpendicular to the bill arrangement direction; generating a long line segment which is substantially parallel to the arrangement direction of the bills and passes through the area where all the bills are located, wherein the long line segment has an intersection point with each first type of boundary line; and determining the number of bills in the image according to the lengths of the sub-line segments between the adjacent intersection points.