Reference-Feature Image Cropping for Difficult Document Edge Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing document detection techniques often fail to accurately identify the edges of documents in images, particularly when they are part of a book or booklet, or when the background has a similar intensity, leading to inefficient use of processing and network resources.
Innovation Solution
An image processing device uses a reference feature associated with predefined location parameters to detect the edges of a document by expanding a bounding box around the reference feature, allowing for accurate cropping without relying on contour-based edge detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If contour-based edge detection is used to identify document edges, then the detection process can be performed, but the detection accuracy deteriorates when documents are part of a book or when the background has similar intensity
Solution Approach 1:
The patent introduces a reference feature as an intermediary element to facilitate document edge detection. Instead of directly detecting document edges which is unreliable in certain conditions, the system detects a known reference feature within the document and uses it as a mediator to infer document boundaries through predefined spatial relationships, thereby achieving accurate detection without direct edge analysis
Solution Approach 2:
The patent applies preliminary action by detecting and localizing the reference feature before attempting to determine document edges. The reference feature detection is performed first using its known characteristics, and its detected position is then used as a basis for calculating document boundaries, ensuring reliable detection even when direct edge detection would fail
2Measurement precision
If additional image captures are performed to improve detection accuracy, then detection precision may improve, but processing and network resources are consumed
Solution Approach 1:
The patent enables the system to achieve accurate document detection using only the information already present in the captured image through reference feature analysis. The reference feature provides self-sufficient information about document location and boundaries, eliminating the need for additional image captures or external resources, thereby achieving precise detection without increased energy consumption
Data Source
AI summary
In some implementations, a device may receive the image of the document, the image of the document depicting the reference feature, and the reference feature being associated with one or more location parameters for a document type associated with the document. The device may detect a location of the reference feature as depicted in the image, the location being defined by bounds of the reference feature as depicted in the image. The device may detect a border of the document as depicted in the image based on identifying one or more edges of the document based on the bounds of the reference feature and the one or more location parameters. The device may modify the image of the document based on the border of the document to obtain a cropped image. The device may transmit, to a server device, the cropped image.