Document Image Cropping via Automatic Boundary Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing systems require users to input document sizes, making them unfriendly for handling documents of various sizes and not supporting non-standard sheet sizes.
Innovation Solution
An image processing apparatus that extracts an object area from a document image, determines a cropping area using pre-stored size information and user-set margins, and crops the image without needing explicit user input on document size, supporting both standard and non-standard sheet sizes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If the user is required to input sheet size information, then the cropping accuracy for standard documents is improved, but the ease of operation deteriorates because users must be familiar with sheet sizes and input information for each document
Solution Approach 1:
The system automatically detects document boundaries and calculates crop boxes without requiring user input. The extraction unit identifies the document region, and the crop box calculation unit computes the cropping area based on detected features, enabling the system to serve itself rather than requiring manual user specification of sheet sizes
Solution Approach 2:
The system performs preliminary detection of document boundaries and characteristics before cropping. By pre-calculating the crop box based on extracted document features and storing size information in advance, the system prepares the cropping parameters beforehand, eliminating the need for real-time user input while maintaining accuracy
2Device complexity
If the system uses pre-stored standard sheet size information, then the cropping process is simplified, but the adaptability deteriorates because non-standard sheet sizes cannot be supported
Solution Approach 1:
The system dynamically adjusts the cropping method based on document characteristics. For standard sizes, it uses pre-stored information for simple processing. For non-standard sizes, it switches to automatic detection and calculation modes, allowing the system to adapt its complexity to match the document type while maintaining ease of use across all scenarios
3Ease of operation
If automatic document size detection is implemented, then the ease of operation is improved, but the measurement precision may deteriorate due to difficulty in accurately detecting document boundaries
Solution Approach 1:
The system introduces intermediate processing steps between image input and cropping. The extraction unit acts as an intermediary that enhances document boundaries through image processing, and the crop box calculation unit serves as another intermediary that refines the cropping area based on enhanced features, thereby maintaining precision while enabling automatic operation
Data Source
AI summary
An object area containing a text or a graphic is extracted from a document image containing the text or the graphic. Then, on the basis of the extracted object area and stored size information, a cropping area is determined that surrounds the object area with given margins. Further, setting of margins is received. Then, on the basis of the object area and the received setting of the margins, the cropping area is determined. Then, the cropping area determined on the basis of the object area and the size information or alternatively the cropping area determined on the basis of the object area and the setting of the margins is cropped from the document image.