Document Image Orientation Correction for Accurate OCR
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods lack the ability to accurately identify and rectify the orientation of document images, leading to reduced accuracy in Optical Character Recognition (OCR) when documents are scanned in rotated orientations.
Innovation Solution
A method and system that utilize a computing device to detect regions in a document image, determine their positional information, and analyze the ratio of region orientations to correct the page orientation by rotating the image if necessary, based on OCR accuracy comparisons.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If OCR is performed on rotated document images, then text extraction can be attempted, but the accuracy of text recognition deteriorates significantly
Solution Approach 1:
The patent applies preliminary action by detecting the orientation of text regions in the document image before performing OCR. The system analyzes the aspect ratios of detected text regions to determine if they are rotated (width > 3×height indicating 90° rotation), and rotates the image to the correct orientation before OCR processing, thereby ensuring high accuracy text recognition
2Ease of operation
If conventional OCR methods are used on images with incorrect orientation, then processing can proceed, but the quality of recognized text deteriorates
Solution Approach 1:
The system performs preliminary orientation detection and correction by analyzing text region aspect ratios before OCR processing. This preliminary action ensures that the image is in the correct orientation, thereby maintaining high text recognition quality while keeping the overall process automated and simple to operate
3Device complexity
If no orientation detection mechanism is implemented, then the processing workflow remains simple, but the ability to handle rotated documents deteriorates
Solution Approach 1:
The patent applies self-service by implementing an automated orientation detection and correction mechanism that automatically analyzes text region aspect ratios, determines rotation status, and rotates the image as needed before OCR processing. This self-service approach enhances adaptability to handle rotated documents while maintaining workflow simplicity through automation
Data Source
AI summary
This disclosure relates to method and system for detecting orientation. The method includes detecting a plurality of regions in a document image, each region including text data, and determining positional information of each of the regions; for each of the plurality of regions, determining a region orientation to be one of first orientation or second orientation based on height and width of the region; determining a ratio of number of regions having first orientation and number of regions having second orientation; determining page orientation of the image as third orientation or second orientation, or rotating the image by 90° in counter-clockwise direction based on the ratio; determining first optical character recognition (OCR) data and second OCR data corresponding to the image and the image rotated by 180°, respectively; and determining number of correct words in first OCR data and second OCR data based on comparison with dictionary data.