Document Image Orientation Detection via Pixel Run Histograms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing OCR technologies are resource-intensive and inefficient in determining page orientation of distorted document images, as they require character recognition and analysis to correct perspective, which is time-consuming and costly.
Innovation Solution
A method that identifies the orientation of rows of text in a document image by analyzing histograms of horizontal and vertical runs of white pixels, without relying on OCR processing, by using a computing device to binarize the image, identify text areas, and calculate area ratios to determine orientation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If OCR processing with document analysis is used to determine page orientation, then the orientation can be identified based on recognized characters, but the process becomes resource-intensive and time-consuming
Solution Approach 1:
The patent extracts only the essential information needed for orientation determination (horizontal and vertical run lengths of white pixels) from the document image, rather than performing complete OCR processing. By taking out only the necessary features (pixel run histograms) and discarding the rest of the complex character recognition process, the system achieves orientation determination with much lower resource consumption while maintaining sufficient accuracy
Solution Approach 2:
Instead of using OCR to recognize characters and then determining orientation from recognized text, the patent inverts the approach by directly analyzing the visual pattern of white pixel runs in the image to determine orientation. This inversion eliminates the need for full OCR processing while still achieving the orientation determination goal
2Measurement precision
If complete OCR processing is performed to identify character orientation, then accurate text orientation can be determined, but processing time increases significantly
Solution Approach 1:
The patent extracts only the essential information needed for orientation determination (horizontal and vertical run lengths of white pixels) from the document image, rather than performing complete OCR processing. By taking out only the necessary features (pixel run histograms) and discarding the rest of the complex character recognition process, the system achieves orientation determination with much lower resource consumption and processing time
Solution Approach 2:
The patent performs partial OCR processing - only enough to generate histograms of pixel run lengths - rather than complete OCR processing that would recognize and analyze every character. This partial action is sufficient for orientation determination while avoiding the time cost of full processing
Data Source
AI summary
A page orientation component of an image processing device receives an image of a document, transforms the image to a binarized image by performing a binarization operation on the image, and identifies a portion of the binarized image that comprises one or more rows of textual content. The page orientation component identifies a plurality of horizontal runs of white pixels and a plurality of vertical runs of white pixels in the one or more rows of textual content in the portion of the binarized image. The page orientation component generates a first histogram for the plurality of horizontal runs of white pixels, and a second histogram for the plurality of vertical runs of white pixels, and determines an orientation of the one or more rows of textual content in the image based on the first histogram and the second histogram.