Text Rotation Angle Determination via Geometric Ratios

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing Optical Character Recognition (OCR) processes are slow and unsuitable for real-time applications, particularly when determining the rotation angle of text, as they either ignore the angle or require manual user input, which is burdensome for high-volume text processing.

Innovation Solution

An apparatus and method that compute the distance to the closest neighboring object, calculate the average font stroke width, and determine the rotation angle by comparing a ratio of average distances to the threshold value, allowing for automatic and fast estimation of text rotation in images.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional Optical Character Recognition (OCR) processes are used to estimate text rotation angle, then measurement precision of text orientation is achieved, but processing speed deteriorates making it unsuitable for real-time applications

Engineering Contradiction:

Improvetext orientation estimation accuracyVSAvoidprocessing speed

Core Design Contradiction:

Measurement precisionVSSpeed

Solution Approach 1:

The patent extracts only the essential geometric features (bounding box dimensions, distances between adjacent text lines, and distances between adjacent characters) needed for rotation angle estimation, rather than using full OCR processing. This selective extraction of critical geometric parameters enables fast real-time computation while maintaining sufficient accuracy for orientation determination.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of using traditional OCR to determine text orientation, the patent inverts the approach by using geometric relationships between text elements (comparing vertical vs horizontal distances) to estimate rotation angle. This inverted methodology bypasses the computational complexity of full OCR while achieving the orientation estimation goal.

Inventive Principle:

Principle #13The other way round (Inversion)

2Measurement precision

If traditional OCR processes are used for text processing, then text orientation can be determined, but productivity deteriorates due to slow processing of high-volume text

Engineering Contradiction:

Improvetext angle determinationVSAvoidtext processing throughput

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent changes the computational parameters from full OCR analysis to simple geometric measurements (comparing ratios of distances and bounding box dimensions). This parameter transformation enables rapid processing of high-volume text while maintaining the ability to determine text orientation accurately.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If manual user input is requested for text rotation angle, then measurement precision can be maintained, but ease of operation deteriorates making it burdensome for users

Engineering Contradiction:

Improvetext rotation angle accuracyVSAvoiduser input requirement

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent implements self-service by automatically calculating text rotation angle using geometric relationships between text elements. The system performs the orientation estimation autonomously by comparing distances between adjacent text lines and characters, eliminating the need for manual user input while maintaining accurate angle determination.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical input process with an automated computational system. Instead of requiring users to manually specify rotation angles, the system uses geometric analysis of text element positions to automatically determine the orientation, substituting human operation with algorithmic processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS9552527B1Apparatus, method, and computer-readable storage medium for determining a rotation angle of text

Publication Date: 2017.01.24 APRYSE SOFTWARE CORP

AI summary

An apparatus, method, and computer-readable storage medium for determining a rotation angle of text. The method includes computing, for each object of a plurality of objects included in text within an image, a distance to a closest neighboring object, computing an average distance of the distances to the closest neighboring objects, determining a ratio between the average distance and an average font stroke width, the average font stroke width being an average of a font stroke width of each of the plurality of objects, and determining a rotation angle of the text by comparing the ratio to a threshold value.