Mixed Western Hieroglyphic Text Line Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Optical character recognition (OCR) systems face challenges in recognizing and segmenting textual lines that contain a mix of Western and East Asian or hieroglyphic text, as they struggle to accurately identify inter-character breaks and separate Western and East Asian text fragments.
Innovation Solution
An image processing apparatus is developed that identifies candidate inter-character breaks, classifies them using geometrical properties and character bounding boxes, and employs a feature set like Gabor features for character recognition, while segmenting textual lines into Western and hieroglyphic text segments using an inter-character break classifier and a Western and hieroglyphic text classifier.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If an OCR engine processes textual lines with mixed Western and East Asian text, then the ability to recognize mixed text is improved, but the complexity of text segmentation and character classification increases
Solution Approach 1:
The patent segments textual lines into distinct Western and East Asian text segments based on character type detection. The system identifies character types (Western vs. East Asian) and creates separate segments for each type, allowing different recognition logic to be applied to each segment. This segmentation approach enables the OCR engine to handle mixed text while managing complexity through structured division.
Solution Approach 2:
The patent applies different recognition logic and processing methods to different segments of text based on their local characteristics. Western text segments use Western language recognition algorithms while East Asian text segments use appropriate East Asian recognition algorithms. This local quality approach allows the system to optimize recognition for each text type without requiring a single complex universal system.
2Measurement precision
If the system identifies and classifies inter-character breaks to segment text, then text segmentation accuracy is improved, but the processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary character type identification and segmentation before the main recognition process. By pre-identifying which characters are Western and which are East Asian, and pre-segmenting the text accordingly, the system prepares the text structure in advance. This preliminary action reduces the computational burden during the main recognition phase while maintaining high segmentation accuracy.
Solution Approach 2:
The system uses feedback from character type detection and inter-character break analysis to refine the segmentation process. By continuously analyzing the text structure and adjusting segment boundaries based on detected patterns, the system improves segmentation accuracy while optimizing processing efficiency through iterative refinement.
Data Source
AI summary
An image processing apparatus segments Western and hieroglyphic portions of textual lines. The apparatus includes an input component that receives an input image having at least one textual line. The apparatus also includes an inter-character break identifier component that identifies candidate inter-character breaks along a textual line and an inter-character break classifier component. The inter-character break classifier component classifies each of the candidate inter-character breaks as an actual break, a non-break or an indeterminate break based at least in part on the geometrical properties of each respective candidate inter-character break and the bounding boxes adjacent thereto. A character recognition component recognizes the candidate characters based at least in part on a feature set extracted from each respective candidate character that can be histogram features, Gabor features or any other feature set applicable to character recognition. A Western and hieroglyphic text classifier component finds and classifies textual line segments as Western text segments or hieroglyphic text segments and further passes the recognition results to an output component.