IMPACT Final Conference - USAL - Text line and word segmentation
Download as PPT, PDF0 likes1,373 views
1) The document outlines the steps in a digitization workflow for historical documents, including image enhancement, segmentation, and optical character recognition (OCR). 2) It describes hybrid methods for textline and word segmentation that do not require character recognition, making them suitable for documents with non-dictionary words. These include a connected component clustering approach and density-based projection profiling. 3) The methods are evaluated on historical documents, demonstrating accurate textline segmentation on over 2700 lines and word segmentation on over 14500 words.
IMPACT Final Conference - USAL - Text line and word segmentation
- 1. IMPACT Research Image Enhancement, Segmentation, Experimental OCR Apostolos Antonacopoulos PRImA Lab, The University of Salford, United Kingdom www.primaresearch.org
- 2. Outline Overview: digitisation workflow Image enhancement Border removal Page curl removal Correction of arbitrary warping Segmentation Recognition-based Standalone Typewritten document OCR Wordspotting
- 3. Overview: Digitisation Workflow Main steps: Scanning Image enhancement Page splitting Border removal Page curl removal Dewarping Layout analysis Segmentation of regions, lines, words and characters Region classification Logical layout analysis OCR (incl. specialist or wordspotting) Post-processing
- 4. Textline and Word Segmentation Standalone methods that can be integrated to systems without the need to integrate FR engine Not based on recognition of characters/words – suitable for documents with non-dictionary words or not practical to OCR to OCR (word spotting) Used in other IMPACT methods: Typewritten OCR Correction of arbitrary warping Word spotting date footertext
- 5. Hybrid Text Line Segmenter Hybrid approach based on connected component clustering and projection profiles Connected component extraction (incl. noise filtering) Group components into line candidates using an efficient data structure Find and split under-segmented lines using local projection profiles Merge small peripheral lines to appropriate neighbour (e.g. for i-dots etc.) Bitonal image Text regions (PAGE XML) Regions with text lines (PAGE XML) Parameters
- 6. Density Word Segmenter Adaptive projection-profile based approach using foreground pixel density Bitonal image Text regions and lines (PAGE XML) Regions, text lines and words (PAGE XML) Parameters For each text line: Generate vertical projection profile Find delimiting white spaces using an adaptive threshold based on the density of foreground pixels in the line Group connected components into words
- 7. Evaluation Text line ground truth: 25 historical documents (more than 2700 text lines) Results (using USAL layout evaluation tool): Word ground truth: 15 historical documents (more than 14500 words) Results (using USAL layout evaluation tool):
- 8. Further Information PRImA http://www.primaresearch.org IMPACT http://www.impact-project.eu