A Review On Text Extraction Techniques For Degraded Historical Document Images
Yogish Naik G. R, B Shashidhara, G K Amith · 2024
Extraction text from degraded historical document images (DHDI) poses a significant challenge's. However, it plays a vital role in uncovering valuable and meaningful information contained within these documents. The appearance and characteristics of text in documents are influenced by diverse factors, including language, stylistic choices, font selection, size variations, color usage, background design, orientation, as well as fluctuations in text arrangement such as intersecting or overlapping lines. This paper provides a comprehensive review of different approaches in text extraction techniques and conducts a performance comparison of various text extraction methods proposed by researchers, evaluating them based on metrics such as recall rate, precision rate, processing time and accuracy.