Text-line segmentation methods and algorithms in handwritten document images

Mardiyev , Azamat, Allayorov , Jasur, Alisherova , Sarvinoz

Innovation science and technologiy · 2025-yil

Annotatsiya

Automatic line segmentation plays a crucial role in the digitization and automatic recognition of handwrittenand historical documents. The variability of handwriting styles, curved baselines, touching characters, ink diffusion,and uneven backgrounds make this task particularly challenging. Traditional methods based on projection profiles ormorphological operations are effective for printed and well-structured texts but often fail when applied to degraded orhistorical documents. In recent years, advanced approaches based on probabilistic modeling, energy minimization, graphtheory, and deep neural networks have emerged. This study presents a detailed review and comparative analysis of twentyfiveleading line segmentation methods. The analysis encompasses language-independent probabilistic approaches,morphological hybrid models, the Mumford–Shah variational framework, and state-of-the-art deep learning architecturessuch as ARU-Net, Adaptive U-Net, Mask R-CNN, and GAN-based models. For each method, working principles,preprocessing requirements, evaluation datasets, and accuracy metrics are systematically examined. The results reveala clear evolution from rule-based and geometry-driven algorithms toward data-centric, binarization-free methods capableof processing multilingual and noisy manuscripts. Furthermore, the analysis consolidates existing research achievementsand identifies open research directions, including the integration of multimodal cues, self-supervised learning, and adaptivesegmentation strategies. Overall, this comprehensive review contributes to a systematic understanding of progress andremaining challenges in the field of handwritten text line segmentation

Maqola ma’lumotlari
MualliflarMardiyev , Azamat, Allayorov , Jasur, Alisherova , Sarvinoz
JurnalInnovation science and technologiy
NashriyotТошкент давлат иқтисодиёт университети
Nashr sanasi2025-10-01
Jild1
Son10
TilIngliz
Ilmiy sohaTexnika
DOI10.5281/zenodo.17511827
Indeksga qo‘shilgan2026-08-26

DOI: 10.5281/zenodo.17511827 · Maqolaning asl sahifasi

Kalit so‘zlar

handwritten text image, text line segmentation, projection profile, handwritten document, parchment

Ilmiy soha

Texnika

Iqtibos keltirish

APAMardiyev , Azamat, Allayorov , Jasur, & Alisherova , Sarvinoz (2025). TEXT-LINE SEGMENTATION METHODS AND ALGORITHMS IN HANDWRITTEN DOCUMENT IMAGES. Innovation science and technologiy, 1(10). https://doi.org/10.5281/zenodo.17511827
GOST (OAK)Mardiyev , Azamat, Allayorov , Jasur, Alisherova , Sarvinoz TEXT-LINE SEGMENTATION METHODS AND ALGORITHMS IN HANDWRITTEN DOCUMENT IMAGES // Innovation science and technologiy. – 2025. – T. 1, № 10. – DOI: 10.5281/zenodo.17511827.
MLAMardiyev , Azamat, Allayorov , Jasur, and Alisherova , Sarvinoz. “TEXT-LINE SEGMENTATION METHODS AND ALGORITHMS IN HANDWRITTEN DOCUMENT IMAGES.” Innovation science and technologiy, 1(10), 2025. https://doi.org/10.5281/zenodo.17511827
ChicagoMardiyev , Azamat, Allayorov , Jasur, and Alisherova , Sarvinoz. “TEXT-LINE SEGMENTATION METHODS AND ALGORITHMS IN HANDWRITTEN DOCUMENT IMAGES.” Innovation science and technologiy, 1(10) (2025). https://doi.org/10.5281/zenodo.17511827
HarvardMardiyev , Azamat, Allayorov , Jasur, and Alisherova , Sarvinoz (2025) ‘TEXT-LINE SEGMENTATION METHODS AND ALGORITHMS IN HANDWRITTEN DOCUMENT IMAGES’, Innovation science and technologiy, 1(10). https://doi.org/10.5281/zenodo.17511827
BibTeX
@article{mardiyevazamat2025,
  title = {TEXT-LINE SEGMENTATION METHODS AND ALGORITHMS IN HANDWRITTEN DOCUMENT IMAGES},
  author = {Mardiyev , Azamat and Allayorov , Jasur and Alisherova , Sarvinoz},
  journal = {Innovation science and technologiy},
  year = {2025},
  volume = {1},
  number = {10},
  doi = {10.5281/zenodo.17511827},
  url = {https://doi.org/10.5281/zenodo.17511827}
}

Boshqa maqola uchun iqtibos tayyorlash

Innovation science and technologiy jurnalidan boshqa maqolalar

Innovation science and technologiy — barcha maqolalar · 2025-yil arxivi

Mardiyev , Azamat — boshqa maqolalari

Texnika sohasidagi boshqa maqolalar

Texnika sohasidagi OAK jurnallari