QO‘LYOZMALI HUJJAT TASVIRIDA MATN JOYLASHGAN SOHALARNI ANIQLASH USUL VA ALGORITMLARI
Mardiyev A. S., Allayorov J. A. & Alisherova S. A.
Annotatsiya
Ushbu tadqiqotda hujjat tasvirlarida matn joylashgan sohalarni avtomatik aniqlashga oid usullar va algoritmlar keng qamrovda o‘rganildi. Ish davomida an’anaviy “pastdan yuqoriga” va “yuqoridan pastga” yondashuvlardan tortib, chuqur o‘rganishga asoslangan zamonaviy neyron tarmoqlar – to‘liq konvolyutsion tarmoq (FCN), U-Net va hujjatlarni tahlil qilish uchun e’tibor mexanizmiga asoslangan neyron tarmoq (DAN) arxitekturalarigacha bo‘lgan model va algoritmlar tahlil qilindi. Ayniqsa, tarixiy qo‘lyozmalardagi shovqin, og‘ish burchagi va bezakli elementlar mavjud sahifalar uchun moslashuvchan modellar ustunligi alohida yoritilgan. Tadqiqot natijalari chuqur o‘rganishga asoslangan va segmentatsiyasiz modellar an’anaviy algoritmlarga nisbatan aniqlik, tezlik va barqarorlik jihatidan sezilarli ustunlikka egaligini ko‘rsatdi. Natijada, bunday modellar hujjat tasvirlarida matn joylashgan sohalarni avtomatik aniqlash sohasida ilg‘or yondashuv sifatida e’tirof etilmoqda.
Adabiyotlar
- O‘Gorman L. The document spectrum for page layout analysis //IEEE Transactions on pattern analysis and machine intelligence. – 2002. – V. 15. – №. 11. – P. 1162-1173.
- Jain A. K., Yu B. Document representation and its application to page decomposition //IEEE Transactions on pattern analysis and machine intelligence. – 1998. – V. 20. – №. 3. – P. 294-308.
- Lee S. W., Ryu D. S. Parameter-free geometric document layout analysis //IEEE Transactions on pattern analysis and machine intelligence. – 2001. – V. 23. – №. 11. – P. 1240-1256.
- Garz A., Sablatnig R., Diem M. Layout analysis for historical manuscripts using sift features //2011 International Conference on Document Analysis and Recognition. – IEEE, 2011. – P. 508-512.
- Asi A. et al. A coarse-to-fine approach for layout analysis of ancient manuscripts //2014 14th international conference on frontiers in handwriting recognition. – IEEE, 2014. – P. 140-145.
- Chen K. et al. Page segmentation for historical handwritten document images using color and texture features //2014 14th International Conference on Frontiers in Handwriting Recognition. – IEEE, 2014. – P. 488-493.
- Le V. P. et al. Text and non-text segmentation based on connected component features //2015 13th International conference on document analysis and recognition (ICDAR). – IEEE, 2015. – P. 1096-1100.
- Simon A., Pret J. C., Johnson A. P. A fast algorithm for bottom-up document layout analysis //IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2002. – V. 19. – №. 3. – P. 273-277.
- Chen K. et al. Page segmentation for historical document images based on superpixel classification with unsupervised feature learning //2016 12th IAPR Workshop on Document Analysis Systems (DAS). – IEEE, 2016. – P. 299-304.
- Oliveira D. A. B., Viana M. P. Fast CNN-based document layout analysis //2017 IEEE International Conference on Computer Vision Workshops (ICCVW). – IEEE, 2017. – P. 1173-1180.
- Xu Y. et al. Page segmentation for historical handwritten documents using fully convolutional networks //2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). – IEEE, 2017. – V. 1. – P. 541-546.
- Oliveira S. A., Seguin B., Kaplan F. dhSegment: A generic deep-learning approach for document segmentation //2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR). – IEEE, 2018. – P. 7-12.
- Xu Y. et al. Multi-task Layout Analysis for Historical Handwritten Documents Using Fully Convolutional Networks //IJCAI. – 2018. – P. 1057-1063.
- Alaasam R., Kurar B., El-Sana J. Layout analysis on challenging historical arabic manuscripts using siamese network //2019 International Conference on Document Analysis and Recognition (ICDAR). – IEEE, 2019. – С. 738-742.
- Monnier T., Aubry M. docExtractor: An offthe-shelf historical document element extraction //2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR). – P. 91-96.
- Markewich L. et al. Segmentation for document layout analysis: not dead yet //International Journal on Document Analysis and Recognition (IJDAR). – 2022. – V. 25. – №. 2. – P. 67-77.
- Biswas S. et al. Beyond document object detection: instance-level segmentation of complex layouts //International Journal on Document Analysis and Recognition (IJDAR). – 2021. – V. 24. – №. 3. – P. 269-281.
- Coquenet D., Chatelain C., Paquet T. Dan: a segmentation-free document attention network for handwritten document recognition //IEEE transactions on pattern analysis and machine intelligence. – 2023. – V. 45. – №. 7. – P. 8227-8243.
- Smith R. W. Hybrid page layout analysis via tab-stop detection //2009 10th International Conference on Document Analysis and Recognition. – IEEE, 2009. – P. 241-245.
- Vasilopoulos N., Kavallieratou E. Complex layout analysis based on contour classification and morphological operations //Proceedings of the 9th Hellenic Conference on Artificial Intelligence. – 2016. – P. 1-4.
- Tran T. A., Na I. S., Kim S. H. Page segmentation using minimum homogeneity algorithm and adaptive mathematical morphology //International Journal on Document Analysis and Recognition (IJDAR). – 2016. – V. 19. – №. 3. – P. 191-209.