{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T17:27:21Z","timestamp":1790184441849,"version":"4.1.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:00:00Z","timestamp":1774396800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"content-version":"vor","delay-in-days":49,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Symbiosis International"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The rapid growth of born-digital PDF documents has amplified the demand for fast, precise tabular data extraction on an industrial scale. State-of-the-art deep-learning approaches have high accuracy, but at the resource expense of substantial computational complexity, data-hungry training process and black-box incomprehensibility, confining deployment in the real world. In this paper, we introduce SPARTAN (Structured Parsing and Relevant Table Analysis), an entirely open-source, heuristic-based pipeline, with high-fidelity table detection and extraction and no model training or GPU requirements. SPARTAN mixes lightweight OpenCV image-processing modules: column whitespace analysis, boundary and text-based region segmentation and line segment cell parsing, with a modular OCR layer and optional post-processing hooks for LLM-driven schema mapping. We evaluated SPARTAN on more than 20\u00a0K pages of PCN-480 (Product Change Notification and Product Discontinuance Notification), scientific papers, certificates and datasheets and reported 0.94 precision, 0.91 recall and 0.93 F1-score, with 96.7% OCR character accuracy, processing a page in 2.8\u00a0s CPU time on an average, and requiring 1.2\u00a0GB peak RAM on the most demanding PDFs. Our model outperformed Tabula, Deepdoctection, TabbyPDF and EMbTTBF in accuracy and speed. It must be noted that this comparison was conducted against standard inference configurations for the learning-based baselines; a performance evaluation against highly-optimized, edge-device deployments is a consideration for future work. Its rule transparency effortlessly copes with borderless, nested and merged-cell layouts that easily outsmart classical heuristics, without incurring the resource cost of end-to-end neural pipelines. SPARTAN\u2019s CLI-governed, swap-in-swap-out architecture encourages domain tuning, edge deployment and cloud-scalable REST service wrapping, making it a practical bridge between brittle rule systems and heavyweight AI for document-understanding pipelines. The work proves that well-crafted modernized heuristics, combined with high-quality OCR, can match or even outperform state-of-the-art deep learning while remaining within reach of small and medium enterprises, thus re-opening a critical gate to cost-efficient, explainable PDF table extraction.<\/jats:p>","DOI":"10.1038\/s41598-026-44325-7","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T14:54:58Z","timestamp":1774450498000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["SPARTAN: automated table detection and extraction from documents using advanced OpenCV heuristics and OCR techniques"],"prefix":"10.1038","volume":"16","author":[{"given":"Shlok","family":"Nandurbarkar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Archana Y.","family":"Chaudhari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahesha","family":"Mulla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"issue":"3","key":"44325_CR1","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1016\/j.ipm.2019.01.008","volume":"56","author":"R Rastan","year":"2019","unstructured":"Rastan, R., Paik, H. Y. & Shepherd, J. TEXUS: a unified framework for extracting and understanding tables in PDF documents. Inf. Process. Manag. 56(3), 895\u2013918 (2019).","journal-title":"Inf. Process. Manag."},{"key":"44325_CR2","doi-asserted-by":"crossref","unstructured":"Shigarov, A., Altaev, A., Mikhailov, A., Paramonov, V. & Cherkashin, E. TabbyPDF: web-based system for PDF table extraction. In ICIST 2018, CCIS, Vol. 920  (eds. Dama\u0161evi\u010dius, R. & Vasiljevien\u0117, G.) 257\u2013269 (Springer, 2018).","DOI":"10.1007\/978-3-319-99972-2_20"},{"key":"44325_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2022.100220","volume":"15","author":"Z Colter","year":"2022","unstructured":"Colter, Z. et al. Tablext: a combined neural network and heuristic-based table extractor. Array 15, 100220 (2022).","journal-title":"Array"},{"key":"44325_CR4","doi-asserted-by":"crossref","unstructured":"Ohta, M., Yamada, R., Kanazawa, T. & Takasu, A.  A cell-detection-based table-structure recognition method. In Proceedings of the ACM Symposium on Document Engineering 2019 1\u20134 (ACM, 2019).","DOI":"10.1145\/3342558.3345412"},{"key":"44325_CR5","doi-asserted-by":"publisher","first-page":"78398","DOI":"10.1109\/ACCESS.2022.3192828","volume":"10","author":"H Arslan","year":"2022","unstructured":"Arslan, H. End to end invoice processing application based on key fields extraction. IEEE Access 10, 78398\u201378413 (2022).","journal-title":"IEEE Access"},{"key":"44325_CR6","doi-asserted-by":"crossref","unstructured":"Mahtab, M. A. & Maisha, J.  Automated financial report detection, classification and structure recognition using YOLO and SLANet. In  IEEE International Conference on Future Machine Learning and Data Science (FMLDS) 277\u2013282 (IEEE, 2024).","DOI":"10.1109\/FMLDS63805.2024.00058"},{"key":"44325_CR7","first-page":"24518","volume":"12","author":"L Song","year":"2024","unstructured":"Song, L., Huang, X., Zhuang, S., Shen, A. & Xu, P. Robust table structure recognition network based on local and global perspectives. IEEE Access 12, 24518\u201324529 (2024).","journal-title":"IEEE Access"},{"key":"44325_CR8","doi-asserted-by":"crossref","unstructured":"Rizan, R. U. B.  Automatic parsing and extraction of structured data from fax images. In  International Conference on Engineering and Emerging Technologies (ICEET)  1\u20137 (IEEE,  2024).","DOI":"10.1109\/ICEET65156.2024.10913905"},{"key":"44325_CR9","doi-asserted-by":"crossref","unstructured":"Chen, H., Song, S. & Su, R.  Table detection method based on Faster-RCNN and window attention. In Proceedings of the 12th International Conference on Networks, Communication and Computing 267\u2013273 (ACM,  2023).","DOI":"10.1145\/3638837.3638879"},{"key":"44325_CR10","doi-asserted-by":"crossref","unstructured":"Kim, H. J. et al. An automated framework for accurately classifying financial tables in enterprise analysis reports. In Asian Conference on Pattern Recognition,  Vol. 1916 374\u2013384 (Springer, 2023).","DOI":"10.1007\/978-3-031-47634-1_28"},{"key":"44325_CR11","doi-asserted-by":"crossref","unstructured":"Li, G., Huang, J., Wang, Z., Gao, J. & Chen, K.  Form recognition based on lightweight U-Net and Tesseract after multi-level retraining. In International Conference of Optical Imaging and Measurement (ICOIM) 243\u2013248 (IEEE,  2021).","DOI":"10.1109\/ICOIM52180.2021.9524385"},{"key":"44325_CR12","doi-asserted-by":"crossref","unstructured":"Jain, P.  et al.  Extracting tabular data for question-answering from documents. In ACM India Joint International Conference on Data Science & Management of Data 400\u2013404 (ACM, 2021).","DOI":"10.1145\/3430984.3430992"},{"key":"44325_CR13","unstructured":"Prasad, D., Gadpal, A., Kapadni, K., Visave, M. &  Sultanpure, K.: CascadeTabNet: end-to-end table detection from image-based documents. In  CVPR Workshops  572\u2013573 (IEEE, 2020)."},{"issue":"1","key":"44325_CR14","first-page":"69","volume":"33","author":"H Dong","year":"2019","unstructured":"Dong, H., Liu, S., Han, S., Fu, Z. & Zhang, D. Tablesense: spreadsheet table detection with convolutional neural networks. AAAI Conf. Artif. Intell. 33(1), 69\u201376 (2019).","journal-title":"AAAI Conf. Artif. Intell."},{"key":"44325_CR15","doi-asserted-by":"crossref","unstructured":"Xue, W., Yu, B., Wang, W., Tao, D. & Li, Q.  Tgrnet: a table graph reconstruction network for table structure recognition. In ICCV 2021 1295\u20131304 (IEEE, 2021).","DOI":"10.1109\/ICCV48922.2021.00133"},{"key":"44325_CR16","doi-asserted-by":"crossref","unstructured":"Fischer, P., Smajic, A., Abrami, G. & Mehler, A. Multi-type-td-tsr: extracting tables from document images. In KI 2021, Vol. 12873  95\u2013108 (Springer, 2021).","DOI":"10.1007\/978-3-030-87626-5_8"},{"key":"44325_CR17","doi-asserted-by":"crossref","unstructured":"Alexiou, M. S. & Bourbakis, N. Automatic deep understanding of tables in technical documents. In 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI) 443\u2013451 (IEEE, 2020).","DOI":"10.1109\/ICTAI50040.2020.00076"},{"key":"44325_CR18","doi-asserted-by":"crossref","unstructured":"Rani, N. S., Pruthvi, T. R., Rao, A. G. & Bipin, N. B. Automated text line segmentation and table detection for pre-printed document image analysis systems. In 2021 3rd International Conference on Signal Processing and Communication (ICPSC) 723\u2013730 (IEEE, 2021).","DOI":"10.1109\/ICSPC51351.2021.9451779"},{"issue":"4","key":"44325_CR19","doi-asserted-by":"publisher","DOI":"10.3390\/informatics11040077","volume":"11","author":"T Ngubane","year":"2024","unstructured":"Ngubane, T. & Tapamo, J. R. TableExtractNet: a model of automatic detection and recognition of table structures from unstructured documents. Informatics 11(4), 77 (2024).","journal-title":"Informatics"},{"key":"44325_CR20","doi-asserted-by":"crossref","unstructured":"Ngubane, T. & Tapamo, J. R. Detection and recognition of table structures from unstructured documents. In 2024 Conference on Information Communications Technology and Society (ICTAS)  221\u2013226 (IEEE, 2024).","DOI":"10.1109\/ICTAS59620.2024.10507118"},{"key":"44325_CR21","doi-asserted-by":"crossref","unstructured":"Singh, M. & Goyal, P. DeepDoT: deep framework for detection of tables in document images. In International Conference on Computer Vision and Image Processing 421\u2013432 (Springer, 2020).","DOI":"10.1007\/978-981-16-1092-9_35"},{"key":"44325_CR22","doi-asserted-by":"crossref","unstructured":"Shepal, P., Rajput, J., Dhavale, A., Lakade, V. & Kulkarni, S. Automated table detection using R-CNN: a cloud-based approach. In 2023 IEEE Pune Section International Conference (PuneCon) 1\u20136 (IEEE, 2023).","DOI":"10.1109\/PuneCon58714.2023.10450066"},{"issue":"2","key":"44325_CR23","doi-asserted-by":"publisher","DOI":"10.3390\/math13020266","volume":"13","author":"MS Kasem","year":"2025","unstructured":"Kasem, M. S. et al. HTTD: a hierarchical transformer for accurate table detection in document images. Mathematics 13(2), 266 (2025).","journal-title":"Mathematics"},{"issue":"1","key":"44325_CR24","doi-asserted-by":"publisher","DOI":"10.3390\/s25010203","volume":"25","author":"MZ Iqbal","year":"2025","unstructured":"Iqbal, M. Z., Garg, N. & Ahmed, S. B. Table extraction with table data using VGG-19 deep learning model.. Sens. (Basel) 25(1), 203 (2025).","journal-title":"Sens. (Basel)"},{"issue":"5","key":"44325_CR25","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1016\/j.vrih.2024.06.003","volume":"6","author":"Y Li","year":"2024","unstructured":"Li, Y., Zhang, P., Sun, M., Huang, J. & He, R. Pre-training transformer with dual-branch context content module for table detection in document images. Virtual Real. Intell. Hardw. 6(5), 408\u2013420 (2024).","journal-title":"Virtual Real. Intell. Hardw."},{"key":"44325_CR26","doi-asserted-by":"crossref","unstructured":"Sun, S., Zhu, J., Zhou, C. & Yang, C. CRCRNet: an integrated approach to table data extraction. In Proceedings of the 2024 3rd International Conference on Networks, Communications and Information Technology 76\u201380 (ACM, 2024).","DOI":"10.1145\/3672121.3672136"},{"key":"44325_CR27","doi-asserted-by":"crossref","unstructured":"Paliwal, S. S. et al. TableNet: seep learning model for end-to-end table detection and tabular data extraction from scanned document images. In 2019 International Conference on Document Analysis and Recognition (ICDAR) 128\u2013133 (IEEE, 2019).","DOI":"10.1109\/ICDAR.2019.00029"},{"key":"44325_CR28","doi-asserted-by":"crossref","unstructured":"Lyu, P. et al. GridFormer: towards accurate table structure recognition via grid prediction. In Proceedings of the 31st ACM International Conference on Multimedia 7747\u20137757 (ACM, 2023).","DOI":"10.1145\/3581783.3611961"},{"key":"44325_CR29","unstructured":"Lattice Semiconductor. PCN\u2011480: product change notification and product discontinuance notification, lattice semiconductor. https:\/\/www.latticesemi.com\/en\/Support\/PCN (2025)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44325-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44325-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44325-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T23:43:36Z","timestamp":1778629416000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44325-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,25]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["44325"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-44325-7","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,25]]},"assertion":[{"value":"4 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"14954"}}