Text Detection and Classification of Construction Documents
Bibliographic record
Abstract
Text Detection and Classification of Construction Documents Narges Sajadfar, Sina Abdollahnejad, Ulrich Hermann and Yasser Mohamed Pages 446-452 (2019 Proceedings of the 36th ISARC, Banff, Canada, ISBN 978-952-69524-0-6, ISSN 2413-5844) Abstract: Large construction projects generate thousands of documents that require a careful management. The classification of documents is an important step in document management and control. Construction documents are generated in different formats, many of which are unstructured and contain drawings and images, which makes the task of document classification and control even more challenging. In this paper, a dataset of 5000 documents is used as a case study. Optical Character Recognition (OCR) bounding boxes are applied to extract text from the set of documents. In the next step, two classification methods are applied. One based on a predefined set of keywords and another based on deep learning long short- term memory (LSTM) network. The challenges of the proposed approaches are discussed in relation to OCR bounding box locations with different document layout and how to obtain a set of representative key words for each class. Initial results of the study are encouraging and show that OCR technique combined with text classification is a powerful method for construction documents control and can reach an accuracy of 92%. Keywords: Construction document; Text detection; Classification; Data mining; Optical Character Recognition (OCR); Deep Learning DOI: https://doi.org/10.22260/ISARC2019/0060 Download fulltext Download BibTex Download Endnote (RIS) TeX Import to Mendeley
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.006 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".