Enhancing Document Image Retrieval in Education: Leveraging Ensemble-Based Document Image Retrieval Systems for Improved Precision
Source abstract
Abstract
Document image retrieval (DIR) systems simplify access to digital data within printed documents by capturing images. These systems act as bridges between print and digital realms, with demand in organizations handling both formats. In education, students use DIR to access online materials, clarify topics, and find solutions in printed textbooks by photographing content with their phones. DIR excels in handling complex figures and formulas. We propose using ensembles of DIR systems instead of single-feature models to enhance DIR’s efficacy. We introduce “Vote-Based DIR” and “The Strong Decision-Based DIR”. These ensembles combine various techniques, like optical code reading, spatial analysis, and image features, improving document retrieval. Our study, using a dataset of university exam preparation materials, shows that ensemble DIR systems outperform individual ones, promising better accuracy and efficiency in digitizing printed content, which is especially beneficial in education.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Image and Video Retrieval Techniques · Image Retrieval and Classification Techniques · Handwritten Text Recognition Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Business Administration, American University of the Middle East, Egaila 54200, Kuwait
College of Engineering and Technology, American University of the Middle East, Egaila 54200, Kuwait
Booking Holdings Inc., 1000 BP Amsterdam, The Netherlands
References (38)
Show source-provided references
1. Deep learned vectors’ formation using auto-correlation, scaling, and derivations with CNN for complex and huge image retrieval10.1007/s40747-022-00866-8 ↗
2. Content-based medical image retrieval by spatial matching of visual words
3. Efficient content-based image retrieval using deep search and rescue algorithm10.1007/s00500-021-06660-x ↗
4. Concentrated hashing with neighborhood embedding for image retrieval and classification10.1007/s13042-021-01466-7 ↗
5. Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval10.1109/TPAMI.2012.193 ↗
6. Large-scale document image retrieval and classification with runlength histograms and binary embeddings10.1016/j.patcog.2012.12.004 ↗
7. End-to-end learning of representations for instance-level document image retrieval10.1016/j.asoc.2023.110136 ↗
8. Multilanguage transformer for improved text to remote sensing image retrieval10.1109/JSTARS.2022.3215803 ↗
9. A document image retrieval system10.1016/j.engappai.2010.03.002 ↗
10. A decisive content based image retrieval approach for feature fusion in visual and textual images10.1016/j.knosys.2019.05.001 ↗
11. Keyword-based diverse image retrieval with variational multiple instance graph10.1109/TNNLS.2022.3168431 ↗
12. Language-based document image retrieval for Trilingual System
13. A faster secure content-based image retrieval using clustering for cloud10.1016/j.eswa.2021.116070 ↗
14. Content-based medical image retrieval system for lung diseases using deep CNNs
15. Scalable nearest neighbor algorithms for high dimensional data10.1109/TPAMI.2014.2321376 ↗
16. Recent advances in graph-based pattern recognition with applications in document analysis10.1016/j.patcog.2010.11.015 ↗
17. Classification of document pages using structure-based features10.1007/PL00013566 ↗
18. Logo and seal based administrative document image retrieval: A survey10.1016/j.cosrev.2016.09.002 ↗
19. A novel content-based image retrieval approach for classification using GLCM features and texture fused LBP variants10.1007/s00521-020-05017-z ↗
20. Augereau, O., Journet, N., and Domenger, J.-P. (2013, January 5–7). Semi-structured document image matching and recognition. Proceedings of the Document Recognition and Retrieval XX, Burlingame, CA USA.10.1117/12.2003911 ↗
21. Camera-based document image matching using multi-feature probabilistic information fusion10.1016/j.patrec.2015.02.014 ↗
22. Kanchi, S., Pagani, A., Mokayed, H., Liwicki, M., Stricker, D., and Afzal, M.Z. (2022). EmmDocClassifier: Efficient multimodal document image classifier for scarce data. Appl. Sci., 12.10.20944/preprints202201.0061.v1 ↗
23. Alzoubi, Y.I., Topcu, A.E., and Erkaya, A.E. (2023). Machine learning-based text classification comparison: Turkish language context. Appl. Sci., 13.10.3390/app13169428 ↗
24. Topcu, A.E., Alzoubi, Y.I., Elbasi, E., and Camalan, E. (2023). Social media zero-day attack detection using TensorFlow. Electronics, 12.10.3390/electronics12173554 ↗
25. Text analysis of smart cities: A big data-based model
26. Forssén, P.-E., and Lowe, D.G. (2007, January 14–21). Shape descriptors for maximally stable extremal regions. Proceedings of the IEEE 11th International Conference on Computer Vision, Rio de Janeiro, Brazil.10.1109/ICCV.2007.4409025 ↗
27. Surf: Speeded up robust features
28. Overview of the RANSAC algorithm
29. Wolf, C., Jolion, J.-M., and Chassaing, F. (2002, January 11–15). Text localization, enhancement and binarization in multimedia documents. Proceedings of the IEEE International Conference on Pattern Recognition, Quebec City, QC, Canada.
30. Binarization of degraded document image based on feature space partitioning and classification10.1007/s10032-010-0142-4 ↗
31. Adaptive document image binarization10.1016/S0031-3203(99)00055-2 ↗
32. A computational approach to edge detection10.1109/TPAMI.1986.4767851 ↗
33. Text mining: Use of TF-IDF to examine the relevance of words to documents
34. Solr (2022, June 22). Apache Solr. Available online: https://solr.apache.org/.
35. Smith, R. (2007, January 23–26). An overview of the Tesseract OCR engine. Proceedings of the IEEE Ninth International Conference on Document Analysis and Recognition, Curitiba, Brazil.10.1109/ICDAR.2007.4376991 ↗
36. Manning, C.D., Raghavan, P., and Schütze, H. (2009). An Introduction to Information Retrieval, Cambridge University Press. Online edition.10.1017/CBO9780511809071 ↗
37. Tosbik (2022, May 25). Tosbik. Available online: https://tosbikapp.com/.
38. Developers (2023, December 07). Android Platform: ExifInterface. Available online: https://developer.android.com/reference/android/media/ExifInterface.