{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T16:29:49Z","timestamp":1772468989842,"version":"3.50.1"},"reference-count":53,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2020,11,27]],"date-time":"2020-11-27T00:00:00Z","timestamp":1606435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Documents are stored in a digital form across several organizations. Printing this amount of data and placing it into folders instead of storing digitally is against the practical, economical, and ecological perspective. An efficient way of retrieving data from digitally stored documents is also required. This article presents a real-time supervised learning technique for document classification based on deep convolutional neural network (DCNN), which aims to reduce the impact of adverse document image issues such as signatures, marks, logo, and handwritten notes. The proposed technique\u2019s major steps include data augmentation, feature extraction using pre-trained neural network models, feature fusion, and feature selection. We propose a novel data augmentation technique, which normalizes the imbalanced dataset using the secondary dataset RVL-CDIP. The DCNN features are extracted using the VGG19 and AlexNet networks. The extracted features are fused, and the fused feature vector is optimized by applying a Pearson correlation coefficient-based technique to select the optimized features while removing the redundant features. The proposed technique is tested on the Tobacco3482 dataset, which gives a classification accuracy of 93.1% using a cubic support vector machine classifier, proving the validity of the proposed technique.<\/jats:p>","DOI":"10.3390\/s20236793","type":"journal-article","created":{"date-parts":[[2020,11,28]],"date-time":"2020-11-28T03:51:16Z","timestamp":1606535476000},"page":"6793","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":128,"title":["Pearson Correlation-Based Feature Selection for Document Classification Using Balanced Training"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3578-0081","authenticated-orcid":false,"given":"Inzamam Mashood","family":"Nasir","sequence":"first","affiliation":[{"name":"Department of Computer Science, HITEC University, Taxila 47080, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6763-2123","authenticated-orcid":false,"given":"Muhammad Attique","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, HITEC University, Taxila 47080, Pakistan"}]},{"given":"Mussarat","family":"Yasmin","sequence":"additional","affiliation":[{"name":"Department of Computer Science, COMSATS University Islamabad, Wah Campus, Wah Cantonment 47040, Pakistan"}]},{"given":"Jamal Hussain","family":"Shah","sequence":"additional","affiliation":[{"name":"Department of Computer Science, COMSATS University Islamabad, Wah Campus, Wah Cantonment 47040, Pakistan"}]},{"given":"Marcin","family":"Gabryel","sequence":"additional","affiliation":[{"name":"Department of Intelligent Computer Systems, Cz\u0119stochowa University of Technology, 42-200 Cz\u0119stochowa, Poland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9592-262X","authenticated-orcid":false,"given":"Rafa\u0142","family":"Scherer","sequence":"additional","affiliation":[{"name":"Department of Intelligent Computer Systems, Cz\u0119stochowa University of Technology, 42-200 Cz\u0119stochowa, Poland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9990-1084","authenticated-orcid":false,"given":"Robertas","family":"Dama\u0161evi\u010dius","sequence":"additional","affiliation":[{"name":"Faculty of Applied Mathematics, Silesian University of Technology, 44-100 Gliwice, Poland"}]}],"member":"1968","published-online":{"date-parts":[[2020,11,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/j.patcog.2016.09.017","article-title":"Beyond OCR: Multi-faceted understanding of handwritten document characteristics","volume":"63","author":"He","year":"2017","journal-title":"Pattern Recognit."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1016\/j.patcog.2017.02.023","article-title":"A survey of document image word spotting techniques","volume":"68","author":"Giotis","year":"2017","journal-title":"Pattern Recognit."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Chen, K., Seuret, M., Liwicki, M., Hennebert, J., and Ingold, R. (2015, January 23\u201326). Page segmentation of historical document images with convolutional autoencoders. Proceedings of the 13th International Conference on Document Analysis and Recognition (ICDAR), Tunis, Tunisia.","DOI":"10.1109\/ICDAR.2015.7333914"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.ins.2018.02.004","article-title":"An HMM framework based on spherical-linear features for online cursive handwriting recognition","volume":"441","author":"Samanta","year":"2018","journal-title":"Inf. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Noce, L., Gallo, I., and Zamberletti, A. (2016, January 23\u201325). Query and Product Suggestion for Price Comparison Search Engines based on Query-product Click-through Bipartite Graphs. Proceedings of the 12th International Conference on Web Information Systems and Technologies, WEBIST 2016, Rome, Italy.","DOI":"10.5220\/0005753400170024"},{"key":"ref_6","unstructured":"Crowe, J.P. (2019). Library Indexing System and Method. (US20150066945A1), U.S. Patent."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zamberletti, A., Noce, L., and Gallo, I. (2014, January 1\u20135). Text localization based on fast feature pyramids and multi-resolution maximally stable extremal regions. Proceedings of the Asian Conference on Computer Vision, ACCV 2014, Singapore.","DOI":"10.1007\/978-3-319-16631-5_7"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Gallo, I., Zamberletti, A., and Noce, L. (2014, January 26\u201330). Interactive object class segmentation for mobile devices. Proceedings of the 27th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), Rio de Janeiro, Brazil.","DOI":"10.1109\/SIBGRAPI.2014.35"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/S0031-3203(99)00055-2","article-title":"Adaptive document image binarization","volume":"33","author":"Sauvola","year":"2000","journal-title":"Pattern Recognit."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1023\/A:1009910911387","article-title":"Comparison and classification of documents based on layout similarity","volume":"2","author":"Hu","year":"2000","journal-title":"Inf. Retr."},{"key":"ref_11","first-page":"308","article-title":"Text skew detection using combined entropy algorithm","volume":"46","year":"2017","journal-title":"Inf. Technol. Control"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1515\/amcs-2017-0014","article-title":"Projection-based text line segmentation with a variable threshold","volume":"27","author":"Ptak","year":"2017","journal-title":"Int. J. Appl. Math. Comput. Sci."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Akhtar, Z., Lee, J.W., Khan, M.A., Sharif, M., Khan, S.A., and Riaz, N. (2020). Optical character recognition (OCR) using partial least square (PLS) based feature reduction: An application to artificial intelligence for biometric identification. J. Enterp. Inf. Manag.","DOI":"10.1108\/JEIM-02-2020-0076"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Tensmeyer, C., and Martinez, T. (2017, January 9\u201315). Analysis of convolutional neural networks for document image classification. Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan.","DOI":"10.1109\/ICDAR.2017.71"},{"key":"ref_15","unstructured":"Kumar, B.S., and Ravi, V. (2016, January 16\u201317). Text Document Classification with PCA and One-Class SVM. Proceedings of the 5th International Conference on Frontiers in Intelligent Computing: Theory and Applications, FICTA 2016, Bhubaneswar, India."},{"key":"ref_16","unstructured":"Kipf, T.N., and Welling, M. (2017, January 24\u201326). Semi-supervised classification with graph convolutional networks. Proceedings of the 5th International Conference on Learning Representations, ICLR 2017, Toulon, France."},{"key":"ref_17","unstructured":"Lenc, L., and Kr\u00e1l, P. (2016, January 3\u20139). Deep neural networks for Czech multi-label document classification. Proceedings of the International Conference on Intelligent Text Processing and Computational Linguistics, Konya, Turkey."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Jiang, X., Ringwald, M., Blake, J.A., Arighi, C., Zhang, G., and Shatkay, H. (2019). An effective biomedical document classification scheme in support of biocuration: Addressing class imbalance. Database, 2019.","DOI":"10.1093\/database\/baz045"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Das, A., Roy, S., Bhattacharya, U., and Parui, S.K. (2018, January 20\u201324). Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks. Proceedings of the 24th International Conference on Pattern Recognition (ICPR), Beijing, China.","DOI":"10.1109\/ICPR.2018.8545630"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"15751","DOI":"10.1007\/s11042-018-7031-0","article-title":"Object detection and classification: A joint selection and fusion strategy of deep convolutional neural network and SIFT point features","volume":"78","author":"Rashid","year":"2019","journal-title":"Multimed. Tools Appl."},{"key":"ref_21","unstructured":"Nasir, I.M., Rashid, M., Shah, J.H., Sharif, M., Awan, M.Y.H., and Alkinani, M.H. (2020). An Optimized Approach for Breast Cancer Classification for Histopathological Images Based on Hybrid Feature Set. Curr. Med. Imaging, 16."},{"key":"ref_22","first-page":"1","article-title":"Hybrid Deep Learning Architecture for the Classification of Superhero Fashion Products: An Application for Medical-Tech Classification","volume":"124","author":"Nasir","year":"2020","journal-title":"Comput. Model. Eng. Sci."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kapo\u010di\u016bt\u0117-Dzikien\u0117, J., Dama\u0161evi\u010dius, R., and Wo\u017aniak, M. (2019). Sentiment analysis of lithuanian texts using traditional and deep learning approaches. Computers, 8.","DOI":"10.3390\/computers8010004"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"107275","DOI":"10.1016\/j.comnet.2020.107275","article-title":"Accurate and fast URL phishing detector: A convolutional neural network approach","volume":"178","author":"Wei","year":"2020","journal-title":"Comput. Netw."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Khan, M.A., Ashraf, I., Alhaisoni, M., Dama\u0161evi\u010dius, R., Scherer, R., Rehman, A., and Bukhari, S.A.C. (2020). Multimodal brain tumor classification using deep learning and robust feature selection: A machine learning application for radiologists. Diagnostics, 10.","DOI":"10.3390\/diagnostics10080565"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Pipiras, L., Maskeli\u016bnas, R., and Dama\u0161evi\u010dius, R. (2019). Lithuanian Speech Recognition Using Purely Phonetic Deep Learning. Computers, 8.","DOI":"10.3390\/computers8040076"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhang, M., Jing, W., Lin, J., Fang, N., Wei, W., Wo\u017aniak, M., and Dama\u0161evi\u010dius, R. (2020). NAS-HRIS: Automatic design and architecture search of neural network for semantic segmentation in remote sensing images. Sensors, 20.","DOI":"10.3390\/s20185292"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Nisa, M., Shah, J.H., Kanwal, S., Raza, M., Khan, M.A., Dama\u0161evi\u010dius, R., and Bla\u017eauskas, T. (2020). Hybrid malware classification method using segmentation-based fractal texture analysis and deep convolution neural network features. Appl. Sci., 10.","DOI":"10.3390\/app10144966"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"28133","DOI":"10.1109\/ACCESS.2020.2966580","article-title":"Road detection based on shearlet for GF-3 synthetic aperture radar images","volume":"8","author":"Sun","year":"2020","journal-title":"IEEE Access"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"8225","DOI":"10.1016\/j.jfranklin.2018.08.012","article-title":"Reduction of the non-uniform illumination using nonlocal variational models for document image analysis","volume":"355","author":"Bella","year":"2018","journal-title":"J. Frankl. Inst."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","article-title":"LabelMe: A database and web-based tool for image annotation","volume":"77","author":"Russell","year":"2008","journal-title":"Int. J. Comput. Vis."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Alom, M.Z., Taha, T.M., Yakopcic, C., Westberg, S., Sidike, P., Nasrin, M.S., Hasan, M., Van Essen, B.C., Awwal, A.A.S., and Asari, V.K. (2019). A State-of-the-Art Survey on Deep Learning Theory and Architectures. Electronics, 8.","DOI":"10.3390\/electronics8030292"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, G., Huang, H.H., Wang, Z., and Zheng, W. (2016, January 16\u201319). Performance analysis of GPU-based convolutional neural networks. Proceedings of the International Conference on Parallel Processing, Philadelphia, PA, USA.","DOI":"10.1109\/ICPP.2016.15"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., and Rabinovich, A. (2015, January 8\u201310). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., and Fergus, R. (2014, January 6\u201312). Visualizing and understanding convolutional networks. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref_38","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Fiat, A., and Woeginger, G.J. (1998). On-line algorithms in machine learning. Online Algorithms, Springer.","DOI":"10.1007\/BFb0029561"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Harley, A.W., Ufkes, A., and Derpanis, K.G. (2015, January 23\u201326). Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval. Proceedings of the 13th International Conference on Document Analysis and Recognition ICDAR 2015, Tunis, Tunisia.","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1214\/ss\/1177012580","article-title":"Francis Galton\u2019s account of the invention of correlation","volume":"4","author":"Stigler","year":"1989","journal-title":"Stat. Sci."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Senliol, B., Gulgezen, G., Yu, L., and Cataltepe, Z. (2008, January 27\u201329). Fast Correlation Based Filter (FCBF) with a different search strategy. Proceedings of the 23rd International Symposium on Computer and Information Sciences, ISCIS\u201908, Istanbul, Turkey.","DOI":"10.1109\/ISCIS.2008.4717949"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Afzal, M.Z., Capobianco, S., Malik, M.I., Marinai, S., Breuel, T.M., Dengel, A., and Liwicki, M. (2015, January 23\u201326). Deepdocclassifier: Document classification with deep convolutional neural network. Proceedings of the 13th International Conference on Document Analysis and Recognition (ICDAR), Tunis, Tunisia.","DOI":"10.1109\/ICDAR.2015.7333933"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"K\u00f6lsch, A., Afzal, M.Z., Ebbecke, M., and Liwicki, M. (2017, January 9\u201315). Real-time document image classification using deep CNN and extreme learning machines. Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan.","DOI":"10.1109\/ICDAR.2017.217"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Afzal, M.Z., K\u00f6lsch, A., Ahmed, S., and Liwicki, M. (2017, January 9\u201315). Cutting the error by half: Investigation of very deep cnn and advanced training strategies for document image classification. Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan.","DOI":"10.1109\/ICDAR.2017.149"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Sarkhel, R., and Nandi, A. (2019, January 10\u201316). Deterministic routing between layout abstractions for multi-scale classification of visually rich documents. Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China.","DOI":"10.24963\/ijcai.2019\/466"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Wiedemann, G., and Heyer, G. (2019). Multi-modal page stream segmentation with convolutional neural networks. Lang. Resour. Eval., 1\u201324.","DOI":"10.1007\/s10579-019-09476-2"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Lewis, D., Agam, G., Argamon, S., Frieder, O., Grossman, D., and Heard, J. (2006, January 6\u201311). Building a test collection for complex document information processing. Proceedings of the 29th Annual Int. ACM SIGIR Conference (SIGIR 2006), Seattle, WA, USA.","DOI":"10.1145\/1148170.1148307"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Arshad, H., Khan, M.A., Sharif, M.I., Yasmin, M., Tavares, J.M.R.S., Zhang, Y.-D., and Satapathy, S.C. (2020). A multilevel paradigm for deep convolutional neural network features selection with an application to human gait recognition. Expert Syst., e12541.","DOI":"10.1111\/exsy.12541"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Khan, M.A., Zhang, Y.-D., Khan, S.A., Attique, M., Rehman, A., and Seo, S. (2020). A resource conscious human action recognition framework using 26-layered deep convolutional neural network. Multimed. Tools Appl., 1\u201323.","DOI":"10.1007\/s11042-020-09408-1"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Khan, M.A., Sharif, M.I., Raza, M., Anjum, A., Saba, T., and Shad, S.A. (2019). Skin lesion segmentation and classification: A unified framework of deep neural network features fusion and selection. Expert Syst., e12497.","DOI":"10.1111\/exsy.12497"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"15929","DOI":"10.1007\/s00521-019-04514-0","article-title":"An integrated framework of skin lesion detection and recognition through saliency method and optimal deep neural network features selection","volume":"32","author":"Khan","year":"2020","journal-title":"Neural Comput. Appl."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/23\/6793\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:38:36Z","timestamp":1760179116000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/23\/6793"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,27]]},"references-count":53,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2020,12]]}},"alternative-id":["s20236793"],"URL":"https:\/\/doi.org\/10.3390\/s20236793","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,27]]}}}