{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T22:40:38Z","timestamp":1772664038330,"version":"3.50.1"},"reference-count":89,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2021,6,14]],"date-time":"2021-06-14T00:00:00Z","timestamp":1623628800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems"],"published-print":{"date-parts":[[2021,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Improvement of deep learning algorithms in smart agriculture is important to support the early detection of plant diseases, thereby improving crop yields. Data acquisition for machine learning applications is an expensive task due to the requirements of expert knowledge and professional equipment. The usability of any application in a real\u2010world setting is often limited by unskilled users and the limitations of devices used for acquiring images for classification. We aim to improve the accuracy of deep learning models on low\u2010quality test images using data augmentation techniques for neural network training. We generate synthetic images with a modified colour value distribution to expand the trainable image colour space and to train the neural network to recognize important colour\u2010based features, which are less sensitive to the deficiencies of low\u2010quality images such as those affected by blurring or motion. This paper introduces a novel image colour histogram transformation technique for generating synthetic images for data augmentation in image classification tasks. The approach is based on the convolution of the Chebyshev orthogonal functions with the probability distribution functions of image colour histograms. To validate our proposed model, we used four methods (resolution down\u2010sampling, Gaussian blurring, motion blur, and overexposure) for reducing image quality from the Cassava leaf disease dataset. The results based on the modified MobileNetV2 neural network showed a statistically significant improvement of cassava leaf disease recognition accuracy on lower\u2010quality testing images when compared with the baseline network. The model can be easily deployed for recognizing and detecting cassava leaf diseases in lower quality images, which is a major factor in practical data acquisition.<\/jats:p>","DOI":"10.1111\/exsy.12746","type":"journal-article","created":{"date-parts":[[2021,6,14]],"date-time":"2021-06-14T14:33:50Z","timestamp":1623681230000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":150,"title":["Cassava disease recognition from <scp>low\u2010quality<\/scp> images using enhanced data augmentation model and deep learning"],"prefix":"10.1111","volume":"38","author":[{"given":"Olusola Oluwakemi","family":"Abayomi\u2010Alli","sequence":"first","affiliation":[{"name":"Department of Software Engineering Kaunas University of Technology  Kaunas Lithuania"}]},{"given":"Robertas","family":"Dama\u0161evi\u010dius","sequence":"additional","affiliation":[{"name":"Department of Software Engineering Kaunas University of Technology  Kaunas Lithuania"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3556-9331","authenticated-orcid":false,"given":"Sanjay","family":"Misra","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering Atilim University  Ankara Turkey"},{"name":"Department of Electrical and Information Engineering Covenant University  Ota Nigeria"}]},{"given":"Rytis","family":"Maskeli\u016bnas","sequence":"additional","affiliation":[{"name":"Faculty of Applied Mathematics Silesian University of Technology  Gliwice Poland"},{"name":"Department of Applied Informatics Vytautas Magnus University  Kaunas Lithuania"}]}],"member":"311","published-online":{"date-parts":[[2021,6,14]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"crossref","unstructured":"Abayomi\u2010Alli O. O. Damasevicius R. Maskeliunas R. &Abayomi\u2010Alli A.(2020).BiLSTM with data augmentation using interpolation methods to improve early detection of parkinson disease. In 2020 federated conference on computer science and information systems FedCSIS 2020 Sofia Bulgaria (pp. 371\u2013380).","DOI":"10.15439\/2020F188"},{"key":"e_1_2_8_3_1","doi-asserted-by":"crossref","unstructured":"Abayomi\u2010Alli O. O. Dama\u0161evi\u010dius R. Wieczorek M. &Wo\u017aniak M.(2020).Data augmentation using principal component resampling for image recognition by deep learning. In 19th international conference on artificial intelligence and soft computing ICAISC 2020 Zakopane Poland LNAI 12416 (pp. 39\u201348).","DOI":"10.1007\/978-3-030-61534-5_4"},{"issue":"4","key":"e_1_2_8_4_1","first-page":"114","article-title":"A machine learning model for field diagnosis of cassava mosaic disease","volume":"8","author":"Aduwo J. R.","year":"2019","journal-title":"International Journal of Computer and Information (IJCIT)"},{"key":"e_1_2_8_5_1","unstructured":"Afrimash. (2016).Economic importance of cassava production in Nigeria. Retrieved fromhttps:\/\/www.afrimash.com\/economic-importance-of-cassava-production-in-nigeria\/"},{"issue":"11","key":"e_1_2_8_6_1","first-page":"457","article-title":"Economic impacts of cassava research and extension in Malawi and Zambia. Journal development","volume":"5","author":"Alene D.","year":"2013","journal-title":"Agriculture. Economics"},{"key":"e_1_2_8_7_1","doi-asserted-by":"crossref","unstructured":"Ali\u2010Gombe A. Elyan E. &Jayne C.(2019).Multiple fake classes GAN for data augmentation in face image dataset. In 2019 international joint conference on neural networks (IJCNN) (pp. 1\u20138).","DOI":"10.1109\/IJCNN.2019.8851953"},{"issue":"8","key":"e_1_2_8_8_1","first-page":"486","article-title":"An efficient deep learning model for olive diseases detection","volume":"10","author":"Alruwaili M.","year":"2019","journal-title":"International Journal of Advanced Computer Science and Applications (IJACSA)"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inpa.2019.12.002"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.biosystemseng.2018.05.013"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2018.08.013"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.biosystemseng.2019.02.002"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8030324"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1080\/08839514.2017.1315516"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.10.020"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolecon.2013.05.006"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-016-1236-x"},{"issue":"2","key":"e_1_2_8_18_1","first-page":"45","article-title":"A novel neural networks\u2010based texture image processing algorithm for orange defects classification","volume":"13","author":"Capizzi G.","year":"2016","journal-title":"International Journal of Computer Science and Applications"},{"key":"e_1_2_8_19_1","unstructured":"Cassava Disease Data. (2019).Cassava Disease Data. Retrieved fromhttps:\/\/www.kaggle.com\/c\/cassava-disease\/data"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym11030343"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2800685"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2017.01741"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2019.100616"},{"key":"e_1_2_8_24_1","doi-asserted-by":"crossref","unstructured":"Dhawale C. A. Misra S. Thakur S. &Dattatraya J. N.(2016).Analysis of nutritional deficiency in citrus species tree leaf using image processing. International conference on advances in computing communications and informatics ICACCI'2016 (pp. 2248\u20132252).","DOI":"10.1109\/ICACCI.2016.7732386"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.06.012"},{"key":"e_1_2_8_26_1","doi-asserted-by":"crossref","unstructured":"Dodge S. &Karam L.(2016).Understanding how image quality affects deep neural networks. In 2016 eighth international conference on quality of multimedia experience (QoMEX) (pp. 1\u20136). IEEE.","DOI":"10.1109\/QoMEX.2016.7498955"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2019.104967"},{"key":"e_1_2_8_28_1","unstructured":"EkinD. C. BarretZ. DandelionM. VijayV. &QuocV. L.(2018).AutoAugment: Learning augmentation policies from data. ArXiv preprint;2018."},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.21608\/ijicis.2016.19822"},{"issue":"7","key":"e_1_2_8_30_1","first-page":"166","article-title":"Detection and classification of cassava diseases using machine learning","volume":"8","author":"Emuoyibofarhe O.","year":"2019","journal-title":"International Journal of Computer Science and Software Engineering (IJCSSE)"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2019.105162"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.7896\/j.1612"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.3390\/s17092022"},{"key":"e_1_2_8_34_1","doi-asserted-by":"crossref","unstructured":"Gabryel M. &Dama\u0161evi\u010dius R.(2017)The image classification with different types of image features. In: Artificial intelligence and soft computing. ICAISC 2017 506.","DOI":"10.1007\/978-3-319-59063-9_44"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-018-1949-x"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2019.04.011"},{"key":"e_1_2_8_37_1","doi-asserted-by":"crossref","unstructured":"Giridhara P. K. B. Chinmaya M. Venkataramana R. K. M. Bukhari S. S. &Dengel A.(2019).A study of various text augmentation techniques for relation classification in free text. In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods.","DOI":"10.5220\/0007311003600367"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19194161"},{"key":"e_1_2_8_39_1","unstructured":"Hendrycks D. &Dietterich T.G.(2019)Benchmarking neural network robustness to common corruptions and perturbations. CoRR abs\/1903.12261"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.suscom.2019.100353"},{"key":"e_1_2_8_41_1","first-page":"979","volume-title":"AMIA annual symposium proceedings","author":"Hussain Z.","year":"2017"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.06.025"},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2018.07.032"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2914929"},{"key":"e_1_2_8_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2019.104948"},{"key":"e_1_2_8_46_1","first-page":"105933","article-title":"Attention embedded residual CNN for disease detection in tomato leaves","volume":"86","author":"Karthik R.","year":"2019","journal-title":"Applied Soft Computing"},{"key":"e_1_2_8_47_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics10080565"},{"key":"e_1_2_8_48_1","unstructured":"Kingma D. P. &Ba J. L.(2015).Adam: A method for stochastic optimization. 3rd international conference on learning representations ICLR 2015\u2014Conference track proceedings."},{"key":"e_1_2_8_49_1","doi-asserted-by":"publisher","DOI":"10.2478\/amcs-2018-0056"},{"key":"e_1_2_8_50_1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"2","author":"Krizhevsky A.","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_51_1","doi-asserted-by":"publisher","DOI":"10.1515\/znc-1981-9-1040"},{"key":"e_1_2_8_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2696121"},{"key":"e_1_2_8_53_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20030578"},{"key":"e_1_2_8_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2019.01.034"},{"key":"e_1_2_8_55_1","doi-asserted-by":"crossref","unstructured":"Long Y. &Liu C.(2019).Research on deep learning method of crop disease identification. ACM International Conference Proceeding Series.","DOI":"10.1145\/3371425.3371497"},{"issue":"4","key":"e_1_2_8_56_1","first-page":"475","article-title":"Real time path finding for assisted living using deep learning","volume":"24","author":"Mal\u016bkas U.","year":"2018","journal-title":"Journal of Universal Computer Science"},{"key":"e_1_2_8_57_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1019\/1\/012026"},{"key":"e_1_2_8_58_1","unstructured":"Mwebaze E. Gebru T. Frome A. Nsumba S. &Tusubira J.(2019).iCassava 2019 fine\u2010grained visual categorization challenge. arXiv preprint arXiv:1908.02900."},{"key":"e_1_2_8_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2019.105117"},{"key":"e_1_2_8_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301272"},{"key":"e_1_2_8_61_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym10110648"},{"key":"e_1_2_8_62_1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.352"},{"key":"e_1_2_8_63_1","doi-asserted-by":"crossref","unstructured":"Pawar R. &Jadhav A.(2017).Pomogranite disease detection and classification. 2017 IEEE International Conference on Power Control Signals and Instrumentation Engineering (ICPCSI) Chennai India.","DOI":"10.1109\/ICPCSI.2017.8392162"},{"key":"e_1_2_8_64_1","doi-asserted-by":"publisher","DOI":"10.4238\/2014.April.30.7"},{"key":"e_1_2_8_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2018.04.002"},{"key":"e_1_2_8_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2019.105093"},{"key":"e_1_2_8_67_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0734-189X(87)80186-X"},{"key":"e_1_2_8_68_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2017.01852"},{"key":"e_1_2_8_69_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2019.00272"},{"key":"e_1_2_8_70_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12183"},{"key":"e_1_2_8_71_1","first-page":"291","article-title":"Quantification of histochemical stains by color deconvolution","volume":"4","author":"Ruifrok A.","year":"2001","journal-title":"Analytical and Quantitative Cytology and Histology"},{"key":"e_1_2_8_72_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-71294-2"},{"key":"e_1_2_8_73_1","doi-asserted-by":"publisher","DOI":"10.3390\/plants8110468"},{"key":"e_1_2_8_74_1","doi-asserted-by":"crossref","unstructured":"Sandler M. Howard A. Zhu M. Zhmoginov A. &Chen L.(2018).MobileNetV2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE computer society conference on computer vision and pattern recognition (pp. 4510\u20134520).","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_2_8_75_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"e_1_2_8_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2907383"},{"key":"e_1_2_8_77_1","unstructured":"Tabernik D. &Skocaj D.(2019).Deep learning for large\u2010scale traffic\u2010sign detection and recognition. CoRR abs\/1904.00649."},{"key":"e_1_2_8_78_1","doi-asserted-by":"crossref","unstructured":"Takalkar M. A. &Xu M.(2017).Image based facial micro\u2010expression recognition using deep learning on small datasets. In 2017 international conference on digital image computing: Techniques and applications (DICTA) (pp. 1\u20137).","DOI":"10.1109\/DICTA.2017.8227443"},{"key":"e_1_2_8_79_1","first-page":"298","volume-title":"International conference on recent developments in science, engineering and technology","author":"Temiatse O. S.","year":"2017"},{"key":"e_1_2_8_80_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2018.03.032"},{"key":"e_1_2_8_81_1","doi-asserted-by":"publisher","DOI":"10.3390\/app9081601"},{"key":"e_1_2_8_82_1","doi-asserted-by":"publisher","DOI":"10.3390\/app9224898"},{"key":"e_1_2_8_83_1","first-page":"2579","article-title":"Visualizing Data Using t\u2010SNE","volume":"9","author":"Van der Maaten L. J. P.","year":"2008","journal-title":"Journal of Machine Learning Research."},{"key":"e_1_2_8_84_1","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/2917536"},{"key":"e_1_2_8_85_1","volume-title":"An empirical analysis of dropout in piecewise linear networks. In International Conference on Learning Representations 2014","author":"Warde\u2010Farley D.","year":"2014"},{"key":"e_1_2_8_86_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.10.009"},{"key":"e_1_2_8_87_1","doi-asserted-by":"crossref","unstructured":"Wu Y. Zhang Z. &Wang G. (2019).Unsupervised deep feature transfer for low resolution image classification. In Proceedings of the IEEE International Conference on Computer Vision Workshops Seoul Korea (South).","DOI":"10.1109\/ICCVW.2019.00136"},{"key":"e_1_2_8_88_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19143195"},{"key":"e_1_2_8_89_1","doi-asserted-by":"publisher","DOI":"10.3390\/e19070313"},{"key":"e_1_2_8_90_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.12.013"}],"container-title":["Expert Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.12746","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/exsy.12746","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.12746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T19:37:13Z","timestamp":1693337833000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/exsy.12746"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,14]]},"references-count":89,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["10.1111\/exsy.12746"],"URL":"https:\/\/doi.org\/10.1111\/exsy.12746","archive":["Portico"],"relation":{},"ISSN":["0266-4720","1468-0394"],"issn-type":[{"value":"0266-4720","type":"print"},{"value":"1468-0394","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,14]]},"assertion":[{"value":"2020-12-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-05-18","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-06-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e12746"}}