{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T05:10:54Z","timestamp":1784783454505,"version":"3.55.0"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Color Vision Deficiency (CVD) affects over 300 million individuals worldwide, with protanopia and deuteranopia being the most common subtypes, causing red\u2013green confusion. This study leverages machine learning to (a) classify reference (considered as normal vision) and simulated protanopia and deuteranopia Ishihara plate images, (b) generate corresponding enhanced versions of these images, and (c) provide improved textbook diagrams (from NCERT books) and other pseudochromatic figures for CVD students, validated through feedback from diagnosed individuals. Tritanopia and milder forms of CVD were excluded in this study. A dataset of 1,400 Ishihara plates was processed to simulate protanopia and deuteranopia perception via standard Red Green Blue (sRGB) to long-, medium-, and short-wavelength cone (LMS) modeling. Enhanced images were generated using a daltonization function defined by the error between reference and simulated images, with enhancement strength (<jats:italic>\u03b1<\/jats:italic>) optimized to maximize contrast gain while minimizing distortion. Feature embeddings from ResNet-50, EfficientNet-B0, and DenseNet-201 were fused and reduced via PCA, followed by One-vs-All (OvA) (classifiers: linear support vector machine, logistic regression, and decision tree), random forest, gradient boosting, and neural network. Results showed optimal enhancement at <jats:italic>\u03b1<\/jats:italic> =\u202f0.54 for deuteranopia and 0.64 for protanopia, achieving contrast gains of 69.6 and 64.3, respectively, with minimal color distortion (\u0394E\u202f\u2248\u202f4.9) and negligible clipping (&amp;lt;0.002). The OvA strategy achieved 99.7% accuracy, while MLP reached 100% across metrics. Surveys with 15 diagnosed students confirmed substantial perceptual improvement: recognition of previously unreadable digits and symbols increased from &amp;lt;20% to full visibility, with mean ratings above 4\/5 for enhanced images. The OvA technique integrated with daltonization can assist in enhancing Ishihara and educational images in real time.<\/jats:p>","DOI":"10.3389\/frai.2025.1676644","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T05:31:39Z","timestamp":1760679099000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Ishihara and educational images using machine learning: toward accessible learning for colorblind individuals"],"prefix":"10.3389","volume":"8","author":[{"given":"Aahan Ritesh","family":"Prajapati","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajay","family":"Goyal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.3390\/sym17071046","article-title":"Improved filter designs using image processing techniques for color vision deficiency (CVD) types","volume":"17","author":"Akal\u0131n","year":"2025","journal-title":"Symmetry"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"7579","DOI":"10.3390\/app14177579","article-title":"EEG-based methods for diagnosing color vision deficiency: a comprehensive review","volume":"14","author":"AlEssa","year":"2024","journal-title":"Appl. Sci."},{"key":"ref3","article-title":"Periodic table of elements","year":"2025"},{"key":"ref4","first-page":"129","author":"Ananto","year":"2011"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1186\/s12886-017-0579-z","article-title":"Development and validation of a questionnaire assessing the quality of life impact of colour blindness (CBQoL)","volume":"17","author":"Barry","year":"2017","journal-title":"BMC Ophthalmol."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/s13721-025-00519-z","article-title":"The innovative DEA application for color vision self-re-education of eyes suffering from dyschromatopsia","volume":"14","author":"Bile","year":"2025","journal-title":"Netw. Model. Anal. Health Inform. Bioinform."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/s42600-023-00263-1","article-title":"Innovative and non-invasive method for the diagnosis of dyschromatopsia and the re-education of the eyes","volume":"39","author":"Bile","year":"2023","journal-title":"Res. Biomed. Eng."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"2647","DOI":"10.1364\/JOSAA.14.002647","article-title":"Computerized simulation of color appearance for dichromats","volume":"14","author":"Brettel","year":"1997","journal-title":"JOSA A"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"11109","DOI":"10.1007\/s11063-023-11367-1","article-title":"Swin-fusion: swin-transformer with feature fusion for human action recognition","volume":"55","author":"Chen","year":"2023","journal-title":"Neural. Process. Lett."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"154466","DOI":"10.1109\/ACCESS.2019.2948653","article-title":"Optimal color correction based on image analysis for color vision deficiency","volume":"7","author":"Choi","year":"2019","journal-title":"IEEE Access"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"396","DOI":"10.3390\/diagnostics14040396","article-title":"Validation of a new digital and automated color perception test","volume":"14","author":"Fanlo-Zarazaga","year":"2024","journal-title":"Diagnostics"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"116","DOI":"10.3390\/jimaging6110116","article-title":"Individualised halo-free gradient-domain colour image Daltonisation","volume":"6","author":"Farup","year":"2020","journal-title":"J. Imaging"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1007\/979-8-8688-0152-5_3","article-title":"Low vision and color blindness","volume-title":"Practical web accessibility: A comprehensive guide to digital inclusion","author":"Firth","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1109\/TKDE.2008.181","article-title":"Adapted one-versus-all decision trees for data stream classification","volume":"21","author":"Hashemi","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref15","article-title":"Deep residual learning for image recognition","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"He","year":"2015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1608.06993","article-title":"Densely connected convolutional","author":"Huang","year":"2018","journal-title":"Networks"},{"key":"ref17","first-page":"1","article-title":"The genetics of color vision and congenital color deficiencies","volume-title":"Human color vision","author":"Hunt","year":"2016"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1002\/9781119975595","volume-title":"Measuring colour","author":"Hunt","year":"2011"},{"key":"ref19","article-title":"Multimedia systems and equipment \u2013 colour measurement and management \u2013 part 2-1: colour management \u2013 default RGB colour space \u2013 sRGB: amendment 1","year":"1999"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"20150202","DOI":"10.1098\/rsta.2015.0202","article-title":"Principal component analysis: a review and recent developments","volume":"374","author":"Jolliffe","year":"2016","journal-title":"Philos. Transact. A Math. Phys. Eng. Sci."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"892","DOI":"10.1016\/j.identj.2023.12.009","article-title":"A comparative study of the sensitivity and specificity of the Ishihara test with various displays","volume":"74","author":"Klinke","year":"2024","journal-title":"Int. Dent. J."},{"key":"ref22","first-page":"27","article-title":"Multiclass date fruit prediction using SVM and logistic regression with OVO and OVR","volume":"3","author":"Kumar","year":"2024","journal-title":"J. Big Data Technol Business Anal."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"110186","DOI":"10.1016\/j.compeleceng.2025.110186","article-title":"An adaptive feature fusion framework of CNN and GNN for histopathology images classification","volume":"123","author":"Li","year":"2025","journal-title":"Comput. Electr. Eng."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"4358","DOI":"10.1016\/j.eswa.2011.09.156","article-title":"Using OVA modeling to improve classification performance for large datasets","volume":"39","author":"Lutu","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1109\/TVCG.2009.113","article-title":"A physiologically-based model for simulation of color vision deficiency","volume":"15","author":"Machado","year":"2009","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref26","first-page":"279","author":"Manasa","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1186\/s12911-025-02894-z","article-title":"Improving stroke risk prediction by integrating XGBoost, optimized principal component analysis, and explainable artificial intelligence","volume":"25","author":"Mochurad","year":"2025","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"108664","DOI":"10.1016\/j.visres.2025.108664","article-title":"Correlation between parameters estimated by the colour assessment and diagnosis and the Cambridge colour test in color discrimination evaluation","volume":"235","author":"Parente","year":"2025","journal-title":"Vis. Res."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"3282","DOI":"10.21917\/ijivp.2024.0467","article-title":"Comprehensive color vision enhancement for color vision deficiency: a tensorflow and keras based approach","volume":"14","author":"Pendhari","year":"2024","journal-title":"ICTACT J. Image Video Proces."},{"key":"ref30","volume-title":"India physical map","year":"2024"},{"key":"ref31","article-title":"Animal cell structure stock vector. Illustration of graphic \u221265486924","author":"Radu","year":"2025"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"137","DOI":"10.4018\/979-8-3693-7888-5.ch005","article-title":"Machine learning techniques for automatic diagnosis of Glaucoma detection","volume-title":"Revolutionizing healthcare experience with digital medical tourism","author":"Ramkumar","year":"2025"},{"key":"ref33","volume-title":"CUD-NET: Color Universal Design Neural Filter for the Color Weakness","author":"Seo","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"010503-1-010503\u201312","DOI":"10.2352\/J.Percept.Imaging.2018.1.1.010503","article-title":"Multiscale daltonization in the gradient domain","volume":"1","author":"Simon-Liedtke","year":"2018","journal-title":"J. Percept. Imaging"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"2409","DOI":"10.1007\/s11831-022-09870-0","article-title":"A review of deep transfer learning approaches for class-wise prediction of Alzheimer\u2019s disease using MRI images","volume":"30","author":"Sisodia","year":"2023","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1016\/S0042-6989(00)00021-3","article-title":"The spectral sensitivities of the middle- and long-wavelength-sensitive cones derived from measurements in observers of known genotype","volume":"40","author":"Stockman","year":"2000","journal-title":"Vis. Res."},{"key":"ref37","first-page":"97","article-title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","volume-title":"International conference on machine learning","author":"Tan","year":"2020"},{"key":"ref38","author":"Tecson","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"2369","DOI":"10.1117\/1.1787531","article-title":"Color image enhancement using a multiple-scale opponent neural network","volume":"43","author":"Tian","year":"2004","journal-title":"Opt. Eng."},{"key":"ref40","first-page":"725","author":"Tillem","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"20894","DOI":"10.1109\/JSEN.2025.3559438","article-title":"Effects of image normalization on CNN-based EEG\u2013EMG fusion","volume":"25","author":"Tryon","year":"2025","journal-title":"IEEE Sensors J."},{"key":"ref42","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1007\/978-3-030-38040-3_18","article-title":"Performance analysis of automated detection of diabetic retinopathy using machine learning and deep learning techniques","volume-title":"Innovative data communication technologies and application","author":"Varghese","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"105922","DOI":"10.1016\/j.knosys.2020.105922","article-title":"A hybrid scheme-based one-vs-all decision trees for multi-class classification tasks","volume":"198","author":"Yan","year":"2020","journal-title":"Knowl.-Based Syst."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1676644\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T05:31:42Z","timestamp":1760679102000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1676644\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":43,"alternative-id":["10.3389\/frai.2025.1676644"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1676644","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,17]]},"article-number":"1676644"}}