{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/using-deep-learning-for-image-based-plant","title":"Using Deep Learning for Image-Based Plant Disease Detection","arxiv_id":"1604.03169","date":"2016-04-11","proceeding":null,"authors":["Sharada Prasanna Mohanty","David Hughes","Marcel Salathe"],"abstract":"Crop diseases are a major threat to food security, but their rapid\nidentification remains difficult in many parts of the world due to the lack of\nthe necessary infrastructure. The combination of increasing global smartphone\npenetration and recent advances in computer vision made possible by deep\nlearning has paved the way for smartphone-assisted disease diagnosis. Using a\npublic dataset of 54,306 images of diseased and healthy plant leaves collected\nunder controlled conditions, we train a deep convolutional neural network to\nidentify 14 crop species and 26 diseases (or absence thereof). The trained\nmodel achieves an accuracy of 99.35% on a held-out test set, demonstrating the\nfeasibility of this approach. When testing the model on a set of images\ncollected from trusted online sources - i.e. taken under conditions different\nfrom the images used for training - the model still achieves an accuracy of\n31.4%. While this accuracy is much higher than the one based on random\nselection (2.6%), a more diverse set of training data is needed to improve the\ngeneral accuracy. Overall, the approach of training deep learning models on\nincreasingly large and publicly available image datasets presents a clear path\ntowards smartphone-assisted crop disease diagnosis on a massive global scale.","url_abs":"http://arxiv.org/abs/1604.03169v2","url_pdf":"http://arxiv.org/pdf/1604.03169v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"using-deep-learning-for-image-based-plant","repo_url":"https://github.com/ShashankMasade/major-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"using-deep-learning-for-image-based-plant","repo_url":"https://github.com/abhimangalms/PlantDoctor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"using-deep-learning-for-image-based-plant","repo_url":"https://github.com/deepcpatel/GreenDoc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"using-deep-learning-for-image-based-plant","repo_url":"https://github.com/nyak10/mwc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"using-deep-learning-for-image-based-plant","repo_url":"https://github.com/sabrisangjaya/plantdoctor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.03169","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}