{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:55:48Z","timestamp":1777704948234,"version":"3.51.4"},"reference-count":24,"publisher":"SAGE Publications","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2023,12,2]]},"abstract":"<jats:p>Leaf segmentation is crucial for plant recognition, especially for tree species identification. In natural environments, leaf segmentation can be very challenging due to the lack of prior information about leaves and the variability of backgrounds. In typical applications, supervised algorithms often require pixel-level annotation of regions, which can be labour-intensive and limited to identifying plant species using pre-labelled samples. On the other hand, traditional unsupervised image segmentation algorithms require specialised parameter tuning for leaf images to achieve optimal results. Therefore, this paper proposes an unsupervised leaf segmentation method that combines mutual information with neural networks to better generalise to unknown samples and adapt to variations in leaf shape and appearance to distinguish and identify different tree species. First, a model combining a Variational Autoencoder (VAE) and a segmentation network is used as a pre-segmenter to obtain dynamic masks. Secondly, the dynamic masks are combined with the segmentation masks generated by the mask generator module to construct the initial mask. Then, the patcher module uses the Mutual Information Minimum (MIM) loss as an optimisation objective to reconstruct independent regions based on this initial mask. The process of obtaining dynamic masks through pre-segmentation is unsupervised, and the entire experimental process does not involve any label information. The experimental method was performed on tree leaf images with a naturally complex background using the publicly available Pl@ntLeaves dataset. The results of the experiment showed that compared to existing excellent methods on this dataset, the IoU (Intersection over Union) index increased by 3.9%.<\/jats:p>","DOI":"10.3233\/jifs-232696","type":"journal-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T11:17:25Z","timestamp":1694776645000},"page":"10127-10139","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised leaf segmentation in complex backgrounds using mutual information minimization"],"prefix":"10.1177","volume":"45","author":[{"given":"Yijian","family":"Guo","sequence":"first","affiliation":[{"name":"School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiqiong","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"issue":"4","key":"10.3233\/JIFS-232696_ref1","doi-asserted-by":"crossref","first-page":"6443","DOI":"10.1007\/s11042-020-10038-w","article-title":"Deep convolutional neural network based plant species recognition through features of leaf","volume":"80","author":"Bisen","year":"2021","journal-title":"Multimedia Tools and Applications"},{"issue":"5","key":"10.3233\/JIFS-232696_ref3","first-page":"1549","article-title":"Tree leaves extraction in natural images: IEEE Transactions on Image Processing","volume":"24","author":"Grand-Brochier","year":"2015","journal-title":"Comparative study of preprocessing tools and segmentation methods"},{"key":"10.3233\/JIFS-232696_ref4","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.compag.2016.11.021","article-title":"Automatic crop detection under field conditions using the HSVcolour space and morphological operations","volume":"133","author":"Hamuda","year":"2017","journal-title":"Computers and Electronics in Agriculture"},{"key":"10.3233\/JIFS-232696_ref6","doi-asserted-by":"crossref","first-page":"105712","DOI":"10.1016\/j.compag.2020.105712","article-title":"Identification of cash crop diseases using automatic image segmentation algorithm and deep learning with expanded dataset","volume":"177","author":"Xiong","year":"2020","journal-title":"Computers and Electronics in Agriculture"},{"key":"10.3233\/JIFS-232696_ref7","doi-asserted-by":"crossref","first-page":"104962","DOI":"10.1016\/j.compag.2019.104962","article-title":"Segmentation of tomato leaf images based on adaptive clustering number of K-means algorithm","volume":"165","author":"Tian","year":"2019","journal-title":"Computers and Electronics in Agriculture"},{"key":"10.3233\/JIFS-232696_ref10","doi-asserted-by":"crossref","first-page":"101373","DOI":"10.1016\/j.ecoinf.2021.101373","article-title":"Convolutional neural network based encoder-decoder architectures for semantic segmentation of plants","volume":"64","author":"Kolhar","year":"2021","journal-title":"Ecological Informatics"},{"key":"10.3233\/JIFS-232696_ref12","unstructured":"Chen M. , Arti\u00e8res T. and Denoyer L. , Unsupervised object segmentation by redrawing, Advances in Neural Information Processing Systems 32 (2019)."},{"key":"10.3233\/JIFS-232696_ref13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00138-020-01130-0","article-title":"A novel approach for unsupervised image segmentation fusion of plant leaves based on G-mutual information","volume":"32","author":"Nikbakhsh","year":"2021","journal-title":"Machine Vision and Applications"},{"key":"10.3233\/JIFS-232696_ref14","unstructured":"Chen X. , et al., Infogan: Interpretable representation learning by information maximizing generative adversarial nets, Advances in Neural Information Processing Systems 29 (2016)."},{"issue":"2","key":"10.3233\/JIFS-232696_ref19","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1109\/83.902291","article-title":"Active contours without edges","volume":"10","author":"Chan","year":"2001","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.3233\/JIFS-232696_ref21","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1016\/j.compag.2019.04.038","article-title":"Maximum mutual information and Tsallis entropy for unsupervised segmentation of tree leaves in natural scenes","volume":"162","author":"Nikbakhsh","year":"2019","journal-title":"Computers and Electronics in Agriculture"},{"issue":"11","key":"10.3233\/JIFS-232696_ref22","doi-asserted-by":"crossref","first-page":"1721","DOI":"10.3390\/agronomy10111721","article-title":"Leaf segmentation and classification with a complicated background using deep learning","volume":"10","author":"Yang","year":"2020","journal-title":"Agronomy"},{"key":"10.3233\/JIFS-232696_ref23","doi-asserted-by":"crossref","first-page":"107511","DOI":"10.1016\/j.compag.2022.107511","article-title":"Modified U-Net for plant diseased leaf image segmentation","volume":"204","author":"Zhang","year":"2023","journal-title":"Computers and Electronics in Agriculture"},{"issue":"12","key":"10.3233\/JIFS-232696_ref24","first-page":"1","article-title":"Correction to: Rosette plant segmentation with leaf count using orthogonal transform and deep onvolutional neural network, [J]","volume":"31","author":"Kumar","year":"2020","journal-title":"Machine Vision and Applications"},{"key":"10.3233\/JIFS-232696_ref27","doi-asserted-by":"crossref","first-page":"105117","DOI":"10.1016\/j.compag.2019.105117","article-title":"Unsupervised image translation using adversarial networks for improved plant disease recognition","volume":"168","author":"Nazki","year":"2020","journal-title":"Computers and Electronics in Agriculture"},{"key":"10.3233\/JIFS-232696_ref30","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.sigpro.2018.10.004","article-title":"Variational probabilistic generative framework for single image super-resolution","volume":"156","author":"Wang","year":"2019","journal-title":"Signal Processing"},{"issue":"3","key":"10.3233\/JIFS-232696_ref32","doi-asserted-by":"crossref","first-page":"297","DOI":"10.2307\/1932409","article-title":"Measures of the amount of ecologic association between species","volume":"26","author":"Dice","year":"1945","journal-title":"Ecology"},{"issue":"3","key":"10.3233\/JIFS-232696_ref33","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1145\/1015706.1015720","article-title":"\u201cGrabCut\u201d interactive foreground extraction using iterated graph cuts","volume":"23","author":"Rother","year":"2004","journal-title":"ACM Transactions on Graphics (TOG)"},{"issue":"25","key":"10.3233\/JIFS-232696_ref34","doi-asserted-by":"crossref","first-page":"1369","DOI":"10.1007\/s00138-014-0612-7","article-title":"Automatic plant identification from photographs","volume":"6","author":"Yanikoglu","year":"2014","journal-title":"Mach Vis Appl"},{"key":"10.3233\/JIFS-232696_ref35","doi-asserted-by":"crossref","first-page":"106150","DOI":"10.1016\/j.compag.2021.106150","article-title":"Apple, peach, and pear flower detection using semantic segmentation network and shape constraint level set","volume":"185","author":"Sun","year":"2021","journal-title":"Computers and Electronics in Agriculture"},{"key":"10.3233\/JIFS-232696_ref36","first-page":"100696","article-title":"Using a multi-convolutional neural network to automatically identify small-sample tea leaf diseases","volume":"35","author":"Hu","year":"2022","journal-title":"Sustainable Computing: Informatics and Systems"},{"key":"10.3233\/JIFS-232696_ref37","doi-asserted-by":"crossref","first-page":"684328","DOI":"10.3389\/fpls.2021.684328","article-title":"Intelligent fruit yield estimation for orchards using deep learning based semantic segmentation techniques\u2014a review","volume":"12","author":"Maheswari","year":"2021","journal-title":"Frontiers in Plant Science"},{"key":"10.3233\/JIFS-232696_ref38","doi-asserted-by":"crossref","first-page":"7869","DOI":"10.1007\/s11042-016-3399-x","article-title":"Improved fuzzy clustering algorithm with non-local information for image segmentation","volume":"76","author":"Zhang","year":"2017","journal-title":"Multimedia Tools and Applications"},{"key":"10.3233\/JIFS-232696_ref39","doi-asserted-by":"crossref","first-page":"28483","DOI":"10.1007\/s11042-018-6005-6","article-title":"Soft computing approaches for image segmentation: A survey","volume":"77","author":"Chouhan","year":"2018","journal-title":"Multimedia Tools and Applications"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-232696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:42:29Z","timestamp":1777455749000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-232696"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,2]]},"references-count":24,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.3233\/jifs-232696","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,2]]}}}