Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386769085> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4386769085 endingPage "13" @default.
- W4386769085 startingPage "1" @default.
- W4386769085 abstract "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%." @default.
- W4386769085 created "2023-09-16" @default.
- W4386769085 creator A5036726873 @default.
- W4386769085 creator A5044394722 @default.
- W4386769085 creator A5064745514 @default.
- W4386769085 creator A5067992188 @default.
- W4386769085 date "2023-09-13" @default.
- W4386769085 modified "2023-09-26" @default.
- W4386769085 title "Unsupervised leaf segmentation in complex backgrounds using mutual information minimization" @default.
- W4386769085 cites W1987869189 @default.
- W4386769085 cites W2003400461 @default.
- W4386769085 cites W2116040950 @default.
- W4386769085 cites W2124351162 @default.
- W4386769085 cites W2297866175 @default.
- W4386769085 cites W2569479441 @default.
- W4386769085 cites W2802655778 @default.
- W4386769085 cites W2896335160 @default.
- W4386769085 cites W2943078549 @default.
- W4386769085 cites W2969591642 @default.
- W4386769085 cites W2996289226 @default.
- W4386769085 cites W3081995103 @default.
- W4386769085 cites W3091795593 @default.
- W4386769085 cites W3093238181 @default.
- W4386769085 cites W3095523211 @default.
- W4386769085 cites W3159149035 @default.
- W4386769085 cites W3175992990 @default.
- W4386769085 cites W3186492510 @default.
- W4386769085 cites W4313420555 @default.
- W4386769085 doi "https://doi.org/10.3233/jifs-232696" @default.
- W4386769085 hasPublicationYear "2023" @default.
- W4386769085 type Work @default.
- W4386769085 citedByCount "0" @default.
- W4386769085 crossrefType "journal-article" @default.
- W4386769085 hasAuthorship W4386769085A5036726873 @default.
- W4386769085 hasAuthorship W4386769085A5044394722 @default.
- W4386769085 hasAuthorship W4386769085A5064745514 @default.
- W4386769085 hasAuthorship W4386769085A5067992188 @default.
- W4386769085 hasConcept C101738243 @default.
- W4386769085 hasConcept C113174947 @default.
- W4386769085 hasConcept C124504099 @default.
- W4386769085 hasConcept C125308379 @default.
- W4386769085 hasConcept C134306372 @default.
- W4386769085 hasConcept C144133560 @default.
- W4386769085 hasConcept C152139883 @default.
- W4386769085 hasConcept C153180895 @default.
- W4386769085 hasConcept C154945302 @default.
- W4386769085 hasConcept C162853370 @default.
- W4386769085 hasConcept C33923547 @default.
- W4386769085 hasConcept C41008148 @default.
- W4386769085 hasConcept C50644808 @default.
- W4386769085 hasConcept C89600930 @default.
- W4386769085 hasConceptScore W4386769085C101738243 @default.
- W4386769085 hasConceptScore W4386769085C113174947 @default.
- W4386769085 hasConceptScore W4386769085C124504099 @default.
- W4386769085 hasConceptScore W4386769085C125308379 @default.
- W4386769085 hasConceptScore W4386769085C134306372 @default.
- W4386769085 hasConceptScore W4386769085C144133560 @default.
- W4386769085 hasConceptScore W4386769085C152139883 @default.
- W4386769085 hasConceptScore W4386769085C153180895 @default.
- W4386769085 hasConceptScore W4386769085C154945302 @default.
- W4386769085 hasConceptScore W4386769085C162853370 @default.
- W4386769085 hasConceptScore W4386769085C33923547 @default.
- W4386769085 hasConceptScore W4386769085C41008148 @default.
- W4386769085 hasConceptScore W4386769085C50644808 @default.
- W4386769085 hasConceptScore W4386769085C89600930 @default.
- W4386769085 hasLocation W43867690851 @default.
- W4386769085 hasOpenAccess W4386769085 @default.
- W4386769085 hasPrimaryLocation W43867690851 @default.
- W4386769085 hasRelatedWork W2292254049 @default.
- W4386769085 hasRelatedWork W2592385986 @default.
- W4386769085 hasRelatedWork W2610906757 @default.
- W4386769085 hasRelatedWork W2772780115 @default.
- W4386769085 hasRelatedWork W2897995864 @default.
- W4386769085 hasRelatedWork W2998168123 @default.
- W4386769085 hasRelatedWork W3099179464 @default.
- W4386769085 hasRelatedWork W4281924768 @default.
- W4386769085 hasRelatedWork W4287995534 @default.
- W4386769085 hasRelatedWork W4309838615 @default.
- W4386769085 isParatext "false" @default.
- W4386769085 isRetracted "false" @default.
- W4386769085 workType "article" @default.