Deep-plant: Plant identification with convolutional neural networks. Lee, S. H., Chan, C. S., Wilkin, P., & Remagnino, P. In pages 452--456, September, 2015. IEEE.
Paper doi abstract bibtex This paper studies convolutional neural networks (CNN) to learn unsupervised feature representations for 44 different plant species, collected at the Royal Botanic Gardens, Kew, England. To gain intuition on the chosen features from the CNN model (opposed to a ’black box’ solution), a visualisation technique based on the deconvolutional networks (DN) is utilized. It is found that venations of different order have been chosen to uniquely represent each of the plant species. Experimental results using these CNN features with different classifiers show consistency and superiority compared to the state-of-the art solutions which rely on hand-crafted features. Index Terms— plant classification, deep learning, feature visualisation Fig. 1: Sample of the 44 plant species employed in this paper.
@inproceedings{lee_deep-plant:_2015,
title = {Deep-plant: {Plant} identification with convolutional neural networks},
isbn = {978-1-4799-8339-1},
shorttitle = {Deep-plant},
url = {http://ieeexplore.ieee.org/document/7350839/},
doi = {10.1109/ICIP.2015.7350839},
abstract = {This paper studies convolutional neural networks (CNN) to learn unsupervised feature representations for 44 different plant species, collected at the Royal Botanic Gardens, Kew, England. To gain intuition on the chosen features from the CNN model (opposed to a ’black box’ solution), a visualisation technique based on the deconvolutional networks (DN) is utilized. It is found that venations of different order have been chosen to uniquely represent each of the plant species. Experimental results using these CNN features with different classifiers show consistency and superiority compared to the state-of-the art solutions which rely on hand-crafted features. Index Terms— plant classification, deep learning, feature visualisation Fig. 1: Sample of the 44 plant species employed in this paper.},
language = {en},
urldate = {2018-03-25TZ},
publisher = {IEEE},
author = {Lee, Sue Han and Chan, Chee Seng and Wilkin, Paul and Remagnino, Paolo},
month = sep,
year = {2015},
pages = {452--456}
}
Downloads: 0
{"_id":"QHX35Gj3tMBTQWohc","bibbaseid":"lee-chan-wilkin-remagnino-deepplantplantidentificationwithconvolutionalneuralnetworks-2015","downloads":0,"creationDate":"2018-04-15T14:41:43.824Z","title":"Deep-plant: Plant identification with convolutional neural networks","author_short":["Lee, S. H.","Chan, C. S.","Wilkin, P.","Remagnino, P."],"year":2015,"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/pvhuy","bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Deep-plant: Plant identification with convolutional neural networks","isbn":"978-1-4799-8339-1","shorttitle":"Deep-plant","url":"http://ieeexplore.ieee.org/document/7350839/","doi":"10.1109/ICIP.2015.7350839","abstract":"This paper studies convolutional neural networks (CNN) to learn unsupervised feature representations for 44 different plant species, collected at the Royal Botanic Gardens, Kew, England. To gain intuition on the chosen features from the CNN model (opposed to a ’black box’ solution), a visualisation technique based on the deconvolutional networks (DN) is utilized. It is found that venations of different order have been chosen to uniquely represent each of the plant species. Experimental results using these CNN features with different classifiers show consistency and superiority compared to the state-of-the art solutions which rely on hand-crafted features. Index Terms— plant classification, deep learning, feature visualisation Fig. 1: Sample of the 44 plant species employed in this paper.","language":"en","urldate":"2018-03-25TZ","publisher":"IEEE","author":[{"propositions":[],"lastnames":["Lee"],"firstnames":["Sue","Han"],"suffixes":[]},{"propositions":[],"lastnames":["Chan"],"firstnames":["Chee","Seng"],"suffixes":[]},{"propositions":[],"lastnames":["Wilkin"],"firstnames":["Paul"],"suffixes":[]},{"propositions":[],"lastnames":["Remagnino"],"firstnames":["Paolo"],"suffixes":[]}],"month":"September","year":"2015","pages":"452--456","bibtex":"@inproceedings{lee_deep-plant:_2015,\n\ttitle = {Deep-plant: {Plant} identification with convolutional neural networks},\n\tisbn = {978-1-4799-8339-1},\n\tshorttitle = {Deep-plant},\n\turl = {http://ieeexplore.ieee.org/document/7350839/},\n\tdoi = {10.1109/ICIP.2015.7350839},\n\tabstract = {This paper studies convolutional neural networks (CNN) to learn unsupervised feature representations for 44 different plant species, collected at the Royal Botanic Gardens, Kew, England. To gain intuition on the chosen features from the CNN model (opposed to a ’black box’ solution), a visualisation technique based on the deconvolutional networks (DN) is utilized. It is found that venations of different order have been chosen to uniquely represent each of the plant species. Experimental results using these CNN features with different classifiers show consistency and superiority compared to the state-of-the art solutions which rely on hand-crafted features. Index Terms— plant classification, deep learning, feature visualisation Fig. 1: Sample of the 44 plant species employed in this paper.},\n\tlanguage = {en},\n\turldate = {2018-03-25TZ},\n\tpublisher = {IEEE},\n\tauthor = {Lee, Sue Han and Chan, Chee Seng and Wilkin, Paul and Remagnino, Paolo},\n\tmonth = sep,\n\tyear = {2015},\n\tpages = {452--456}\n}\n\n","author_short":["Lee, S. H.","Chan, C. S.","Wilkin, P.","Remagnino, P."],"key":"lee_deep-plant:_2015","id":"lee_deep-plant:_2015","bibbaseid":"lee-chan-wilkin-remagnino-deepplantplantidentificationwithconvolutionalneuralnetworks-2015","role":"author","urls":{"Paper":"http://ieeexplore.ieee.org/document/7350839/"},"downloads":0},"search_terms":["deep","plant","plant","identification","convolutional","neural","networks","lee","chan","wilkin","remagnino"],"keywords":[],"authorIDs":[],"dataSources":["E2tDnyqghkeNYrDGK"]}