Filters








771 Hits in 4.8 sec

Human experts vs. machines in taxa recognition [article]

Johanna Ärje, Jenni Raitoharju, Alexandros Iosifidis, Ville Tirronen, Kristian Meissner, Moncef Gabbouj, Serkan Kiranyaz, Salme Kärkkäinen
2019 arXiv   pre-print
The step of expert taxa recognition currently slows down the response time of many bioassessments.  ...  In our study, we investigate both the differences in accuracy and in the identification logic of taxonomic experts and machines.  ...  We expect that automatic methods can replace human experts in the routine-like identification of the easiest taxa already in the near future, while the human experts or genetic methods can concentrate  ... 
arXiv:1708.06899v4 fatcat:q7lg4bbkdvgk7gnk2x4rvx2lbe

Sharing taxonomic expertise between natural history collections using image recognition

Michael Greeff, Max Caspers, Vincent Kalkman, Luc Willemse, Barry Sunderland, Olaf Bánki, Laurens Hogeweg
2022 Research Ideas and Outcomes  
Such an ecosystem will facilitate sharing taxonomic expertise among institutions by offering image datasets that are correctly identified by their in-house taxonomic experts.  ...  Together with openly accessible machine learning algorithms and easy to use workbenches, this will allow other institutes to train image recognition algorithms and thereby compensate for the lacking expertise  ...  In contrast to identifications done by human experts, machine identifications not only deliver taxonomic names, but also metadata about the probability of the determination, the range of taxa considered  ... 
doi:10.3897/rio.8.e79187 fatcat:l44hyvignrctnabnchgsuzrmhi

Plant Identification: Experts vs. Machines in the Era of Deep Learning [chapter]

Pierre Bonnet, Hervé Goëau, Siang Thye Hang, Mario Lasseck, Milan Šulc, Valéry Malécot, Philippe Jauzein, Jean-Claude Melet, Christian You, Alexis Joly
2018 Multimedia Tools and Applications for Environmental & Biodiversity Informatics  
The next big question is how far such automated systems are from the human expertise.  ...  Automated identification of plants and animals have improved considerably in the last few years, in particular thanks to the recent advances in deep learning.  ...  Acknowledgements Most of the work conducted in this paper was funded by the Floris'Tic initiative, especially for the support of the organization of the PlantCLEF challenge.  ... 
doi:10.1007/978-3-319-76445-0_8 fatcat:kpgy5jx6jjc3dc6cilyt722ama

Fine-grained Recognition Datasets for Biodiversity Analysis [article]

Erik Rodner and Marcel Simon and Gunnar Brehm and Stephanie Pietsch and J. Wolfgang Wägele and Joachim Denzler
2015 arXiv   pre-print
We conclude with a list of challenging new research directions in the area of visual classification for biodiversity research.  ...  In the following paper, we present and discuss challenging applications for fine-grained visual classification (FGVC): biodiversity and species analysis.  ...  Incorporating human-machine interaction not only for active classification [9] and learning [4] : There is a lot of expert knowledge already available which should be used to develop new models or actively  ... 
arXiv:1507.00913v1 fatcat:yiaay3iuordqtj5kqn5zyeb65a

Next-generation phenomics for the Tree of Life

Gordon Burleigh, Kenzley Alphonse, Andrew J Alverson, Holly M Bik, Carrine Blank, Andrea L Cirranello, Hong Cui, Marymegan Daly, Thomas G Dietterich, Gail Gasparich, Jed Irvine, Matthew Julius (+16 others)
2013 PLOS Currents  
Phenotypic characters also are a rich source of biodiversity data for tree building, and they enable scientists to reconstruct the evolutionary history of organisms, including most fossil taxa, for which  ...  In contrast to recent advances in molecular sequencing, which has become faster and cheaper through recent technological advances, phenotypic data collection remains often prohibitively slow and expensive  ...  Crowdsourcing experts on our team are designing experiments in which volunteer human annotators score the cells and label cell images to complete a sample of enriched matrices.  ... 
doi:10.1371/currents.tol.085c713acafc8711b2ff7010a4b03733 pmid:23827969 pmcid:PMC3697239 fatcat:zy6bcq3annawffxtswzgrtdchy

Automatic Classification of a Taxon-Rich Community Recorded in the Wild

Ilyas Potamitis, Gianni Pavan
2014 PLoS ONE  
Automatic acoustic monitoring has not yet been proven to be generic enough to scale to other taxa and habitats than the ones described in the original research.  ...  Research usually is restricted to specific species -in most cases a single one.  ...  The idea of multiple templates was further developed by Fodor Gabor from Budapest University of Technology and Economics in the MLSP 2013 bird recognition challenge [19] .  ... 
doi:10.1371/journal.pone.0096936 pmid:24826989 pmcid:PMC4020809 fatcat:zxqqla3imrdhnadbcued6e7mne

Machine vision for automated optical recognition and classification of pollen grains or other singulated microscopic objects

G. P. Allen, R. M. Hodgson, S. R. Marsland, J. R. Flenley
2008 2008 15th International Conference on Mechatronics and Machine Vision in Practice  
Our system aims to remove the need for laborious, time-consuming, and inaccurate counting of pollen grains by humans with a low-cost machine solution. It can deal with slides obtained using different  ...  The location and identification of singulated objects on microscope slides is a problem that is common to many applications, including recognition of pollen.  ...  In a comparison with human experts on the same images, our system produces comparable output, with significantly less variation that different humans.  ... 
doi:10.1109/mmvip.2008.4749537 fatcat:kaao7s3ijreqfjjhdujfzyixqu

Endless Forams: >34,000 modern planktonic foraminiferal images for taxonomic training and automated species recognition using convolutional neural networks

Allison Y. Hsiang, Anieke Brombacher, Marina Costa Rillo, Maryline J. Mleneck-Vautravers, Stephen Conn, Sian Lordsmith, Anna Jentzen, Michael J. Henehan, Brett Metcalfe, Isabel Fenton, Bridget S. Wade, Lyndsey Fox (+11 others)
2019 Paleoceanography and Paleoclimatology  
of human experts.  ...  We also had remixing in some samples, and because we did not include a "remixed" option for classifiers, experts were forced to assign modern names to ancient taxa in these instances.  ... 
doi:10.1029/2019pa003612 fatcat:y6venz7myvgf3az5aolwgwly7u

Quantitative comparison of taxa and taxon concepts in the diatom genus Fragilariopsis : a case study on using slide scanning, multiexpert image annotation, and image analysis in taxonomy1

Bánk Beszteri, Claire Allen, Gastón O. Almandoz, Leanne Armand, María Ángeles Barcena, Hannelore Cantzler, Xavier Crosta, Oliver Esper, Richard W. Jordan, Gerhard Kauer, Christine Klaas, Michael Kloster (+4 others)
2018 Journal of Phycology  
grant ID2014/0019, The Scientific Committee on Antarctic Research (PAIS and AnT-ERA), The International Arctic Science Committee, The Palaeontological Association and The Micropalaeontological Society in  ...  We have demonstrated that an automatic identification of the three taxa with an accuracy comparable to human experts is possible.  ...  It is not possible to reliably tease apart the relative importance of experience vs. communication among experts in this study since most of them regularly participate in the Polar Marine Diatom Workshops  ... 
doi:10.1111/jpy.12767 pmid:30014469 fatcat:tdsj3la7k5bg5ao55nf4sijebi

Comparison of a Cost-Effective Integrated Plankton Sampling and Imaging Instrument with Traditional Systems for Mesozooplankton Sampling in the Celtic Sea

Sophie G. Pitois, Julian Tilbury, Paul Bouch, Hayden Close, Samantha Barnett, Phil F. Culverhouse
2018 Frontiers in Marine Science  
With the help of an expert taxonomist the system in its current form can also integrate the sampling and analysis steps, thus increasing the speed, and reducing the costs for zooplankton sampling in near  ...  Three plankton collection methods were used to gather plankton samples in the Celtic Sea in October 2016.  ...  ACKNOWLEDGMENTS We acknowledge the considerable efforts of the officers and crew of RV Cefas Endeavor involved in the PELTIC survey in October 2016.  ... 
doi:10.3389/fmars.2018.00005 fatcat:lcuadihsjvbfvkbmfy6kiiv57i

Awakening a taxonomist's third eye: exploring the utility of computer vision and deep learning in insect systematics

Miroslav Valan, Dominik Vondráček, Fredrik Ronquist
2021 Systematic Entomology  
In the early 20th century, electrification transformed transportation, agriculture and manufacturing, permanently changing human societies.  ...  Even more astonishing, once these features are learned for one task, the CNN can use its feature-recognition skills in tackling a new but related task, thus eliminating the need to train a dedicated CNN  ...  AI expert: Yes, we can prepare 'heat maps', which show the areas in the image on which the machine is focusing.  ... 
doi:10.1111/syen.12492 fatcat:5xhayirivzeibdhpcmb7ogfhlq

Pattern Recognition for Ecological Science and Environmental Monitoring [chapter]

Eric Mortensen, Enrique Delgado, Hongli Deng, David Lytle, Andrew Moldenke, Robert Paasch, Linda Shapiro, Pengcheng Wu, Wei Zhang, Thomas Dietterich
2007 Systematics Association Special Volumes  
Existing methods for obtaining population counts require expensive and tedious manual identification by human experts.  ...  This chapter presents techniques being explored in the first two years of a four year project, along with the results obtained thus far.  ...  Existing methods for obtaining population counts involve the manual collection and identification of specimens by human experts, which is too costly to provide ongoing high-resolution data.  ... 
doi:10.1201/9781420008074.ch11 fatcat:gkzn2docnbf33iiggaq3iuzxmy

Applying Computerized-Scoring Models of Written Biological Explanations across Courses and Colleges: Prospects and Limitations

Minsu Ha, Ross H. Nehm, Mark Urban-Lurain, John E. Merrill, Vivian Siegel
2011 CBE - Life Sciences Education  
We found that machine-learning software was capable in most cases of accurately evaluating the degree of scientific sophistication in undergraduate majors' and nonmajors' written explanations of evolutionary  ...  Machine-learning software holds promise as an assessment tool for use in undergraduate biology education, but like most assessment tools, it is also characterized by limitations.  ...  but differed in specific taxa and traits (i.e., X and Y).  ... 
doi:10.1187/cbe.11-08-0081 pmid:22135372 pmcid:PMC3228656 fatcat:sf3qz66n2ff47j2ulumqgsodsa

500,000 fish phenotypes: The new informatics landscape for evolutionary and developmental biology of the vertebrate skeleton

P. Mabee, J. P. Balhoff, W. M. Dahdul, H. Lapp, P. E. Midford, T. J. Vision, M. Westerfield
2012 Journal of Applied Ichthyology  
Using ontology-based reasoning, candidate genes can be inferred for the phenotypes that vary across taxa, thereby uniting genetic and phenotypic data to formulate evo-devo hypotheses.  ...  The morphological data in the KB can be browsed, sorted, and aggregated in ways that provide unprecedented possibilities for data mining and discovery.  ...  Eckhard Witten, for the invitation to participate in the excellent workshop ÔInterdisciplinary Approaches in Fish Skeletal BiologyÕ.  ... 
doi:10.1111/j.1439-0426.2012.01985.x pmid:22736877 pmcid:PMC3377363 fatcat:gikpcf5acnc5deciqne5wwwcpa

Monitoring of Coral Reefs Using Artificial Intelligence: A Feasible and Cost-Effective Approach

González-Rivero, Beijbom, Rodriguez-Ramirez, EP Bryant, Ganase, Gonzalez-Marrero, Herrera-Reveles, V Kennedy, Kim, Lopez-Marcano, Markey, P Neal (+8 others)
2020 Remote Sensing  
In recent years, a rapid evolution of artificial intelligence in image recognition has been evident in its broad applications in modern society, offering new opportunities for increasing the capabilities  ...  We found unbiased and high agreement between expert and automated observations (97%).  ...  Secondly, while monitoring of coral reefs can benefit from fast processing and data standardisation powered by automated image analyses, an integration between human expert observations and machine learning  ... 
doi:10.3390/rs12030489 fatcat:wbcloaudtvavflrlockthqgqbe
« Previous Showing results 1 — 15 out of 771 results