scholarly journals Image analysis for taxonomic identification of Javanese butterflies

2018 ◽  
Author(s):  
Saskia de Vetter ◽  
Rutger Vos

SummaryTaxonomic experts classify millions of specimens, but this is very time-consuming and therefore expensive. Image analysis is a way to automate identification and was previously done at Naturalis Biodiversity Center for slipper orchids (Cypripedioideae) by the program ‘OrchID’. This program operated by extracting a pre-defined number of features from images, and these features were used to train artificial neural networks (ANN) to classify out-of-sample images. This program was extended to work for a collection of Javanese butterflies, donated to Naturalis by the Van Groenendael-Krijger Foundation. Originally, for the orchids, an image was divided into a pre-defined number of horizontal and vertical bins and the mean blue-green-red values of each bin were calculated (BGR method) to obtain image features. In the extended implementation, characteristic image features were extracted using the SURF algorithm implemented in OpenCV and clustered with the BagOfWords method (SURF-BOW method). In addition, a combination of BGR- and SURF-BOW was implemented to extract both types of features in a single dataset (BGR-SURF method). A selection of the butterfly and orchid images was made to create datasets with at least 5 and at most 50 specimens per species. The SURF-BOW and BGR-SURF methods were applied to both selected datasets, and the original BGR method was applied to the selected butterfly dataset. PCA plots were made to inspect visually how well the applied methods discriminated among the species. For the butterflies, both genus and species appeared to cluster together in the plots of the SURF-BOW method. However, no obvious clustering was noticeable for the orchid plots. The performance of the ANNs was validated by a stratified k-fold cross validation. For the butterflies, the BGR-SURF method scored best with an accuracy of 77%, against 71% for the SURF-BOW method and 66% for the BGR method, all for chained genus and species prediction with k = 10. The new methods could not improve the accuracy of the orchid classification with k = 10, which was 75% on genus, 52% on genus and section and 48% on genus, section and species in the original framework and now less than 25% for all. The validation results also showed that at least about 15 specimens per species were necessary for a good prediction with the SURF-BOW method. The BGR-SURF method was found to be the best of these methods for butterflies, but the original BGR method was best for the slipper orchids. In the future these methods may be tested with other datasets, for example with mosquitoes. In addition, other classifiers may be tested for better performance, like support vector machines.

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 64895-64905
Author(s):  
Essam H. Houssein ◽  
Diaa Salama Abdelminaam ◽  
Hager N. Hassan ◽  
Mustafa M. Al-Sayed ◽  
Emad Nabil

2015 ◽  
Vol 11 (S319) ◽  
pp. 101-101
Author(s):  
G. Marton ◽  
L.V. Tóth ◽  
L. G. Balázs ◽  
S. Zahorecz ◽  
Z. Bagoly ◽  
...  

AbstractThe point sources in the Bright Source Catalogue (BSC) of the AKARI Far–Infrared Surveyor (FIS) were classified based on their far–IR and mid–IR fluxes and colours using Quadratic Discriminant Analysis method (QDA) and Support Vector Machines (SVM). The reliability of our results show that we can successfully separate galactic and extragalactic AKARI point sources in the multidimensional space of fluxes and colours. However, differentiating among the extragalactic sub–types needs further information.


2017 ◽  
Vol 3 (2) ◽  
pp. 563-567
Author(s):  
Christian Heinze ◽  
Constantin Hütterer ◽  
Thomas Schnupp ◽  
Gustavo Lenis ◽  
Martin Golz

AbstractWe examined if ECG-based features are discrimi-native towards drowsiness. Twenty-five volunteers (19–32 years) completed 7×40 minutes of monotonous overnight driving simulation, designed to induce drowsiness. ECG (512 s-1) was recorded continuously; subjective ratings of drowsiness on the Karolinska sleepiness scale (KSS) were polled every five minutes. ECG recordings were divided into 5-min segments, each associated with the mean of one self- and two observer-KSS ratings. Those mean KSS values were binarized to obtain two classes not drowsy and drowsy. The Q-, R- and T-waves in the recordings were detected; R-peak positions were manually reviewed; the Q- and T-detection method was tested against the manual annotations of Physio-net’s QT database. Power spectral densities of RR intervals (RR-PSD) and quantiles of the empirical distribution of heart-rate corrected QTc intervals were estimated. Support-vector machines and random-holdout cross-validation were used for the estimation of the classification error. Using either RR-PSD or QTc features yielded mean test errors of 79.3 ± 0.3 % and 82.7 ± 0.5 %, respectively. Merging RR and QTc features improved the accuracy to 88.3 ± 0.2 %. QTc intervals of the class drowsy were generally prolonged com-pared to not drowsy. Our findings indicate that the inclusion of QT intervals contribute to the discrimination of driver sleepiness.


2006 ◽  
Vol 387 (3) ◽  
pp. 1105-1112 ◽  
Author(s):  
Alessandra Borin ◽  
Marco Flôres Ferrão ◽  
Cesar Mello ◽  
Lívia Cordi ◽  
Luiz C. M. Pataca ◽  
...  

2011 ◽  
Vol 204-210 ◽  
pp. 423-426
Author(s):  
Chun Li Xie ◽  
Dan Dan Zhao ◽  
Juan Wang ◽  
Cheng Shao

Parameters selection plays an important role for the performance of least squares support vector machines (LS-SVM). In this paper, a novel parameters selection method for LS-SVM is presented based on chaotic ant swarm (CAS) algorithm. Using this method, the optimization model is established, within which the fitness function is the mean square error (MSE) index, and the constraints are the ranges of the designing parameters. The proposed method is used in the identification for inverse model of the nonlinear systems, and simulation results are given to show the efficiency.


2021 ◽  
Author(s):  
Jermaine Ramdass

A technique is proposed that can be used to predict the cup-to-disc ratio from a single optic fundus image and determine which image features have the highest contribution to a specific ophthalmologist’s measured cup-to-disc ratio. The procedure starts with image pre-processing. The main step of the procedure is feature extraction where image features related to pixel intensities are found. These features are used to train three different classifiers: neural networks, support vector machines, and sparse representation classifiers. The classifiers are tested and evaluated to see how accurately they can predict the cup-to-disc ratio. The best obtained results are in the 70-75% success range. Finally, feature ranking is performed using the methods of chi square and information gain on a combined feature vector using measured cup-to-disc ratios from each ophthalmologist to determine the importance and contribution of each feature to that ophthalmologist.


Sign in / Sign up

Export Citation Format

Share Document