Lepidoptera Classification through Deep Learning

Jia, Xiaotian; Tan, Xueting; Jin, Guoen; Sinnott, Richard

doi:10.1109/csde50874.2020.9411382

Cited by 2 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Insect identification algorithms have been described before [21][22][23]. However, they were limited to later stages of development than the egg, at which point identification by eye is more feasible relying on distinguishable characteristics such as color, shape, and gross morphological features.…”

Section: Discussionmentioning

confidence: 99%

“…Initial traction for this technique spawned from the successful uses of AlexNet to accurately identify thousands of different images of one thousand different classes including animals, plants, and common objects [20], and later ResNet to improve the feasible depth of neural architectures [21]. Insect identification using neural networks has been described before for insect stages where major differences in color and morphology can be found, e.g., in butterflies, caterpillars, beetles, bees, mantids, and cicadas [22][23][24]. Imaging and the traditional analysis of insect eggs is significantly more challenging because of their small size, minute differences in their size or color between species in some cases, and in general lack of easily distinguishable features.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Species Identification of Caterpillar Eggs by Machine Learning Using a Convolutional Neural Network and Massively Parallelized Microscope

Efromson

Lawrie

Doman³

et al. 2022

Agriculture

View full text Add to dashboard Cite

Rapid, accurate insect identification is the first and most critical step of pest management and vital to agriculture for determining optimal management strategies. In many instances, classification is necessary within a short developmental window. Two examples, the tobacco budworm, Chloridea virescens, and bollworm, Helicoverpa zea, both have <5 days from oviposition until hatching. H. zea has evolved resistance to Bt-transgenic crops and requires farmers to decide about insecticide application during the ovipositional window. The eggs of these species are small, approximately 0.5 mm in diameter, and often require a trained biologist and microscope to resolve morphological differences between species. In this work, we designed, built, and validated a machine learning approach to insect egg identification with >99% accuracy using a convolutional neural architecture to classify the two species of caterpillars. A gigapixel scale parallelized microscope, referred to as the Multi-Camera Array Microscope (MCAM™), and automated image-processing pipeline allowed us to rapidly build a dataset of ~5500 images for training and testing the network. In the future, applications could be developed enabling farmers to photograph eggs on a leaf and receive an immediate species identification before the eggs hatch.

show abstract

Section: Discussionmentioning

confidence: 99%