A tool for developing an automatic insect identification system based on wing outlines

Yang, Heping; Ma, Chun‐Sen; Wen, Hui; Zhan, Qimin; Wang, Xinli

doi:10.1038/srep12786

Cited by 68 publications

(67 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The rapid development of computer vision technologies has led to applications in highly promising automatized arthropod identification platforms based on multivariate biometric features of the taxon. This novel approach, based fully on classical taxonomy and computer algorithms, allows species identification procedures to be performed even by non-taxonomists, with a high degree of reliability (Watson et al 2003;Hassan et al 2014;Yang et al 2015;Favret and Sieracki 2016;Wang et al 2017). Despite being highly attractive, automated species identification suffers from a number of limitations, the most significant being the limited applicability of automated platforms which have for now been created only for a few groups of insects (e.g.…”

Section: Classical Techniquesmentioning

confidence: 99%

Forewarned is forearmed: harmonized approaches for early detection of potentially invasive pests and pathogens in sentinel plantings

Morales‐Rodríguez¹,

Anslan²,

Auger‐Rozenberg³

et al. 2019

View full text Add to dashboard Cite

The number of invasive alien pest and pathogen species affecting ecosystem functioning, human health and economies has increased dramatically over the last decades. Discoveries of invasive pests and pathogens previously unknown to science or with unknown host associations yet damaging on novel hosts highlights the necessity of developing novel tools to predict their appearance in hitherto naïve environments. The use of sentinel plant systems is a promising tool to improve the detection of pests and pathogens before introduction and to provide valuable information for the development of preventative measures to minimize economic or environmental impacts. Though sentinel plantings have been established and studied during the last decade, there still remains a great need for guidance on which tools and protocols to put into practice in order to make assessments accurate and reliable. The sampling and diagnostic protocols chosen should enable as much information as possible about potential damaging agents and species identification. Consistency and comparison of results are based on the adoption of common procedures for sampling design and sample processing. In this paper, we suggest harmonized procedures that should be used in sentinel planting surveys for effective sampling and identification of potential pests and pathogens. We also review the benefits and limitations of various diagnostic methods for early detection in sentinel systems, and the feasibility of the results obtained supporting National Plant Protection Organizations in pest and commodity risk analysis.

show abstract

Section: Classical Techniquesmentioning

confidence: 99%

Forewarned is forearmed: harmonized approaches for early detection of potentially invasive pests and pathogens in sentinel plantings

Morales‐Rodríguez¹,

Anslan²,

Auger‐Rozenberg³

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Image processing ties closely with the core of research area within engineering and computer science disciplines. Image processing is important in classifying based on what the machine sees and identify in a much faster way [8]. There are roughly two types of image processing, which are analog and digital image processing.…”

Section: Butterfly Family Detection and Identificationmentioning

confidence: 99%

Butterfly Family Detection and Identification using Convolutional Neural Network for Lepidopterology

2019

IJRTE

View full text Add to dashboard Cite

Lepidopterology is a branch of entomology concerning the scientific study of moths and the three superfamilies of butterflies. The project aims to help biology students in identifying butterfly without harming the insect. In the studies of lepidopterology, the students normally need to capture the butterflies with nets and dissect the insect to identify its family types. Computer vision is a study on how computers can be used to make high-level comprehension from the input of digital image and videos. By utilizing the latest Image Processing technique, it can identify the correct species of butterfly with high accuracy by using layers of node in a Convolutional Neural Network (CNN). The work process starts with data acquisition (mining the butterfly image automatically from google image search), pre-processing (converting image format and rotation), analyzing and understanding digital images (group images into folders), and to make assumptions of the high complication data from the real world in the process of producing numerical information that can be comprehend by machines in order to form conclusions. Benefits of using CNN is to reduce the need for human and physical intervention in identifying each of the butterfly characters. This makes it easier to expand the database in the future. The image is acquired using Fatkun Batch Downloader to download large number of images. The project is develop using Tensorflow in Ubuntu operating system and interface is in HTML connected to the Python script via Flask. The results of the experiment show that CNN can identify with 92.7 percent of final accuracy with learning saturation (overfitting) of 500 cycle. While testing results shows 62.5 percent of accuracy in predicting new datasets.

show abstract

“…Together with conventional classifying methods (such as a principal component analysis (PCA) (P Weeks et al 1997)) images data could be classified. Other, slightly more complex systems use simple forms of machine learning (ML) (Kang et al 2012), such as a support vector machine (SVM) ((Yang et al 2015) or K -nearest neighbors (Watson et al 2004). An identification system for insects at the order level (including ants within the order of Hymenoptera) designed by Wang et al (2012b), used seven geometrical features (e.g.…”

Section: Computer Visionmentioning

confidence: 99%

“…wing venation patterns) with great success (95%). Seven owlfly species (Neuroptera: Ascalaphidae) were classified using an SVM on wing outlines (99%) (Yang et al 2015). Five wasp species (Hymenoptera: Ichneumonidae) could be classified using PCA on wing venation data (94%) (P Weeks et al 1997).…”

Section: Computer Visionmentioning

confidence: 99%

Taxonomic Classification of Ants (Formicidae) from Images using Deep Learning

Boer

Vos

2018

Preprint

View full text Add to dashboard Cite

The well-documented, species-rich, and diverse group of ants (Formicidae) are important 1 ecological bioindicators for species richness, ecosystem health, and biodiversity, but ant 2 species identification is complex and requires specific knowledge. In the past few years, 3 insect identification from images has seen increasing interest and success, with processing 4 speed improving and costs lowering. Here we propose deep learning (in the form of a 5 convolutional neural network (CNN)) to classify ants at species level using AntWeb 6 images. We used an Inception-ResNet-V2-based CNN to classify ant images, and three 7 shot types with 10,204 images for 97 species, in addition to a multi-view approach, for 8 training and testing the CNN while also testing a worker-only set and an AntWeb 9 protocol-deviant test set. Top 1 accuracy reached 62% -81%, top 3 accuracy 80% -92%, 10 and genus accuracy 79% -95% on species classification for different shot type approaches. 11The head shot type outperformed other shot type approaches. Genus accuracy was broadly 12 similar to top 3 accuracy. Removing reproductives from the test data improved accuracy 13 only slightly. Accuracy on AntWeb protocol-deviant data was very low. In addition, we 14 make recommendations for future work concerning image threshold, distribution, and 15 quality, multi-view approaches, metadata, and on protocols; potentially leading to higher 16 accuracy with less computational effort. BOER & VOS

show abstract

A tool for developing an automatic insect identification system based on wing outlines

Cited by 68 publications

References 34 publications

Forewarned is forearmed: harmonized approaches for early detection of potentially invasive pests and pathogens in sentinel plantings

Forewarned is forearmed: harmonized approaches for early detection of potentially invasive pests and pathogens in sentinel plantings

Butterfly Family Detection and Identification using Convolutional Neural Network for Lepidopterology

Taxonomic Classification of Ants (Formicidae) from Images using Deep Learning

Contact Info

Product

Resources

About