ScannerVision: Scanner-based image acquisition of medically important arthropods for the development of computer vision and deep learning models

Song-Quan Ong; Nathan Pinoy; Min Hui Lin; Kim Bjerge; Francisco Javier Peris-Felipo; Rob Lind; Jordan  P. Cuff; Samantha M. Cook; Toke Thomas Høye

doi:10.1016/j.crpvbd.2025.100268

ScannerVision: Scanner-based image acquisition of medically important arthropods for the development of computer vision and deep learning models

Song-Quan Ong^*
, Nathan Pinoy
, Min Hui Lin
, Kim Bjerge
, Francisco Javier Peris-Felipo
, Rob Lind
, Jordan P. Cuff
, Samantha M. Cook
, Toke Thomas Høye

^*Corresponding author for this work

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

Abstract

Computer vision methods offer great potential for rapid image-based identification of medically important arthropod specimens. However, imaging large numbers of specimens is time consuming, and it is difficult to achieve the high image quality required for machine learning models. Conventional imaging methods for identifying and digitizing arthropods, such as insects and spiders, use a stereomicroscope or macro lenses with a camera. This method is challenging due to the narrow field of view, especially when large numbers of arthropods need to be processed. In this paper, we present a high-throughput scanner-based method for capturing images of arthropods that can be used to generate large datasets suitable for training machine learning algorithms for identification. We demonstrate the ability of this approach to image arthropod samples collected with different sampling methods, such as sticky traps (unbaited, in different colors), baited mosquito traps as used by the US Centers for Disease Control and Prevention (CDC) and BioGents-Sentinel (BGS), and UV light traps with a sticky pad. Using different strategies to place the arthropods on a charge-coupled device (CCD) flatbed scanner and optimized settings that balance processing time and image quality, we captured high-resolution images of various arthropods and obtained morphological details with resolution and magnification similar to a stereomicroscope. We validate the method by comparing the performance of three different deep learning models (InceptionV3, ResNet and MobileNetV2) on two different datasets, namely the scanned images from this study and the images captured with a camera of a stereomicroscope. The results show that the performance of the models trained on the two datasets is not significantly different, indicating that the quality of the scanned images is comparable to that of a stereomicroscope.

Original language	English
Article number	100268
Journal	Current Research in Parasitology & Vector-Borne Diseases
Volume	7
DOIs	https://doi.org/10.1016/j.crpvbd.2025.100268
Publication status	Published - Jan 2025

Keywords

Aedes
Anopheles
Biodiversity
Culex
Digitization
Entomology
Machine learning

Access to Document

10.1016/j.crpvbd.2025.100268

Library access?

Check availability with the Royal Danish Library

Cite this

Ong, S.-Q., Pinoy, N., Hui Lin, M., Bjerge, K., Peris-Felipo, F. J., Lind, R., P. Cuff, J., M. Cook, S., & Høye, T. T. (2025). ScannerVision: Scanner-based image acquisition of medically important arthropods for the development of computer vision and deep learning models. Current Research in Parasitology & Vector-Borne Diseases, 7, Article 100268. https://doi.org/10.1016/j.crpvbd.2025.100268

@article{917665cdd9594a5797e365594dad8d29,

title = "ScannerVision: Scanner-based image acquisition of medically important arthropods for the development of computer vision and deep learning models",

abstract = "Computer vision methods offer great potential for rapid image-based identification of medically important arthropod specimens. However, imaging large numbers of specimens is time consuming, and it is difficult to achieve the high image quality required for machine learning models. Conventional imaging methods for identifying and digitizing arthropods, such as insects and spiders, use a stereomicroscope or macro lenses with a camera. This method is challenging due to the narrow field of view, especially when large numbers of arthropods need to be processed. In this paper, we present a high-throughput scanner-based method for capturing images of arthropods that can be used to generate large datasets suitable for training machine learning algorithms for identification. We demonstrate the ability of this approach to image arthropod samples collected with different sampling methods, such as sticky traps (unbaited, in different colors), baited mosquito traps as used by the US Centers for Disease Control and Prevention (CDC) and BioGents-Sentinel (BGS), and UV light traps with a sticky pad. Using different strategies to place the arthropods on a charge-coupled device (CCD) flatbed scanner and optimized settings that balance processing time and image quality, we captured high-resolution images of various arthropods and obtained morphological details with resolution and magnification similar to a stereomicroscope. We validate the method by comparing the performance of three different deep learning models (InceptionV3, ResNet and MobileNetV2) on two different datasets, namely the scanned images from this study and the images captured with a camera of a stereomicroscope. The results show that the performance of the models trained on the two datasets is not significantly different, indicating that the quality of the scanned images is comparable to that of a stereomicroscope.",

keywords = "Aedes, Anopheles, Biodiversity, Culex, Digitization, Entomology, Machine learning",

author = "Song-Quan Ong and Nathan Pinoy and \{Hui Lin\}, Min and Kim Bjerge and Peris-Felipo, \{Francisco Javier\} and Rob Lind and \{P. Cuff\}, Jordan and \{M. Cook\}, Samantha and H{\o}ye, \{Toke Thomas\}",

year = "2025",

month = jan,

doi = "10.1016/j.crpvbd.2025.100268",

language = "English",

volume = "7",

journal = "Current Research in Parasitology \& Vector-Borne Diseases",

issn = "2667-114X",

publisher = "Elsevier",

}

Ong, S-Q, Pinoy, N, Hui Lin, M, Bjerge, K, Peris-Felipo, FJ, Lind, R, P. Cuff, J, M. Cook, S & Høye, TT 2025, 'ScannerVision: Scanner-based image acquisition of medically important arthropods for the development of computer vision and deep learning models', Current Research in Parasitology & Vector-Borne Diseases, vol. 7, 100268. https://doi.org/10.1016/j.crpvbd.2025.100268

ScannerVision: Scanner-based image acquisition of medically important arthropods for the development of computer vision and deep learning models. / Ong, Song-Quan; Pinoy, Nathan; Hui Lin, Min et al.
In: Current Research in Parasitology & Vector-Borne Diseases, Vol. 7, 100268, 01.2025.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

TY - JOUR

T1 - ScannerVision: Scanner-based image acquisition of medically important arthropods for the development of computer vision and deep learning models

AU - Ong, Song-Quan

AU - Pinoy, Nathan

AU - Hui Lin, Min

AU - Bjerge, Kim

AU - Peris-Felipo, Francisco Javier

AU - Lind, Rob

AU - P. Cuff, Jordan

AU - M. Cook, Samantha

AU - Høye, Toke Thomas

PY - 2025/1

Y1 - 2025/1

N2 - Computer vision methods offer great potential for rapid image-based identification of medically important arthropod specimens. However, imaging large numbers of specimens is time consuming, and it is difficult to achieve the high image quality required for machine learning models. Conventional imaging methods for identifying and digitizing arthropods, such as insects and spiders, use a stereomicroscope or macro lenses with a camera. This method is challenging due to the narrow field of view, especially when large numbers of arthropods need to be processed. In this paper, we present a high-throughput scanner-based method for capturing images of arthropods that can be used to generate large datasets suitable for training machine learning algorithms for identification. We demonstrate the ability of this approach to image arthropod samples collected with different sampling methods, such as sticky traps (unbaited, in different colors), baited mosquito traps as used by the US Centers for Disease Control and Prevention (CDC) and BioGents-Sentinel (BGS), and UV light traps with a sticky pad. Using different strategies to place the arthropods on a charge-coupled device (CCD) flatbed scanner and optimized settings that balance processing time and image quality, we captured high-resolution images of various arthropods and obtained morphological details with resolution and magnification similar to a stereomicroscope. We validate the method by comparing the performance of three different deep learning models (InceptionV3, ResNet and MobileNetV2) on two different datasets, namely the scanned images from this study and the images captured with a camera of a stereomicroscope. The results show that the performance of the models trained on the two datasets is not significantly different, indicating that the quality of the scanned images is comparable to that of a stereomicroscope.

AB - Computer vision methods offer great potential for rapid image-based identification of medically important arthropod specimens. However, imaging large numbers of specimens is time consuming, and it is difficult to achieve the high image quality required for machine learning models. Conventional imaging methods for identifying and digitizing arthropods, such as insects and spiders, use a stereomicroscope or macro lenses with a camera. This method is challenging due to the narrow field of view, especially when large numbers of arthropods need to be processed. In this paper, we present a high-throughput scanner-based method for capturing images of arthropods that can be used to generate large datasets suitable for training machine learning algorithms for identification. We demonstrate the ability of this approach to image arthropod samples collected with different sampling methods, such as sticky traps (unbaited, in different colors), baited mosquito traps as used by the US Centers for Disease Control and Prevention (CDC) and BioGents-Sentinel (BGS), and UV light traps with a sticky pad. Using different strategies to place the arthropods on a charge-coupled device (CCD) flatbed scanner and optimized settings that balance processing time and image quality, we captured high-resolution images of various arthropods and obtained morphological details with resolution and magnification similar to a stereomicroscope. We validate the method by comparing the performance of three different deep learning models (InceptionV3, ResNet and MobileNetV2) on two different datasets, namely the scanned images from this study and the images captured with a camera of a stereomicroscope. The results show that the performance of the models trained on the two datasets is not significantly different, indicating that the quality of the scanned images is comparable to that of a stereomicroscope.

KW - Aedes

KW - Anopheles

KW - Biodiversity

KW - Culex

KW - Digitization

KW - Entomology

KW - Machine learning

UR - https://www.scopus.com/pages/publications/105004666829

U2 - 10.1016/j.crpvbd.2025.100268

DO - 10.1016/j.crpvbd.2025.100268

M3 - Journal article

C2 - 40487328

SN - 2667-114X

VL - 7

JO - Current Research in Parasitology & Vector-Borne Diseases

JF - Current Research in Parasitology & Vector-Borne Diseases

M1 - 100268

ER -

ScannerVision: Scanner-based image acquisition of medically important arthropods for the development of computer vision and deep learning models

Abstract

Keywords

Access to Document

Library access?

Other files and links

Fingerprint

Cite this