A Computer Vision-Based Approach for Tick Identification Using Deep Learning Models

• Published in: Insects (Basel, Switzerland) Vol. 13; no. 2; p. 116
• Main Authors: Luo, Chu-Yuan, Pearson, Patrick, Xu, Guang, Rich, Stephen M
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 22.01.2022; MDPI
• Subjects: Accuracy; Algorithms; Anaplasmosis; Arachnids; Artificial intelligence; Artificial neural networks; Bacterial diseases; Biting; Classification; Climate change; Computer vision; Datasets; Deep learning; Disease transmission; Ectoparasites; Face recognition; Health risks; Human error; Identification; Identification methods; Learning algorithms; Livestock; Lyme disease; Machine learning; medical entomology; Medical imaging; Medical personnel; Morphology; Mountains; Neural networks; Object recognition; Parasitic diseases; Pattern recognition; Range extension; Rocky Mountain spotted fever; Species; Surveillance; Taxonomy; Threat evaluation; Tick-borne diseases; Ticks; Vector-borne diseases; Vectors; Viruses; Vision systems; Wild animals; United States > US; medical entomology; ticks; computer vision

A wide range of pathogens, such as bacteria, viruses, and parasites can be transmitted by ticks and can cause diseases, such as Lyme disease, anaplasmosis, or Rocky Mountain spotted fever. Landscape and climate changes are driving the geographic range expansion of important tick species. The morphol...