A lightweight keypoint matching framework for insect wing morphometric landmark detection
Institution:
1. University of Science and Technology of Hanoi, ICT Lab, Hanoi 10000, Viet Nam;2. Oxford University Clinical Research Unit, Ho Chi Minh City 700000, Viet Nam;3. FPT University, Department of Computing Fundamentals, Hanoi 10000, Viet Nam;4. MIVEGEC, Univ of Montpellier, IRD, CNRS, LMI DRISA, Montpellier 34000, France;1. Department of Environmental Science, Kangwon National University, Chuncheon 200-701, Republic of Korea;2. Forest Ecology and Climate Change Division, National Institute of Forest Science, Seoul, Republic of Korea;3. Department of Geography, Indiana University Bloomington, Indiana, USA;1. Department of Environmental Engineering, College of Engineering, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam 31451, Saudi Arabia;2. Interdisciplinary Research Center for Membranes and Water Security, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi Arabia;3. Department of Civil Engineering, Transilvania University of Brasov, 5, Turnului Str, 500152, Brasov, Romania;4. Danube Delta National Institute for Research and Development,165 Babadag Street, 820112 Tulcea, Romania;5. Department of Civil Engineering, Faculty of Engineering Baze University, Abuja, Nigeria;1. Department of Wildlife and Habitat Management, Forest College and Research Institute, Mulugu, Hyderabad, Telangana 502279, India;2. Department of Wildlife Science, College of Forestry, Kerala Agricultural University, Thrissur, Kerala 680656, India;1. Research Institute of Tibet Plateau Ecology, Tibet Agriculture & Animal Husbandry University, Nyingchi, Tibet 860000, China;2. Key Laboratory of Forest Ecology in Tibet Plateau, Ministry of Education, Nyingchi, Tibet 860000, China;3. National Key Station of Field Scientific Observation & Experiment, Nyingchi, Tibet 860000, China;4. Key Laboratory of Alpine Vegetation Ecological Security in Tibet, Nyingchi, Tibet 860000, China;1. Institute for Tropical Technology, Vietnam Academy of Science and Technology, 18 Hoang Quoc Viet, Cau Giay District, Hanoi 10000, Vietnam;2. Chemistry at Surfaces, Interfaces and Nanostructure (ChemSIN), Faculté des Sciences, Université libre de Bruxelles (ULB), Boulevard du Triomphe, 2, CP 255, B-1050 Bruxelles, Belgium;3. Center for Technology Application and Transfer, Vietnam Petroleum Institute, 167 Trung Kinh, Yen Hoa, Cau Giay District, Hanoi 10000, Vietnam;4. University of Science and Technology of Hanoi, Vietnam Academy of Science and Technology, 18 Hoang Quoc Viet, Cau Giay District, Hanoi 10000, Vietnam;1. School of Earth Sciences and Resources, China University of Geosciences (Beijing), Beijing, China;2. Harbin Center for Integrated Natural Resources Survey, China Geological Survey, Harbin, Heilongjiang, China
Abstract:
Geometric morphometrics has become an important approach in insect morphology studies because it capitalizes on advanced quantitative methods to analyze shape. Shape could be digitized as a set of landmarks from specimen images. However, the existing tools mostly require manual landmark digitization, and previous works on automatic landmark detection methods do not focus on implementation for end-users. Motivated by that, we propose a novel approach for automatic landmark detection, based on visual features of landmarks and keypoint matching techniques. While still archiving comparable accuracy to that of the state-of-the-art method, our framework requires less initial annotated data to build prediction model and runs faster. It is lightweight also in terms of implementation, in which a four-step workflow is provided with user-friendly graphical interfaces to produce correct landmark coordinates both by model prediction and manual correction. The utility iMorph is freely available at https://github.com/ha-usth/InsectWingLandmark, currently supporting Windows, MacOS, and Linux.
