Education, Science, Technology, Innovation and Life
Open Access
Sign In

Research on false eyewitness Detection algorithm of Asian giant hornet Image based on support Vector Machine

Download as PDF

DOI: 10.23977/jipta.2021.41005 | Downloads: 23 | Views: 1307

Author(s)

Jiaxu Li 1

Affiliation(s)

1 College of Physics and Optoelectronic Engineering, Shenzhen University Shenzhen City, Guangdong Province 518000

Corresponding Author

Jiaxu Li

ABSTRACT

Recently, Vespa mandarinia have been found frequently in Washington state, causing severe potential damage to the local ecosystem. To establish effective pest management programs, Washington State collected reports of people witnessing these wasps. However, due to the existence of a large number of wrong reports and the limited resources of government agencies, it is not possible to conduct field visits to all reports. In recognition of report images, since the image data set is extremely unbalanced, we use data enhancement, cutting and rotating the positive images to increase the number of positive images. In addition, due to the fact that the traditional neural network is easy to overfit in this kind of imbalanced data set, we use the One-Class SVM model to transform the classification problem into the outlier test problem and the experimental results show that the accuracy of our algorithm is 98%.

KEYWORDS

Asian giant hornet, sample imbalance, support vector machine, data enhancement

CITE THIS PAPER

Jiaxu Li. Research on false eyewitness Detection algorithm of Asian giant hornet Image based on support Vector Machine. Journal of Image Processing Theory and Applications (2021) Vol. 4: 33-37. DOI: http://dx.doi.org/10.23977/jipta.2021.41005

REFERENCES

[1] Mark A Davis and Ken Thompson. Eight ways to be a colonizer; two ways to be an invader: a proposed nomenclature scheme for invasion ecology. Bulletin of the ecological society of America, 81(3):226–230, 2000.
[2] J. Ehrenfeld. Ecosystem consequences of biological invasions. Annual Review of Ecology, Evolution, and Systematics, 41:59–80, 2010.
[3] Yunqiang Chen, Xiang Sean Zhou, and Thomas S Huang. One-class svm for learning in image retrieval. In Proceedings 2001 International Conference on Image Processing (Cat.No. 01CH37205), volume 1, pages 34–37. IEEE, 2001.
[4] Florent Perronnin, Jorge Sánchez, and Thomas Mensink. Improving the fisher kernel for large-scale image classification. In European conference on computer vision, pages 143–156. Springer, 2010.

Downloads: 1149
Visits: 99453

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.