Journal
ECOLOGICAL INFORMATICS
Volume 57, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.ecoinf.2020.101089
Keywords
Pest recognition; Convolutional neural networks; Saliency methods; Classifiers ensemble
Categories
Funding
- NVIDIA Corporation
Ask authors/readers for more resources
Insect pests recognition is necessary for crop protection in many areas of the world. In this paper we propose an automatic classifier based on the fusion between saliency methods and convolutional neural networks. Saliency methods are famous image processing algorithms that highlight the most relevant pixels of an image. In this paper, we use three different saliency methods as image preprocessing and create three different images for every saliency method. Hence, we create 3 x 3 = 9 new images for every original image to train different convolutional neural networks. We evaluate the performance of every preprocessing/network couple and we also evaluate the performance of their ensemble. We test our approach on both a small dataset and the large IP102 dataset. Our best ensembles reaches the state of the art accuracy on both the smaller dataset (92.43%) and the IP102 dataset (61.93%), approaching the performance of human experts on the smaller one. Besides, we share our MATLAB code at: https://github.com/LorisNanni/.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available