Research on Image Acquisition and Recognition for Stored Grain Pests

DOI

10.2991/aiie-16.2016.62How to use a DOI?

Keywords

stored grain pests; image dataset; MSERs; color features; shape features

Abstract

Manual ways of recognizing stored grain pests which are trapped is very time-consuming. In this study, an image dataset of 9 species of pests was built up by finding the MSERs (Maximally Stable Extremal Regions), through a trap of stored grain pests combined with a real-time imaging device. On this basis, the localization and recognition of stored grain pests were achieved. The experimental results on 3600 images showed that by the combination of shape features and color features, the average F1 score was about 0.947 by selecting the appropriate parameters of SVM (Support Vector Machines) classifier.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Defa Wang
AU  - Huiling Zhou
AU  - Haiying Yang
AU  - Yufeng Shen
AU  - Yang Cao
AU  - Huiyi Zhao
PY  - 2016/11
DA  - 2016/11
TI  - Research on Image Acquisition and Recognition for Stored Grain Pests
BT  - Proceedings of the 2016 2nd International Conference on Artificial Intelligence and Industrial Engineering (AIIE 2016)
PB  - Atlantis Press
SP  - 268
EP  - 272
SN  - 1951-6851
UR  - https://doi.org/10.2991/aiie-16.2016.62
DO  - 10.2991/aiie-16.2016.62
ID  - Wang2016/11
ER  -