Automatic identification of butterfly specimen images at the family level based on deep learning method
       Home | About Journal | Editorial Board | Subscription | Instruction | Advertisement | Contact Us | Chinese
ACTA ENTOMOLOGICA SINICA  2017, Vol. 60 Issue (11): 1339-1348    DOI: 10.16380/j.kcxb.2017.11.012
RESEARCH PAPERS Current Issue | Next Issue | Archive | Adv Search Previous Articles  |  Next Articles  
Automatic identification of butterfly specimen images at the family level based on deep learning method
ZHOU Ai-Ming1, MA Peng-Peng1, XI Tian-Yu2, WANG Jiang-Ning2, FENG Jin1, SHAO Ze-Zhong1, TAO Yu-Lei1, YAO Qing1,*
(1. School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China; 2. Institute of Zoology, Chinese Academy of Sciences, Beijing 100101, China)
 Download: PDF (4090 KB)   HTML (1 KB)   Export: BibTeX | EndNote (RIS)      Supporting Info
Abstract 【Aim】 This study aims to explore the feasibility and generalization ability of deep learning model applied to the automatic identification of butterfly images at the family level. 【Methods】 To improve the robustness and generalization performance of model, the data augmentation with images of 1 117 butterfly species of six families were performed to increase the number of images by flipping image horizontally, increasing image contrast and brightness, and adding noises for training. In Caffe framework, an ImageNet-trained convolution neural network model was obtained by 310 000 iterations. The training set of butterfly images was used to train a new CaffeNet model to automatically identify butterflies at the family level by the transfer learning method. To compare generalization ability of the CaffeNet model based on deep learning with the models based on traditional pattern recognition methods, global and local features were extracted from the same training samples, and the support vector machine (SVM) classifier was trained. All models were used to detect the two different test sample sets. 【Results】 When the test samples, same as the training samples, were from specimen images, the CaffeNet model had a mean accuracy rate of 95.8%, while the SVM classifier based on Gabor features had a mean accuracy rate of 94.8% in six butterfly families. When the test samples were from natural images of butterflies, the accuracy rates of the CaffeNet and SVM models were decreased. However, the accuracy rate of CaffeNet model still achieved 65.6% and the SVM classifier based on Gabor features only got the 38.9% accuracy rate. 【Conclusion】 The butterfly identification model based on deep learning has a high identification rate at the family level, with higher robustness and generalization ability than those traditional pattern recognition models based on global and local features by manual extraction and selection.
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
Articles by authors
ZHOU Ai-Ming
MA Peng-Peng
XI Tian-Yu
WANG Jiang-Ning
SHAO Ze-Zhong
TAO Yu-Lei
YAO Qing
Key wordsButterfly   specimen images   automatic identification   deep learning   CaffeNet model   feature extraction   support vector machine     
Cite this article:   
ZHOU Ai-Ming,MA Peng-Peng,XI Tian-Yu et al. Automatic identification of butterfly specimen images at the family level based on deep learning method[J]. ACTA ENTOMOLOGICA SINICA, 2017, 60(11): 1339-1348.
URL:      or
No references of article
[1] YU Shao-Jun, LI Hong, XIE Lin-Bo, Zhou Guo-Ying, HU Jun . Segmentation of larval images of the tea tussock moth, Euproctis pseudoconspersa (Lepidoptera: Lymantriidae) based on the maximum neighborhood difference and region merging[J]. ACTA ENTOMOLOGICA SINICA, 2015, 58(8): 904-910.
[2] ZHU Le-Qing, ZHANG Da-Xing, ZHANG Zhen. Feature description of lepidopteran insect wing images based on WLD and HoC and its application in species recognition[J]. ACTA ENTOMOLOGICA SINICA, 2015, 58(4): 419-426.
[3] ZHU Le-Qing, ZHANG Da-Xing, ZHANG Zhen. Recognition of lepidopteran species based on color name and OpponentSIFT features[J]. ACTA ENTOMOLOGICA SINICA, 2015, 58(12): 1331-1337.
[4] CAI Xiao-Na, HUANG Da-Zhuang, SHEN Zuo-Rui, GAO Ling-Wang. Feasibility of math-morphological characters of wings for classification and identification of noctuid moths (Lepidoptera: Noctuidae)[J]. ACTA ENTOMOLOGICA SINICA, 2012, 55(5): 596-605.
[5] ZHU Le-Qing, ZHANG Zhen. Automatic recognition of insect sounds using MFCC and GMM[J]. ACTA ENTOMOLOGICA SINICA, 2012, 55(4): 466-471.
[6] CHEN Yuan, FENG Feng, YUAN Zhe-Ming. Automatic identification of butterfly species with an improved support vector classification[J]. ACTA ENTOMOLOGICA SINICA, 2011, 54(5): 609-614.
[7] ZHANG Lei, CHEN Xiao-Lin*, HOU Xin-Wen, LIU Cheng-Lin, FAN Li-Min, WANG Xing-Jian. Construction and testing of Automated Fruit Fly Identification System-Bactrocera Macquart (Diptera: Tephritidae)[J]. ACTA ENTOMOLOGICA SINICA, 2011, 54(2): 184-196.
[8] XIANG Chang-Sheng. Application of ARIMA and SVM hybrid model in pest forecast[J]. ACTA ENTOMOLOGICA SINICA, 2010, 53(9): 1055-1060.
Supported by:Beijing Magtech