Insect Sound Recognition Based on Convolutional Neural Network

A novel insect sound recognition system using enhanced spectrogram and convolutional neural network is proposed. Contrast-limit adaptive histogram equalization (CLAHE) is adopted to enhance R-space spectrogram. Traditionally, artificial feature extraction is an essential step of classification, introducing extra noise caused by subjectivity of individual researchers. In this paper, we construct a convolutional neural network (CNN) as classifier, extracting deep feature by machine learning. Mel-Frequency Cepstral Coefficient (MFCC) and chromatic spectrogram have been compared with enhanced R-space spectrogram as feature image. Eventually, 97.8723 % accuracy rate is achieved among 47 types of insect sound from USDA library.

[1]  Kan Li,et al.  Automatic insect recognition using optical flight dynamics modeled by kernel adaptive ARMA network , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Yan Liang,et al.  Adaptive extended piecewise histogram equalisation for dark image enhancement , 2015, IET Image Process..

[3]  K. M. Coggins,et al.  Detection and classification of insect sounds in a grain silo using a neural network , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[4]  Anushikha Singh,et al.  Using bioacoustic signals and Support Vector Machine for automatic classification of insects , 2016, 2016 3rd International Conference on Signal Processing and Integrated Networks (SPIN).

[5]  Mingyin Yao,et al.  Study on Image Recognition of Insect Pest of Sugarcane Cotton Aphis Based on Rough Set and Fuzzy C-means Clustering , 2009, 2009 Third International Symposium on Intelligent Information Technology Application.

[6]  Ke Chen,et al.  Turning wingbeat sounds into spectrum images for acoustic insect classification , 2017 .

[7]  Wang Jun,et al.  Combination of contrast limited adaptive histogram equalisation and discrete wavelet transform for image enhancement , 2015, IET Image Process..

[8]  Daniel P. W. Ellis,et al.  Applying Machine Learning and Audio Analysis Techniques to Insect Recognition in Intelligent Traps , 2013, 2013 12th International Conference on Machine Learning and Applications.

[9]  Nikos Fakotakis,et al.  Automatic acoustic identification of crickets and cicadas , 2007, 2007 9th International Symposium on Signal Processing and Its Applications.

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Driss Mammass,et al.  Automatic recognition of plant leaves diseases based on serial combination of two SVM classifiers , 2016, 2016 International Conference on Electrical and Information Technologies (ICEIT).

[12]  Heikki Huttunen,et al.  Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection , 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[13]  Ying Wei,et al.  A Method of Insect Recognition Based on Spectrogram , 2014 .

[14]  Zhang Zhen,et al.  Insect Sound Recognition Based on SBC and HMM , 2010, 2010 International Conference on Intelligent Computation Technology and Automation.

[15]  Zhu Le-Qing,et al.  Insect Sound Recognition Based on MFCC and PNN , 2011, 2011 International Conference on Multimedia and Signal Processing.

[16]  Lin Zhu,et al.  Hyperspectral Images Classification With Gabor Filtering and Convolutional Neural Network , 2017, IEEE Geoscience and Remote Sensing Letters.

[17]  V. A. E. Chaves,et al.  Katydids acoustic classification on verification approach based on MFCC and HMM , 2012, 2012 IEEE 16th International Conference on Intelligent Engineering Systems (INES).