Image based fruit category classification by 13-layer deep convolutional neural network and data augmentation
- 496 Downloads
Fruit category identification is important in factories, supermarkets, and other fields. Current computer vision systems used handcrafted features, and did not get good results. In this study, our team designed a 13-layer convolutional neural network (CNN). Three types of data augmentation method was used: image rotation, Gamma correction, and noise injection. We also compared max pooling with average pooling. The stochastic gradient descent with momentum was used to train the CNN with minibatch size of 128. The overall accuracy of our method is 94.94%, at least 5 percentage points higher than state-of-the-art approaches. We validated this 13-layer is the optimal structure. The GPU can achieve a 177× acceleration on training data, and a 175× acceleration on test data. We observed using data augmentation can increase the overall accuracy. Our method is effective in image-based fruit classification.
KeywordsConvolutional neural network Fully connected layer Softmax Fruit category identification
This study was supported by Natural Science Foundation of China (61602250), Natural Science Foundation of Jiangsu Province (BK20150983), Open fund of Key Laboratory of Guangxi High Schools Complex System and Computational Intelligence (2016CSCI01).
Compliance with ethical standards
Conflict of interest
We have no conflicts of interest to disclose with regard to the subject matter of this paper.
- 5.Chen Y (2016) Voxelwise detection of cerebral microbleed in CADASIL patients by leaky rectified linear unit and early stopping: a class-imbalanced susceptibility-weighted imaging data study. Multime Tools Appl. https://doi.org/10.1007/s11042-017-4383-9
- 15.Jiang YL, Zur RM, Pesce LL et al (2009) A Study of the Effect of Noise Injection on the Training of Artificial Neural Networks. In International Joint Conference on Neural Networks (IJCNN), IEEE, Atlanta, pp 2784–2788Google Scholar
- 16.Kim JH, Hong HG, Park KR (2017) Convolutional neural network-based human detection in nighttime images using visible light camera sensors. Sensors (Basel) 17(5). https://doi.org/10.3390/s17051065
- 18.Lee CH, Chien JT (2016) Deep unfolding inference for supervised topic model. In International Conference on Acoustics, Speech And Signal Processing Proceedings, IEEE, Shanghai, pp 2279–2283Google Scholar
- 20.Liu F, Snetkov L, Lima D (2017) Summary on fruit identification methods: A literature review. Adv Soc Sci Educ Hum Res 119:1629–1633Google Scholar
- 21.Lu Z (2016) Fractional Fourier entropy increases the recognition rate of fruit type detection. BMC Plant Biol 16(S2) Article ID: 10Google Scholar
- 22.Lu Z, Li Y (2017) A fruit sensing and classification system by fractional fourier entropy and improved hybrid genetic algorithm. In 5th International Conference on Industrial Application Engineering (IIAE). Kitakyushu, Institute of Industrial Applications Engineers, Japan, pp 293–299Google Scholar
- 26.Qian RQ, Yue Y, Coenen F et al (2016) Traffic sign recognition with convolutional neural network based on max pooling positions. In 2th International Conference on Natural Computation, Fuzzy Systems And Knowledge Discovery (ICNC-FSKD), IEEE, Changsha pp 578–582Google Scholar
- 35.Tovar MF, Losada HV (2016) Fuzzy systems: case study classification of fruit Mc Stipitata Vaug (Araza). Amazonia Investiga 5(9):45–56Google Scholar
- 36.Wei L (2015) Fruit classification by wavelet-entropy and feedforward neural network trained by fitness-scaled chaotic ABC and biogeography-based optimization. Entropy 17(8):5711–5728Google Scholar
- 39.Smirnov EA, Timoshenko DM, Andrianov SN (2014) Comparison of regularization methods for imagenet classification with deep convolutional neural networks. In 2nd Aasri Conference on Computational Intelligence And Bioinformatics (CIB). Elsevier Science Bv, South Korea, pp 89–94Google Scholar
- 42.Zhang Y, Qiu M, Tsai CW et al (2015) Health-CPS: healthcare cyber-physical system assisted by cloud and big data. IEEE Syst J PP(99):1–8Google Scholar
- 44.Zhu SG, Du JP (2014) Visual tracking using max-average pooling and weight-selection strategy. J Appl Math 2014:828907Google Scholar