Image based fruit category classification by 13-layer deep convolutional neural network and data augmentation

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.

[1]  Oscar Núñez,et al.  Characterization, classification and authentication of fruit-based extracts by means of HPLC-UV chromatographic fingerprints, polyphenolic profiles and chemometric methods. , 2017, Food chemistry.

[2]  F. Garcia,et al.  Fruit Classification by Extracting Color Chromaticity, Shape and Texture Features: Towards an Application for Supermarkets , 2016, IEEE Latin America Transactions.

[3]  M. Fatih Adak,et al.  Classification of E-Nose Aroma Data of Four Fruit Types by ABC-Based Neural Network , 2016, Sensors.

[4]  Junping Du,et al.  Visual Tracking Using Max-Average Pooling and Weight-Selection Strategy , 2014, J. Appl. Math..

[5]  Jucimara Colombo,et al.  Effect of Melatonin in Epithelial Mesenchymal Transition Markers and Invasive Properties of Breast Cancer Stem Cells of Canine and Human Cell Lines , 2016, PloS one.

[6]  Saeed Yaghoubi,et al.  Resource allocation in multi-class dynamic PERT networks with finite capacity , 2015, Eur. J. Oper. Res..

[7]  Pasquale Filannino,et al.  Bioprocessing technology to exploit organic palm date (Phoenix dactylifera L. cultivar Siwi) fruit as a functional dietary supplement , 2017 .

[8]  Fangyuan Liu,et al.  Summary on fruit identification methods: A literature review , 2017 .

[9]  Jen-Tzung Chien,et al.  Deep unfolding inference for supervised topic model , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[10]  Mostafa Mehdipour-Ghazi,et al.  Plant identification using deep neural networks via optimization of transfer learning parameters , 2017, Neurocomputing.

[11]  D. Shen,et al.  Identification of progressive mild cognitive impairment patients using incomplete longitudinal MRI scans , 2015, Brain Structure and Function.

[12]  Duc-Dung Nguyen,et al.  An adaptive over-split and merge algorithm for page segmentation , 2016, Pattern Recognit. Lett..

[13]  Xiangrong Zhou,et al.  Classification of teeth in cone-beam CT using deep convolutional neural network , 2017, Comput. Biol. Medicine.

[14]  Christian Bräuer-Burchardt,et al.  Underwater 3D Surface Measurement Using Fringe Projection Based Scanning Devices , 2015, Sensors.

[15]  Karen Drukker,et al.  A study of the effect of noise injection on the training of artificial neural networks , 2009, 2009 International Joint Conference on Neural Networks.

[16]  Umezuruike Linus Opara,et al.  Analysis of airflow and heat transfer inside fruit packed refrigerated shipping container: Part I - Model development and validation , 2017 .

[17]  Yilong Yin,et al.  Choroid segmentation from Optical Coherence Tomography with graph-edge weights learned from deep convolutional neural networks , 2017, Neurocomputing.

[18]  Yudong Zhang,et al.  Classification of Fruits Using Computer Vision and a Multiclass Support Vector Machine , 2012, Sensors.

[19]  Kok Swee Sim,et al.  Brain early infarct detection using gamma correction extreme-level eliminating with weighting distribution. , 2016, Scanning.

[20]  Frans Coenen,et al.  Traffic sign recognition with convolutional neural network based on max pooling positions , 2016, 2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD).

[21]  Gonzalo Pajares,et al.  Cross entropy based thresholding for magnetic resonance brain images using Crow Search Algorithm , 2017, Expert Syst. Appl..

[22]  Meikang Qiu,et al.  Health-CPS: Healthcare Cyber-Physical System Assisted by Cloud and Big Data , 2017, IEEE Systems Journal.

[23]  Siham Tabik,et al.  A snapshot of image pre-processing for convolutional neural networks: case study of MNIST , 2017, Int. J. Comput. Intell. Syst..

[24]  Yudong Zhang,et al.  Fruit Classification by Wavelet-Entropy and Feedforward Neural Network Trained by Fitness-Scaled Chaotic ABC and Biogeography-Based Optimization , 2015, Entropy.

[25]  Siqi Li,et al.  Joint multiple fully connected convolutional neural network with extreme learning machine for hepatocellular carcinoma nuclei grading , 2017, Comput. Biol. Medicine.

[26]  Elena Marchiori,et al.  Convolutional neural networks for vibrational spectroscopic data analysis. , 2017, Analytica chimica acta.

[27]  Rolando González-José,et al.  Automatic ear detection and feature extraction using Geometric Morphometrics and convolutional neural networks , 2017, IET Biom..

[28]  Kim-Han Thung,et al.  Content-based image quality metric using similarity measure of moment vectors , 2012, Pattern Recognit..

[29]  Dinggang Shen,et al.  Neurodegenerative disease diagnosis using incomplete multi-modality data via matrix shrinkage and completion , 2014, NeuroImage.

[30]  Kang Ryoung Park,et al.  Convolutional Neural Network-Based Human Detection in Nighttime Images Using Visible Light Camera Sensors , 2017, Sensors.

[31]  Lu Zhihai,et al.  A Fruit Sensing and Classification System by Fractional Fourier Entropy and Improved Hybrid Genetic Algorithm , 2017 .

[32]  Yanjie Li,et al.  Rapid classification of Chinese quince (Chaenomeles speciosa Nakai) fruit provenance by near-infrared spectroscopy and multivariate calibration , 2016, Analytical and Bioanalytical Chemistry.

[33]  Yin Zhang,et al.  GroRec: A Group-Centric Intelligent Recommender System Integrating Social, Mobile and Big Data Technologies , 2016, IEEE Transactions on Services Computing.

[34]  Serge Andrianov,et al.  Comparison of Regularization Methods for ImageNet Classification with Deep Convolutional Neural Networks , 2014 .

[35]  Xiang Bai,et al.  Text/non-text image classification in the wild with convolutional neural networks , 2017, Pattern Recognit..

[36]  Milher Fabián Tovar,et al.  Sistemas Difusos: Caso de Estudio Clasificación del fruto Mc Stipitata Vaug (Áraza) , 2016 .

[37]  Hong Chen,et al.  Voxelwise detection of cerebral microbleed in CADASIL patients by leaky rectified linear unit and early stopping , 2017, Multimedia Tools and Applications.

[38]  Lieven Annemans,et al.  Effectiveness of Pricing Strategies on French Fries and Fruit Purchases among University Students: Results from an On-Campus Restaurant Experiment , 2016, PloS one.

[39]  Min Chen,et al.  iDoctor: Personalized and professionalized medical recommendations based on hybrid matrix factorization , 2017, Future Gener. Comput. Syst..

[40]  Yudong Zhang,et al.  Fruit classification using computer vision and feedforward neural network , 2014 .

[41]  Mauridhi Hery Purnomo,et al.  Electronic nose based on partition column integrated with gas sensor for fruit identification and classification , 2016, Comput. Electron. Agric..

[42]  Sung Wook Baik,et al.  Efficient object-based surveillance image search using spatial pooling of convolutional features , 2017, J. Vis. Commun. Image Represent..

[43]  N. Karssemeijer,et al.  Discriminating solitary cysts from soft tissue lesions in mammography using a pretrained deep convolutional neural network , 2017, Medical physics.

[44]  Yudong Zhang,et al.  Fruit classification by biogeography‐based optimization and feedforward neural network , 2016, Expert Syst. J. Knowl. Eng..

[45]  Mark D Cicero,et al.  Training and Validating a Deep Convolutional Neural Network for Computer-Aided Detection and Classification of Abnormalities on Frontal Chest Radiographs , 2017, Investigative radiology.