Monitoring the Change Process of Banana Freshness by GoogLeNet

Freshness is the most critical indicator for fruit quality, and directly impacts consumers’ physical health and their desire to buy. Also, it is an essential factor of the price in the market. Therefore, it is urgent to study the evaluation method of fruit freshness. Taking banana as an example, in this study, we analyzed the freshness changing process using transfer learning and established the relationship between freshness and storage dates. Features of banana images were automatically extracted using the GoogLeNet model, and then classified by the classifier module. The results show that the model can detect the freshness of banana and the accuracy is 98.92%, which is higher than the human detecting level. In order to study the robustness of the model, we also used this model to detect the changing process of strawberry and found that it is still useful. According to the above results, transfer learning is an accurate, non-destructive, and automated fruit freshness monitoring technique. It may be further applied to the field of vegetable detection.

[1]  Nandan Thor.  Applying Machine Learning Clustering and Classification to Predict Banana Ripeness States and Shelf Life , 2017 .

[2]  Andreas Kamilaris,et al.  Deep learning in agriculture: A survey , 2018, Comput. Electron. Agric..

[3]  Kamil Dimililer,et al.  Intelligent Sorting System Based on Computer Vision for Ba-nana Industry , 2015 .

[4]  Nidhi Goel,et al.  Fuzzy classification of pre-harvest tomatoes for ripeness estimation - An approach based on automatic rule learning using decision tree , 2015, Appl. Soft Comput..

[5]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[6]  Daniel S. Kermany,et al.  Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning , 2018, Cell.

[7]  Enbang Li,et al.  Quality Detection and Specie Identification of Apples Based on Multi-Spectral Imaging , 2011 .

[8]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Dorian Q. Fuller,et al.  Bananas: The Spread of a Tropical Forest Fruit as an Agricultural Staple , 2015 .

[10]  Frederik Dara,et al.  APPLYING ARTIFICIAL NEURAL NETWORKS (ANN) TECHNIQUES TO AUTOMATED VISUAL APPLE SORTING , 2016 .

[11]  Raimund Leitner,et al.  Hyperspectral fruit and vegetable classification using convolutional neural networks , 2019, Comput. Electron. Agric..

[12]  Eduardo Jr Piedad,et al.  Postharvest classification of banana (Musa acuminata) using tier-based machine learning , 2018, Postharvest Biology and Technology.

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

[14]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

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

[16]  Sam Kwong,et al.  G-MS2F: GoogLeNet based multi-stage feature fusion of deep CNN for scene recognition , 2017, Neurocomputing.

[17]  A. Siedliska,et al.  Detection of pits in fresh and frozen cherries using a hyperspectral system in transmittance mode , 2017 .

[18]  Marsyita Hanafi,et al.  Prediction of quality attributes and ripeness classification of bananas using optical properties , 2016 .

[19]  D. Surya Prabha,et al.  Assessment of banana fruit maturity by image processing technique , 2015, Journal of Food Science and Technology.

[20]  Ghulam Muhammad,et al.  Automatic Fruit Classification Using Deep Learning for Industrial Applications , 2019, IEEE Transactions on Industrial Informatics.

[21]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[22]  Mónica González,et al.  Antioxidant activity in banana peel extracts: Testing extraction conditions and related bioactive compounds , 2010 .

[23]  Marsyita Hanafi,et al.  Application of laser-induced backscattering imaging for predicting and classifying ripening stages of "Berangan" bananas , 2019, Comput. Electron. Agric..

[24]  Mahmoud Omid,et al.  Classification of peeled pistachio kernels using computer vision and color features , 2017 .

[25]  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.