Global Journal of Computer Science and Technology, G: Interdisciplinary, Volume 23 Issue 1

Horizontal flipped image Affine Transformation In; Out = [50,70; 230,50; 50,220] ; [50,70; 230,50; 50,220] Fig. 3: An example of generated images Fig. 4: Workflow of the data augmentation task c) CNN model Use Residual neural network (ResNet) is proposed in 2015, by He et al. [20]. ResNet won the first place at the ImageNet Large Scale Visual Recognition Challenge (ILSVRC 2015). To preserve knowledge, reduce losses and boost performance during the training phase, ResNet introduced residual connections between layers. A residual connection in a layer means that the output of a layer is convolution of its input plus its input [21]. ReNet50 is used in this research. It consists of 50 layers as it is shown by the Fig. 5. The model is updated by replacing the number (1000) of nodes of the softmax output layer by 5 (corresponding to the number of treated mango leaf diseases). d) Implementation details The data augmentation process and ResNet50 model are all carried out using respectively, OpenCV and Keras labreries. Model’s training parameters used include Adam optimizer with a learning rate of 0.001, binary cross-entropy (loss function) and epochs of 8. The model is trained on a server with an NVIDIA GPU and 32 GB of RAM. IV. R esult and D iscussion The initial small dataset is splitted as follow: 64% for training, 16% for validation and 20% for testing. After randomly splitting the dataset, we have 1,600 images for training, 400 images for validation and 500 images for testing. Results sho that the training accuracy (87.18%) is greater than the testing accuracy (39.34%). So the model overfitted as it is shown by the Fig. 6. A Combination of Data Augmentation Techniques for Mango Leaf Diseases Classification © 2023 Global Journals Global Journal of Computer Science and Technology Volume XXIII Issue I Version I 5 ( )G Year 2023