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

The data augmentation process (Fig. 4) is carried out as follow: First step: For each of the above mentioned data augmentation strategies (except affine transformation), a new dataset for training and validation is generated (Fig. 3, Table 2). Images of the original dataset are added to the generated one. This is to know the impact of each data augmentation strategy on the overall performance of the model. Second step: Every strategy (except affine transformation) is combined respectively by the 4 others sequentially to generate new datasets (Table 2). Final step: Affine transformation is applied to the best combination that gives the best performance to the DL model (Table 3). The augmentation techniques are carried out using python Open Source Computer Vision Library (OpenCV). Table 1: Composition of the datasets in the first step Original Original & Blur Original & Contrast Original & Flip Original & Noise Original & Zoom Train 1600 3200 6400 4800 3200 6400 Validation 400 800 1600 1200 800 1600 Test 500 500 500 500 500 500 Total 2500 4500 8500 6500 4500 8500 Table 2: Composition of the datasets in the second step Blur & Contrast Blur & Flip Blur & Noise Blur & Zoom Contrast & Flip Contrast & Noise Contrast & Zoom Flip & Noise Flip & Zoom Noise & Zoom Train 8000 6400 4800 8000 9600 8000 11200 6400 9600 8000 Validatio n 2000 1600 1200 2 000 2400 2000 2800 1600 2400 2000 Test 500 500 500 500 500 500 500 500 500 500 Total 10500 8500 6500 10500 12500 10500 14500 8500 12500 10500 Original image Noised image Blurred image (mean: 0.1, std: 0.5) (std: 0.5, kernel: (5,15)) Contrast; {c,b} = {2, 4} Zoomed image (param: 5) Vertical flipped image 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 4 ( ) Year 2023 G