Our research tackles the problem of identifying fundus tessellation.We diagnose tessellation for a given retinal image using deep learning algorithms on image data. Tessellation is an eye ailment similar to myopia. For the provided image data, we created a CNN-based system to categorize and recognize tessellated fundus patterns. In order to guarantee noise reduction and data augmentation, the image data is first preprocessed using a normalization technique.A CNN model that has several convolutional and pooling layers is then trained using the normalized dataset in order to extract hierarchical features from the pictures. The last layer used to categorize the degree of tessellation is logistic regression.Metrics including area under the curve (AUC), accuracy, and F1 score are used to assess the performance of the model.