This Paper aims to classify the type of flowers using convolutional neural networks (CNNs). We will start by gathering a dataset of flower images, resizing and normalizing them as part of data preprocessing. We will then divide the dataset into three subsets, namely training, validation, and test sets. We will design a CNN architecture with multiple convolutional layers, pooling layers, and fully connected layers. Techniques like dropout and batch normalization will be applied to improve the model's generalization ability and prevent overfitting. The training set will be used to train the model, and the validation set will be used to prevent overfitting by using techniques like early stopping and learning rate scheduling. Finally, we will evaluate the performance of the model on the test set and report the classification accuracy. Our approach will be compared to other classification algorithms such as logistic regression and decision trees, to demonstrate the effectiveness of CNNs in solving classification problems. In addition, we will explore techniques like data augmentation and transfer learning to further enhance the model's performance. Data augmentation involves creating new training examples by transforming the original images through techniques like rotation, scaling, and flipping. Meanwhile, transfer learning involves using pre-trained models as a starting point and fine-tuning them for a specific task.