Automatic image description generation has gained significant attention in recent years due to its potential applications in various domains. This paper proposes an image description generator using a deep learning-based approach to automatically generate textual descriptions for given images. The suggested model extracts the visual features using convolutional neural networks (CNNs) and generates systematic and contextually relevant description using recurrent neural networks (RNNs). To train the model, RSICD (Remote Sensing Image Captioning Dataset) dataset consisting of paired images and corresponding human-generated descriptions is utilized. The CNN extracts high-level visual features from the input images, which are then fed into the RNN for language modeling. The RNN employs a long short-term memory (LSTM) architecture to capture sequential dependencies in the generated descriptions. The generated descriptions are assessed using common evaluation metrics like BLEU score.