Abstract: In the era of rapidly growing digital content, the automatic generation of image captions has gain significant attention in the field of deep learning and computer vision. Our proposed model leverages deep learning techniques, including convolutional neural networks (CNNs) for image feature extraction and recurrent neural networks (RNNs) with attention mechanisms for caption generation. To evaluate the performance of our model, we employ a comprehensive dataset containing a diverse range of images and corresponding human-generated captions. In conclusion, our deep learning-based image captioning project offers a promising solution to the challenge of automatically generating meaningful and contextually accurate descriptions for images. The potential applications of the technology are vast, and we anticipate that it will continue to various fields, including artificial intelligence, accessibility, content creation, content management and publishing across various social media platform.