Image captioning using deep learning is a prominent research area in computer vision and natural language processing that focuses on automatically generating descriptive textual captions for images. Early approaches combined convolutional neural networks (CNNs) for image feature extraction with recurrent neural networks (RNNs) or long short-term memory (LSTM) networks for sequence generation. Subsequent research introduced attention mechanisms to focus on salient image regions during caption generation, significantly improving descriptive accuracy and fluency. More recent advances leverage transformer-based architectures, multimodal embeddings, and reinforcement learning to optimize captioning for semantic relevance and evaluation metrics such as BLEU and CIDEr. Applications of image captioning include assistive technologies for visually impaired users, content-based image retrieval, social media automation, and human–computer interaction. Current research also explores dense captioning, cross-modal pretraining, and multilingual captioning, as well as methods robust to complex scenes, occlusions, and diverse domains, establishing deep learning-based image captioning as a key technology for visual understanding and language generation.