The process that produces written descriptions that effectively represent the meaning and context of an image is known as image captioning. To integrate visual and textual data, it needs to blend computer vision and natural language processing methods. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs), such as long-short-term memory (LSTM) networks, are two methods used for captioning images. High-level visual features from the input image are extracted by the CNN, and the RNN uses those features to generate the matching captions. Residual Network is a deep CNN architecture with exceptional results in a range of computer vision tasks, including the classification of images. ResNet has been used as the foundation for extracting picture features. ResNet and CNN abstracts an image's visual information via feature extraction and uses neural networks with recurrent architecture to provide meaningful, contextually appropriate captions. Machines are now able to comprehend and speak about the visual world in a manner similar to humans because of the integration of computer vision and natural language processing.