In the past few years, computer vision in image processing area has made significant progress, like image classification and object detection. Benefiting from the advances of image classification and object detection, it becomes possible to automatically generate one or more sentences to understand the visual content of an image, which is the problem known as Image Captioning. Generating complete and natural image descriptions automatically has large potential effects, such as titles attached to news images, descriptions associated with medical images, text-based image retrieval, information accessed for blind users, human-robot interaction. These applications in image captioning have important theoretical and practical research value. Image captioning is a more complicated but meaningful task in the age of artificial intelligence. Given a new image, an image captioning algorithm should output a description about this image at a semantic level. In this an Image caption generator, Basis on our provided or uploaded image file It will generate the caption from trained model which is trained using algorithms and on large dataset. The main idea behind this is that users will get automated captions when we use or implement it on social media or on any applications.
