ENHANCE APPROACH FOR AUTO CAPTION GENERATION ON DIFFERENT NEWS IMAGES DATASET USING FUZZY LOGIC

These times, whenever retrieving images from the search Engines that retrieves images without analysing their include restrain, simply by matching user inquires against the image’s file name and format, user comment the tags, captions, and, generally, text surrounding the image. Also the retrieved image contains any textual data along with the images. Our announced the task of automatic caption generation for news images. The task fuses insights from computer vision and natural language processing and holds promise for various multimedia applications, such as image retrieval, development of tools supporting news media management, and for individuals with visual impairment. It is possible to learn a caption generation model from weakly labelled data without costly manual involvement. Instead of manually creating annotations, image captions are treated as labels for the image. Although the caption words are admittedly noisy compared to traditional human-created keywords, we show that they can be used to learn the correspondences between visual and textual modalities, and also serve as a gold standard for the caption generation task. We have presented extractive and abstractive caption generation models. A key aspect of our approach is to allow both the visual and textual modalities to influence the generation task. We proposed fuzzy rules for generating caption of the new image.