Open AccessCAPTION GENERATION OF IMAGES USING CNN AND LSTM
Author(s) -
Ummar Yousuf,
Ravinder Pal Singh,
Monika Mehra
Publication year - 2022
Publication title -
international journal of innovative research in engineering and management
Language(s) - English
Resource type - Journals
ISSN - 2350-0557
DOI - 10.55524/ijirem.2022.9.1.1
Subject(s) - computer science , artificial intelligence , recurrent neural network , convolutional neural network , machine translation , natural language processing , natural language , translation (biology) , language model , pattern recognition (psychology) , speech recognition , computer vision , artificial neural network , biochemistry , chemistry , messenger rna , gene
The contents of a picture are automatically created in Artificial Intelligence (AI), which combines computer vision and natural language processing (NLP) (Natural Language Processing). It is developed a regenerative neuronal model. Computer vision and machine translation are required. This model is used to produce natural-sounding phrases that describe the picture. Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) are used in this model (RNN). The CNN is used to extract features from images, while the RNN is used to generate sentences. The model has been trained in such a manner that when an input image is provided to it, it creates captions that almost accurately describe the image. On various datasets, the model's accuracy, smoothness, and command of language learned from picture descriptions are assessed. These tests reveal that the model typically provides correct descriptions of the input image.