Automated Image Capturing Using CNN and RNN


  • Lakshitaa Sehgal
  • Simran Mandan


Images, Convolutional Neural Networks (CNN), conventional strategies, CNN and RNN, encoder-decoder model, language


With the evolution of generation picture captioning is a totally essential issue of virtually all industries regarding information abstraction. To interpret such information by a machine may be very complex and time-consuming. For a device to apprehend the context and surroundings info of a photo, it wishes a higher understanding of the outline projected from the picture. Many deep gaining knowledge of techniques have now not followed conventional strategies however are changing the manner a machine is familiar with and translates. Majorly the usage of Captions and attaining a properly-described vocabulary linked to images. The improvements in technology and ease of computation of extensive information have made it possible for us to without problems observe deep gaining knowledge of in several projects the usage of our non-public computer. A solution calls for each that the content of the photograph is thought and translated to that means within the phrases of words and that the phrases must string collectively to be comprehensible. It combines both laptop imagination and prescient using deep mastering and herbal language processing and marks virtually tough trouble in broader synthetic intelligence. In this project, we create an automatic photo captioning version with the use of Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) to provide a series of texts that greatly describe the photograph. Using Flickr 8000 dataset, we have organized our model. As image captioning requires a neural network right here we've got nicely described steps to carry out. To create a deep neural community using CNN and RNN, we first hyperlink the description to the photograph convolutional neural network will take the image and segregate it into a number of traits, the recurrent neural community will make this function into well-described descriptive language. The task makes use of the encoder-decoder model, wherein the CNN which performs the function extraction and the output of the encoder is fed to the decoder which approaches the categorized features into suitable sentences. The characteristic extraction could be finished by using today's Inception V3 module-50 era with the method of switch learning in order that we will adjust the venture-precise to our cause. The language model uses a herbal language toolkit for simple herbal language processing and the structure used for the recurrent neural networks is lengthy-brief term memory.


Download data is not yet available.




How to Cite

L. Sehgal and S. Mandan, “Automated Image Capturing Using CNN and RNN”, IJRESM, vol. 5, no. 1, pp. 13–17, Jan. 2022.




Most read articles by the same author(s)