• BIKKI SANDHYA
• I KULLAYAMMA

The century is extensively dependent on image-based information processing. Image processing can be described as the process of manipulating an image to either improve its quality or extract valuable information from it. In lines with that, image captioning is an increasingly emerging technique used in a variety of applications such as usage in virtual assistants, image indexing, visually impaired persons, social media and several other natural processing applications. The project aims to develop a targeted voice-based advertisements from images using CNN and LSTM, with using MATLAB tools. For an efficient image caption generator, the system needs to identify the information and should further generate the most relevant and brie f description for a syntactically and semantically correct image. An image caption generation is a task that involves the NLP (natural language processing) concept for understanding the description of an image. The main target of the proposed project is to obtain ads for specific images by combining CNN and LSTM. First, the description of the image is obtained. Then based on the information in the captions, specific ads are obtained. After obtaining the description, it will be converted into text and the text into a voice. Image description is a best solution used for a visually impaired people who are unable to comprehend visuals. The project could have great impact in social media platforms where images are the primary source of data.

NLP (natural language processing), CNN (Convolutional neural network), LSTM (Long short-term memory), RNN (recurrent neural network).

"Developing an voice based advertisement generator from images using CNN & LSTM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.e145-e154, May-2024, Available :http://www.jetir.org/papers/JETIR2405416.pdf

"Developing an voice based advertisement generator from images using CNN & LSTM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppe145-e154, May-2024, Available at : http://www.jetir.org/papers/JETIR2405416.pdf