• Rishabh Kunwar
• Shreyas N. Kale
• Adil Khan
• Ajinkya H. Jagadale

Generating proper, accurate content or caption of images deals with generating captions for various query images. The semantic meaning within the image is captured and transformed into proper content. It is going to be a tedious task that collaborates both object detection, image identification, and computer vision. OpenCV library is used to recognize and detect the object properly. The mechanism should detect and create relationships between objects, people, and animals. The project target includes object detection, object recognition using computer vision, and generating captions after processing the entire image. For detection, recognition and creation various different captions for various different images, Regional Object Detector (RODe) is taken into consideration. The proposed methodology mainly focuses on deep learning to further improve upon the prevailing image caption generator system. Experiments are conducted on the Flickr 8k dataset using python language to demonstrate the selected method.

"Image Caption Generator (Deep Learning Approach Using RNN & CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 4, page no.f159-f162, April-2022, Available :http://www.jetir.org/papers/JETIR2204521.pdf

"Image Caption Generator (Deep Learning Approach Using RNN & CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 4, page no. ppf159-f162, April-2022, Available at : http://www.jetir.org/papers/JETIR2204521.pdf