The aim of this paper is to focus on utilizing deep learning approaches for the building of an intelligent image captioning system. To bridge the semantic gap between the literal depiction of the images and the languages, this combined architecture is employed. The structure of the model is of an encoder-decoder architecture which consists of InceptionV3 CNN for feature extraction and LSTMs with attention mechanism to generate the captions. The complexity of the model is determined based on the usage of the Flickr8K image dataset and it was revealed through the results that it can generate accurate, interesting and appropriate content describing the images. This study has good prospects for the development of framework for learning with multiple modalities especially for usage databases that require content-based searching, image-based data retrieval and usability for users with sight problems. The results show that InceptionV3 Model performs best with BLEU Score of 0.8504 followed by DenseNet 201 with score of 0.8274. Further analysis shows that the best BLEU score of 0.9172 is attained when the dataset of the best performing model, Inception V3, is split into 75:25 Train:Test and running the model for 50 epochs is done. This resulted in a loss function value of 0.70 for the above-mentioned configuration.