Search

Captioning of colored images has been around for quite some time now, it uses object detection and the spatial relation between the objects to generate captions. There have been numerous approaches to caption colorized images in the past, but there have been a very few. In this paper we present an approach to caption Black and white images without any attempt of colorization. We have used transfer learning to implement Inception V3, a CNN model developed by Google and a runner up in the ImageNet image classification challenge, to generate captions from Black and white images achieving an accuracy of 45.77% on the validation set.

Deep Learning and Internet of Things (IoT) are some top fields of research in computer science now days. Many researches are going on to incorporate the best of both the fields and to collaborate them into one. Inspired from this, this paper works on using and creating an efficient Deep Learning model for colorizing the image and transport them to remote systems through IoT deployment tools. This paper develops two models, namely Alpha and Beta, for the colorization of the greyscale images. Efficient models are developed to lessen the loss rate to around 0.005. Then the paper uses tools like AWS Greengrass and Docker for the deployment of the model, thus combining Deep Learning with IoT deployment tools.

Bee Colony optimization techniques are inspired by the high level of mutual intelligence shown by the natural bees in the food foraging process. It is a population based natural search algorithm which provides the base to solve metaheuristic computational optimization problems. In this paper we have carried out a literature review of the applications of BCO into various areas of computational problems where they prove their worth in providing optimized solutions. We have further carried out a tabular comparison of the work performed by the various researchers by applying the the BCO as optimization algorithms for solving the Optimization Problems.