Image captioning is a sentence summarizing the semantic content of an image. Describing the essential information of an image in the form of a statement typically deals with computer vision and natural language processing. The prior research frequently addressed this subject simply using standard machine learning approaches that model such systems by extracting the hand-engineered characteristics from the input data. With the resurgence of deep-learning approaches, the image captioning area has experienced state-of-the-art outcomes in numerous application domains, including visual aid, traffic assistance, medical support, and remote sensing. This research thoroughly reviews the application domain-based image captioning frameworks by addressing both classical and modern deep learning-based architectures. We further propose a taxonomy to characterize the same by studying their distinct technological foundations and performances across diverse datasets. We also describe evaluation metrics used to examine the captioning image models across several domains. Finally, we highlight open research problems concerning such models from a futuristic standpoint.

Apple is one of the most popular plants in the Indian-origin Kashmir valley, where it is grown on about half of the horticultural land. Every year, the apples from Kashmir are exported to other areas of the globe, creating a substantial amount of revenue. However, apple trees are prone to diseases like apple scab, alternaria leaf blotch, and apple rot, which devastate apple yields and cause major losses for apple growers. Disease in apple plants mostly originates in the leaves and causes significant losses to apple farmers. Consequently, the prompt detection or prediction of such diseases is essential in a country like India, where half of the population does farming. The early detection of apple plant diseases may enable apple producers to take the necessary precautions immediately to save the fruits from illness. The conventional methods of apple plant disease prediction are time-consuming and laborious, involving lab assistance to diagnose the apple leaves for possible diseases. With the advent of machine learning and deep learning, it is now possible to quickly determine if a plant is infected or not with reliable accuracy. In this article, we introduce D-KAP, a deep learning-based Kashmiri apple plant disease prediction framework capable of detecting the above-described diseases. For feature extraction and prediction, our model employs the advanced deep learning capabilities of Convolutional Neural Networks (CNN). In conclusion, our framework produces state-of-the-art results in identifying apple plant diseases with an accuracy of 92 percent over testing samples. In addition, we also introduce a novel Kashmiri apple plant leaf dataset containing samples of three distinct diseases along with healthy leaves.