Natural language description of images using hybrid recurrent neural network

Abstract

We presented a learning model that generated natural language description of images. The model utilized the connections between natural language and visual data by produced text line based contents from a given image. Our Hybrid Recurrent Neural Network model is based on the intricacies of Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Bi-directional Recurrent Neural Network (BRNN) models. We conducted experiments on three benchmark datasets, e.g., Flickr8K, Flickr30K, and MS COCO. Our hybrid model utilized LSTM model to encode text line or sentences independent of the object location and BRNN for word representation, this reduced the computational complexities without compromising the accuracy of the descriptor. The model produced better accuracy in retrieving natural language based description on the dataset.

Enhancing currency prediction in international e-commerce: Bayesian-optimized random forest approach using the Klarna dataset

“…b. Accuracy, as a performance metric (2), assesses the proportion of correct predictions relative to the total predictions made by a model [20]. In essence, it quantifies the ratio of accurately predicted outcomes to the overall number of predictions, offering a straightforward indication of a model's correctness.…”

Forecasting smoked rubber sheets price based on a deep learning model with long short-term memory

“…They are scalable, powerful, and versatile, ideal to address highly complex large machine learning tasks, such as video recommending, speech recognition services, and classifying images [18]. An interesting algorithm with an ANN component, such as the convolution neural network (CNN), focuses on image recognition, and recurrent neural network (RNN) [19].…”

Deep learning-based decision support system for weeds detection in wheat fields

“…The first thing we did is annotating those images which is a key technique used to create training data for computer vision. In order that the model perceives objects in their surroundings and automatically assign it a caption, annotated images are needed to train the model to learn to see an area full of objects as we do [21]. We used for that, bounding box technique that requires labellers to draw a box as close as possible to the edges of key objects within the image Figure 3, and stored the top-left and bottom-right points in the corresponding txt file respecting the syntax of class_id x y width height [22].…”