Bangla language textual image description by hybrid neural network model

Abstract

Automatic image captioning task in different language is a challenging task which has not been well investigated yet due to the lack of dataset and effective models. It also requires good understanding of scene and contextual embedding for robust semantic interpretation of images for natural language image descriptor. To generate image descriptor in Bangla, we created a new Bangla dataset of images paired with target language label, named as Bangla Natural Language Image to Text (BNLIT) dataset. To deal with the image understanding, we propose a hybrid encoder-decoder model based on encoder-decoder architecture and the model is evaluated on our newly created dataset. This proposed approach achieves significance performance improvement on task of semantic retrieval of images. Our hybrid model uses the Convolutional Neural<br />Network as an encoder whereas the Bidirectional Long Short Term Memory is used for the sentence representation that decreases the computational complexities without trading off the exactness of the descriptor. The model yielded benchmark accuracy in recovering Bangla natural language and we also conducted a thorough numerical analysis of the model performance on the BNLIT dataset.

Aerial image semantic segmentation based on 3D fits a small dataset of 1D

“…The description of the course of research should be supported references, so the explanation can be accepted scientifically [5], [6]. Figures 1 and 2 and Table 1 are presented center, as shown and cited in the manuscript [2], [7]- [12]. The settlement curves produced at SG1 has been illustrated in Figure 2(a) and SG2 has been illustrated Figure 2(b).…”

“…Explaining research chronological, including research design, research procedure (in the form of algorithms, Pseudocode or other), how to test and data acquisition [2]- [4]. The description of the course of research should be supported references, so the explanation can be accepted scientifically [5], [6].…”

“…The Semantic Drone Dataset focuses on improving the safety of autonomous drone flying and landing processes by using semantic comprehension of urban settings. More than 20 buildings are depicted in the imagery, which was captured from a nadir (bird's eye) view at the height of 5 to 30 meters distant from the ground [2]- [4]. Images with a resolution of 6,000×4,000px were captured with a high-resolution camera (24Mpx) 5,6.…”

Text-to-image generation based on AttnDM-GAN and DMAttn-GAN: applications and challenges

“…In the last few years, when the generative adversarial networks (GANs) have first introduced, they have shown very exciting results in the classification and generation fields [3], and they are considered a leap in this area. Text-to-image synthesis (the reverse of image captioning [4]) is considered an emerging domain where the generation process aims mainly to generate output images as real as possible which are consistent with the textual input description [5]- [10]. GAN is a deep neural network that consists of two competitive networks called generator and discriminator.…”

Development of Bangla Spell and Grammar Checkers: Resource Creation and Evaluation

“…Bangla is a language spoken by roughly 250 million native speakers around the world, mainly in Bangladesh and some regions of India [1]. Every day hundreds of books, magazines, and newspapers are being published in Bangla.…”