Related papers: Towards Deployable OCR models for Indic languages

Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. This is creating a new version of the digital divide: the…

There has been an increasing interest in large speech models that can perform multiple tasks in a single model. Such models usually adopt an encoder-decoder or decoder-only architecture due to their popularity and good performance in many…

Most existing machine translation systems operate at the level of words, relying on explicit segmentation to extract tokens. We introduce a neural machine translation (NMT) model that maps a source character sequence to a target character…

This paper presents a novel approach towards Indic handwritten word recognition using zone-wise information. Because of complex nature due to compound characters, modifiers, overlapping and touching, etc., character segmentation and…

Tremendous progress has been made in recent years in developing better image captioning models, yet most of them rely on a separate object detector to extract regional features. Recent vision-language studies are shifting towards the…

Multimodal research has predominantly focused on single-image reasoning, with limited exploration of multi-image scenarios. Recent models have sought to enhance multi-image understanding through large-scale pretraining on interleaved…

Automatic Part-of-speech (POS) tagging is a preprocessing step of many natural language processing (NLP) tasks such as name entity recognition (NER), speech processing, information extraction, word sense disambiguation, and machine…

We propose a novel method that uses convolutional neural networks (CNNs) for feature extraction. Not just limited to conventional spatial domain representation, we use multilevel 2D discrete Haar wavelet transform, where image…

Capsule networks (CapsNets) have recently gotten attention as a novel neural architecture. This paper presents the sequential routing framework which we believe is the first method to adapt a CapsNet-only structure to sequence-to-sequence…

We develop a representation suitable for the unconstrained recognition of words in natural images: the general case of no fixed lexicon and unknown length. To this end we propose a convolutional neural network (CNN) based architecture which…

This paper presents a printed Bengali and English text OCR system developed by us using a single hidden BLSTM-CTC architecture having 128 units. Here, we did not use any peephole connection and dropout in the BLSTM, which helped us in…

For analysing and/or understanding languages having no word boundaries based on morphological analysis such as Japanese, Chinese, and Thai, it is desirable to perform appropriate word segmentation before word embeddings. But it is…

The Connectionist Temporal Classification (CTC) has achieved great success in sequence to sequence analysis tasks such as automatic speech recognition (ASR) and scene text recognition (STR). These applications can use the CTC objective…

Detection and recognition of text from scans and other images, commonly denoted as Optical Character Recognition (OCR), is a widely used form of automated document processing with a number of methods available. Yet OCR systems still do not…

Text recognition is a long-standing research problem for document digitalization. Existing approaches are usually built based on CNN for image understanding and RNN for char-level text generation. In addition, another language model is…

This thesis addresses automatic lexical error recovery and tokenization of corrupt text input. We propose a technique that can automatically correct misspellings, segmentation errors and real-word errors in a unified framework that uses…

Graph Convolutional Networks (GCN) have achieved state-of-art results on single text classification tasks like sentiment analysis, emotion detection, etc. However, the performance is achieved by testing and reporting on resource-rich…

Natural Language Processing (NLP) and especially natural language text analysis have seen great advances in recent times. Usage of deep learning in text processing has revolutionized the techniques for text processing and achieved…

Handwritten character recognition is a hot topic for research nowadays. If we can convert a handwritten piece of paper into a text-searchable document using the Optical Character Recognition (OCR) technique, we can easily understand the…

English Character Recognition (CR) has been extensively studied in the last half century and progressed to a level, sufficient to produce technology driven applications. But same is not the case for Indian languages which are complicated in…