Handwritten Amharic Character Recognition Using a Convolutional Neural Network

Gondere, Mesay Samuel; Schmidt-Thieme, Lars; Boltena, Abiot Sinamo; Jomaa, Hadi S.

doi:10.48550/arxiv.1909.12943

Cited by 4 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to recent sequence based deep learning based methods, in this paper the recognition phase does not require segmentation of characters [4,5]. Other recent works have adapted deep learning methods for character based recognition [10,6] and sequence based recognition [1,9]. Sequence based methods particularly address the problem of OCR in an end-to-end fashion using a convolutional neural network as feature extractor from the text image, recurrent neural network as sequence learner, and connectionist temporal classification as a loss function and transcriber.…”

Section: Related Workmentioning

confidence: 99%

“…There are many highly relevant printed as well as handwritten documents available in Ethiopia. These documents are primarily written in Gee'z and Amharic languages covering a large variety of subjects including religion, history, governance, medicine, philosophy, astronomy, and the like [7,10,2]. Hence, due to the need to explore and share the knowledge in these languages, there are further established educational programs outside Ethiopia as well, including Germany, the USA, and China recently.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Amharic Handwritten Word Recognition Using Auxiliary Task

Gondere¹,

Schmidt-Thieme²,

Sharma³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Amharic is one of the official languages of the Federal Democratic Republic of Ethiopia. It is one of the languages that use an Ethiopic script which is derived from Gee'z, ancient and currently a liturgical language. Amharic is also one of the most widely used literature-rich languages of Ethiopia. There are very limited innovative and customized research works in Amharic optical character recognition (OCR) in general and Amharic handwritten text recognition in particular. In this study, Amharic handwritten word recognition will be investigated. State-of-theart deep learning techniques including convolutional neural networks together with recurrent neural networks and connectionist temporal classification (CTC) loss were used to make the recognition in an end-toend fashion. More importantly, an innovative way of complementing the loss function using the auxiliary task from the row-wise similarities of the Amharic alphabet was tested to show a significant recognition improvement over a baseline method. Such findings will promote innovative problem-specific solutions as well as will open insight to a generalized solution that emerges from problem-specific domains.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving Amharic Handwritten Word Recognition Using Auxiliary Task

Gondere¹,

Schmidt-Thieme²,

Sharma³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently there are some encouraging works emerging on Amharic character recognition applying deep learning techniques. The different authors emphasized on different types of documents including printed [2,9,13], ancient [20,11], and handwritten documents [14,13,1]. Accordingly the research efforts in this regard lack complementing each other and improving results based on a clear baseline.…”

Section: Related Workmentioning

confidence: 99%

“…The dataset for Amharic handwritten character recognition experiment was organized from Assabie et al and Samuel et al [5,14]. It was organized to 77 characters with 11 (row) by 7 (column) tabular structure as shown in Table 2.…”

Section: Dataset Preparationmentioning

confidence: 99%

“…First we will introduce the formulation of a multi-task learning setting from the individual tasks. The motivation behind this formulation is to bring the problem of Amharic, Indian, Japanese, and related character recognition [14,17,4,28] to a more general setting so that researchers contribute to the solution with ease. In these languages the alphabets can be organized in a matrix form where one can exploit the information available over the rows and columns as they exhibit similarities, Fig.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-script Handwritten Digit Recognition Using Multi-task Learning

Gondere,

Schmidt-Thieme,

Sharma

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Handwritten digit recognition is one of the extensively studied area in machine learning. Apart from the wider research on handwritten digit recognition on MNIST dataset, there are many other research works on various script recognition. However, it is not very common for multi-script digit recognition which encourage the development of robust and multipurpose systems. Additionally working on multi-script digit recognition enables multi-task learning, considering the script classification as a related task for instance. It is evident that multi-task learning improves model performance through inductive transfer using the information contained in related tasks. Therefore, in this study multi-script handwritten digit recognition using multi-task learning will be investigated. As a specific case of demonstrating the solution to the problem, Amharic handwritten character recognition will also be experimented. The handwritten digits of three scripts including Latin, Arabic and Kannada are studied to show that multi-task models with reformulation of the individual tasks have shown promising results. In this study a novel way of using the individual tasks predictions was proposed to help classification performance and regularize the different loss for the purpose of the main task. This finding has outperformed the baseline and the conventional multi-task learning models. More importantly, it avoided the need for weighting the different losses of the tasks, which is one of the challenges in multi-task learning.

show abstract

Amharic Handwritten & Machine Printed Character Recognition Using Deep CNN with Random Search Hyperparameter Optimization Algorithm

Sinshaw,

Ejigu,

Assefa

et al. 2023

Preprint

View full text Add to dashboard Cite

The Amharic language is widely spoken in Ethiopia by over 31.8 million people as their mother tongue, and an additional 25 million as second-language speakers. It is also used to document a significant portion of Ethiopia’s historical and literary records. However, recognizing handwritten and machine-printed characters in Amharic has been a challenging issue. Several OCR technologies have been proposed to address this issue, but it remains unresolved. This study proposes a convolutional neural network (CNN) model for Amharic character recognition. The model was developed using 104,177 Amharic character images and subjected to data preprocessing activities such as binarization and noise removal. The dataset was partitioned into training, validation, and test sets, with each partition containing 80%, 10%, and 10% of the data, respectively. The proposed model's hyperparameters were optimized using three algorithms: random search, Bayesian optimization, and hyperband optimization. Results showed that the random search algorithm produced the best performance, achieving 96.02% accuracy when tested with unseen data. The study concludes that increasing the dataset size and tuning the hyperparameters under different scopes could further improve the model's performance. In general, this study provides a promising approach to Amharic character recognition using deep learning techniques.

show abstract

Handwritten Amharic Character Recognition Using a Convolutional Neural Network

Cited by 4 publications

References 0 publications

Improving Amharic Handwritten Word Recognition Using Auxiliary Task

Improving Amharic Handwritten Word Recognition Using Auxiliary Task

Multi-script Handwritten Digit Recognition Using Multi-task Learning

Amharic Handwritten & Machine Printed Character Recognition Using Deep CNN with Random Search Hyperparameter Optimization Algorithm

Contact Info

Product

Resources

About

Handwritten Amharic Character Recognition Using a Convolutional Neural Network

Cited by 4 publications

References 0 publications

Improving Amharic Handwritten Word Recognition Using Auxiliary Task

Improving Amharic Handwritten Word Recognition Using Auxiliary Task

Multi-script Handwritten Digit Recognition Using Multi-task Learning

Amharic Handwritten &amp; Machine Printed Character Recognition Using Deep CNN with Random Search Hyperparameter Optimization Algorithm

Contact Info

Product

Resources

About

Amharic Handwritten & Machine Printed Character Recognition Using Deep CNN with Random Search Hyperparameter Optimization Algorithm