Handwritten computer science words vocabulary recognition using concatenated convolutional neural networks

Optical Character Recognition (OCR) is at the forefront of numerous applications such as digitalization of legal and legacy documents, automatic form processing, writer identification in forensic intelligence. Most of these applications seldom have sufficient training samples in order to achieve an accuracy worthy of real-time deployments. Inspired by the demonstrated performance of Siamese Neural Networks (SNN) in various fields such as Computer vision, Natural Language Processing, Signal processing etc., in this paper, we explore the application of SNN for Tamil Handwritten character recognition. The Siamese-CNN learning is implemented using cross-entropy loss and subsequently used to validate the few-shot learning. It achieved an optimal accuracy of 83.39% for n-way-40-shot learning. Rigorous experiments were conducted all through and the results are indicative of a promising new direction for the development of efficient Indic OCR models using Siamese networks.

Few-Shot Learning for Tamil Handwritten Character Recognition Using Deep Siamese Convolutional Neural Network

Geometric algebra graph neural network for cross-domain few-shot classification

This paper introduces a new publicly available image-based Swedish historical handwritten character and word dataset named Character Arkiv Digital Sweden (CArDIS) (https://cardisdataset.github. io/CARDIS/). The samples in CArDIS are collected from 64,084 Swedish historical documents written by several anonymous priests between 1800 and 1900. The dataset contains 116,000 Swedish alphabet images in RGB color space with 29 classes, whereas the word dataset contains 30,000 image samples of ten popular Swedish names as well as 1,000 region names in Sweden. To examine the performance of different machine learning classifiers on CArDIS dataset, three different experiments are conducted. In the first experiment, classifiers such as Support Vector Machine (SVM), Artificial Neural Networks (ANN), k-Nearest Neighbor (k-NN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Random Forest (RF) are trained on existing character datasets which are Extended Modified National Institute of Standards and Technology (EMNIST), IAM and CVL and tested on CArDIS dataset. In the second and third experiments, the same classifiers as well as two pre-trained VGG-16 and VGG-19 classifiers are trained and tested on CArDIS character and word datasets. The experiments show that the machine learning methods trained on existing handwritten character datasets struggle to recognize characters efficiently on the CArDIS dataset, proving that characters in the CArDIS contain unique features and characteristics. Moreover, in the last two experiments, the deep learning-based classifiers provide the best recognition rates. 

CArDIS: A Swedish Historical Handwritten Character and Word Dataset

Facial expression recognition is an intriguing research area that has been explored and utilized in a wide range of applications such as health, security, and human-computer interactions. The ability to recognize facial expressions accurately is crucial for human-computer interactions. However, most of the facial expression analysis techniques have so far paid little or no concern to users’ data privacy. To overcome this concern, in this paper, we incorporated Federated Learning (FL) as a privacy-preserving machine learning approach in the field of facial expression recognition to develop a shared model without exposing personal information. The individual models are trained on the different client devices where the data is stored. In this work, a lightweight Convolutional Neural Network (CNN) model called the MobileNet architecture is utilised to detect expressions from facial images. To evaluate the model, two publicly available datasets are used and several experiments are conducted. The result shows that the proposed privacy-preserving Federated-MobileNet approach could recognize facial expressions with considerable accuracy compared to the general approaches. 

A Privacy-Preserving Federated-MobileNet for Facial Expression Detection from Images

The robustness of a typical Handwritten character recognition system relies on the availability of comprehensive supervised data samples. There has been considerable work reported in the literature about creating the database for several Indic scripts, but the Tamil script has only one standardized database up to date. This paper presents the work done to create an exhaustive and extensive unconstrained Tamil Handwritten Character Database (uTHCD). The samples were generated from around 850 native Tamil volunteers including school-going kids, homemakers, university students, and faculty. The database consists of about 91000 samples with nearly 600 samples in each of 156 classes. This isolated character database is made publicly available as raw images and Hierarchical Data File (HDF) compressed file. The paper also presents several possible use cases of the proposed uTHCD database using Convolutional Neural Networks (CNN) to classify handwritten Tamil characters. Several experiments demonstrate that training on the proposed database helps traditional and contemporary classifiers perform on par or better than the existing dataset when tested with unseen data. With this database, we expect to set a new benchmark in Tamil handwritten character recognition and serve as a launchpad for developing robust language technologies for the Tamil script.

/pdf/uthcd-a-new-benchmarking-for-tamil-handwritten-ocr-v1y9om97fb.pdf

uTHCD: A New Benchmarking for Tamil Handwritten OCR

Alzheimer’s disease (AD) is a neurodegenerative disease that causes irreversible damage to several brain regions including the hippocampus causing impairment in cognition, function and behaviour. Earlier diagnosis of the disease will reduce the suffering of the patients and their family members. Towards that aim, this paper presents a Siamese Convolutional Neural Network (CNN) based model using the Triplet-loss function for the 4-way classification of AD. We evaluated our models using both pre-trained and non-pre-trained CNNs. The models’ efficacy was tested on the OASIS dataset and obtained satisfactory results under a data-scarce real-time environment. 

Triplet-Loss Based Siamese Convolutional Neural Network for 4-Way Classification of Alzheimer's Disease

Abstract Alzheimer’s disease (AD) is a neurodegenerative disease that causes irreversible damage to several brain regions, including the hippocampus causing impairment in cognition, function, and behaviour. Early diagnosis of the disease will reduce the suffering of the patients and their family members. Towards this aim, in this paper, we propose a Siamese Convolutional Neural Network (SCNN) architecture that employs the triplet-loss function for the representation of input MRI images as k -dimensional embeddings. We used both pre-trained and non-pretrained CNNs to transform images into the embedding space. These embeddings are subsequently used for the 4-way classification of Alzheimer’s disease. The model efficacy was tested using the ADNI and OASIS datasets which produced an accuracy of 91.83% and 93.85%, respectively. Furthermore, obtained results are compared with similar methods proposed in the literature. 

/pdf/four-way-classification-of-alzheimers-disease-using-deep-5rk2zaig.pdf

Four-way classification of Alzheimer’s disease using deep Siamese convolutional neural network with triplet-loss function

Machine Learning (ML) techniques remain a massively influential tool in the Computer-Aided Diagnosis (CAD) of several health applications. Mainly due to its ability to rapid learning of end-to-end models accurately using compound data. Recent years have seen an extensive application of Deep Learning (DL) models in solving the 4-way classification of Alzheimer’s Disease (AD) and achieved good results too. However, traditional machine learning classifiers such as KNN, XGBoost, SVM, etc perform either the same or better than the DL models and usually require less data for training. This property is very useful when it comes to medical applications which is characterized by unavailability of large labelled datasets. In this paper, we demonstrate the application of state-of-the-art ML classifiers in the 4-way classification of AD using the OASIS dataset. Furthermore, an ensemble classifier model is proposed based on ML models. The proposed ensemble classifier achieved an accuracy of 94.92% which is approximately 5% accuracy increase compared to individual classifier approach. The source code used in this work are publicly available at: https://github.com/snoushath/AII2022.git 

Noushath Shaffi

Papers

uTHCD: A New Benchmarking for Tamil Handwritten OCR

Triplet-Loss Based Siamese Convolutional Neural Network for 4-Way Classification of Alzheimer's Disease

Few-Shot Learning for Tamil Handwritten Character Recognition Using Deep Siamese Convolutional Neural Network

Four-way classification of Alzheimer’s disease using deep Siamese convolutional neural network with triplet-loss function

Ensemble Classifiers for a 4-Way Classification of Alzheimer's Disease