Efficient Assamese Word Recognition for Societal Empowerment: A Comparative Feature-Based Analysis

Borah, Naiwrita; Baruah, Udayan; Thylore Ramakrishna, Mahesh; Kumar, V. Vinoth; Dorai, D. Ramya; Rajkumar Annad, Jonnakuti

doi:10.1109/access.2023.3301564

Cited by 16 publications

(1 citation statement)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2 displays the specific information regarding the classes and the corresponding number of instances in our dataset. Borah et al offer a thorough and complete explanation of a detailed segmentation process [15]. The experimental phase utilized a dataset consisting of 10,274 photographs, which were classified into five unique categories, as detailed in Table II and Fig.…”

Section: A Dataset Creationmentioning

confidence: 99%

Enhancing Assamese Word Recognition for CBIR: A Comparative Study of Ensemble Methods and Feature Extraction Techniques

Borah,

Baruah,

Dey

et al. 2023

IJACSA

View full text Add to dashboard Cite

This study conducts a thorough assessment of ensemble machine learning methods, specifically focusing on the identification of Assamese words. This task is crucial for improving Content-Based Image Retrieval systems and safeguarding the digital heritage of Assamese culture. We analyze the efficacy of different algorithms, such as CatBoost, XGBoost, Gradient Boosting, Random Forest, Bagging, AdaBoost, Stacking, and Histogram-Based Gradient Boosting, by thoroughly examining their performance in terms of accuracy, precision, recall, Kappa, F1-score, Matthews Correlation Coefficient, and AUC. The Cat-Boost algorithm stands out as the top performer, achieving an accuracy rate of 97.7%, precision rate of 95%, and recall rate of 96%. XGBoost is also acknowledged for its substantial effectiveness. This comparative analysis emphasizes CatBoost's superiority in terms of precision and recall. Additionally, it underscores the strong ability of ensemble classifiers to enhance assistive technologies, promote social inclusivity, and seamlessly integrate the Assamese language into technological applications.

show abstract

Section: A Dataset Creationmentioning

confidence: 99%