×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerAiming to enhance the accuracy of sign classification in sign language (SL), this research presents an innovative approach that combines hand-engineered characteristics with deep learning (DL) algorithms. The focus is on American Sign Language (ASL), a critical communication tool for the deaf and hard-of-hearing community. The goal is to bridge the existing communication chasm between SL users and the general public by designing a real-time SL recognition system that allows non- SL users to converse with the hearing-impaired individuals. The application and assessment of various machine learning (ML) models, such as VGG19, DenseNet, ResNet50, MobileNet, and NASNetMobile, yielded promising outcomes with superior evalu- ation metrics. These models exhibit utility in the classification of ASL signs as they can differentiate between diverse hand gestures with high accuracy (ACC). The paper highlights the potential of these models across an array of ASL recognition applica- tions, considering factors like computational resources, model dimension, and real-time functionality. The findings endorse the application of ML techniques in SL interpretation, promoting inclusive communication for those with hearing impairment.
Advancements in internet accessibility and the affordability of digital picture sensors have led to the proliferation of extensive image databases utilized across a multitude of applications. Addressing the semantic gap between low- level attributes and human visual perception has become pivotal in refining Content Based Image Retrieval (CBIR) methodologies, especially within this context. As this field is intensely researched, numerous efficient algorithms for CBIR systems have surfaced, precipitating significant progress in the artificial intelligence field. In this study, we propose employing a hard voting ensemble approach on features derived from three robust deep learning architectures: Inception, Exception, and Mobilenet. This is aimed at bridging the divide between low-level image features and human visual perception. The Euclidean method is adopted to determine the similarity metric between the query image and the features database. The outcome was a noticeable improvement in image retrieval accuracy. We applied our approach to a practical dataset named CBIR 50, which encompasses categories such as mobile phones, cars, cameras, and cats. The effectiveness of our method was thereby validated. Our approach outshone existing CBIR algorithms with superior accuracy (ACC), precision (PREC), recall (REC), and F1-score (F1-S), proving to be a noteworthy addition to the field of CBIR. Our proposed methodology could be potentially extended to various other sectors, including medical imaging and surveillance systems, where image retrieval accuracy is of paramount importance.