An Intelligent Heuristic Manta-Ray Foraging Optimization and Adaptive Extreme Learning Machine for Hand Gesture Image Recognition

Abstract

The development of hand gesture recognition systems has gained more attention in recent days, due to its support of modern human-computer interfaces. Moreover, sign language recognition is mainly developed for enabling communication between deaf and dumb people. In conventional works, various image processing techniques like segmentation, optimization, and classification are deployed for hand gesture recognition. Still, it limits the major problems of inefficient handling of large dimensional datasets and requires more time consumption, increased false positives, error rate, and misclassification outputs. Hence, this research work intends to develop an efficient hand gesture image recognition system by using advanced image processing techniques. During image segmentation, skin color detection and morphological operations are performed for accurately segmenting the hand gesture portion. Then, the Heuristic Manta-ray Foraging Optimization (HMFO) technique is employed for optimally selecting the features by computing the best fitness value. Moreover, the reduced dimensionality of features helps to increase the accuracy of classification with a reduced error rate. Finally, an Adaptive Extreme Learning Machine (AELM) based classification technique is employed for predicting the recognition output. During results validation, various evaluation measures have been used to compare the proposed model's performance with other classification approaches.

Real-time Classification of Brain States in Functional MRI Using Dynamic Connectivity Patterns and Machine Learning

“…The research in [19] introduces an automated diabetes detection system using Inherent Coefficient Normalization (ICN) for dataset preprocessing, Intelligent Harris Hawks Optimization (IHHO) for feature selection, and Pivotal Decision Tree (PDT) for efficient classification, addressing limitations seen in traditional machine learning systems. The research in [20] introduces an advanced hand gesture recognition system, utilizing skin color detection, Heuristic Manta-ray Foraging Optimization for feature selection, and an Adaptive Extreme Learning Machine for classification to enhance accuracy and reduce error rates compared to traditional methods.…”

Dynamic Adaptive Resource Allocation for Edge Computing in Big Data Analytics Using GBDT, DQN, and GA Algorithms

“…Advanced machine learning-driven approaches dynamically adapt resource allocation based on workload characteristics, node capabilities, and optimization objectives [18]. The authors in [19] present an efficient hand gesture image recognition system utilizing advanced image processing techniques, including skin color detection, morphological operations, Heuristic Manta-ray Foraging Optimization (HMFO) for optimal feature selection, and Adaptive Extreme Learning Machine (AELM) for accurate classification, addressing issues of large dimensional datasets, time consumption, false positives, and misclassifications. The research in [20] aims to enhance diabetes prediction by implementing an Inherent Coefficient Normalization technique for data preprocessing, utilizing Intelligent Harris Hawks Optimization for optimal feature selection, and deploying a Pivotal Decision Tree based classification system with reduced computational complexity and time consumption, addressing limitations of conventional machine learning methods [20].…”

A Deep Learning-Based Approach for Hand Sign Recognition Using CNN Architecture

“…In convolution, a low matrix called a filter is applied to every pixel of a picture to produce a new pixel value. The kernel is typically a small square matrix, and the size of the kernel determines the size of the output image [8]. The process involves sliding the kernel over each pixel of the input image and performing a mathematical operation between the kernel and the input image.…”