Recent methods in vision-based hand gesture recognition

Abstract

The goal of static hand gesture recognition is to classify the given hand gesture data represented by some features into some predefined finite number of gesture classes. The main objective of this effort is to explore the utility of two feature extraction methods, namely, hand contour and complex moments to solve the hand gesture recognition problem by identifying the primary advantages and disadvantages of each method. Artificial neural network is built for the purpose of classification by using the back-propagation learning algorithm. The proposed system presents a recognition algorithm to recognize a set of six specific static hand gestures, namely: Open, Close, Cut, Paste, Maximize, and Minimize. The hand gesture image is passed through three stages, namely, pre-processing, feature extraction, and classification. In the pre-processing stage, some operations are applied to extract the hand gesture from its background and prepare the hand gesture image for the feature extraction stage. In the first method, the hand contour is used as a feature which treats scaling and translation problems (in some cases). The complex moments algorithm is, however, used to describe the hand gesture and treat the rotation problem in addition to the scaling and translation. The back-propagation learning algorithm is employed in the multi-layer neural network classifier. The results show that hand contour method has a performance of (71.30 %) recognition, while complex moments have a better performance of (86.90 %) recognition rate.

HGR-ViT: Hand Gesture Recognition with Vision Transformer

“…In view of this, researchers have begun utilising deep learning approaches such as CNNs [ 1 , 2 , 3 , 4 , 6 , 17 , 27 , 28 , 29 , 30 , 31 , 32 ] and ANNs [ 33 ] over conventional hand-crafted methods. Deep learning approaches have the ability to automatically discover complex and important features through their hidden layers, saving time and reducing bias during feature extraction.…”

SDViT: Stacking of Distilled Vision Transformers for Hand Gesture Recognition

“…In contrast, deep learning approaches are capable of automatically learning high-level representations of the data through multiple layers of abstraction, reducing the need for manual feature engineering and improving performance in complex tasks. Consequently, researchers shifted towards employing deep learning approaches such as CNNs [1][2][3][4][5][6][22][23][24][25][26][27], artificial neural networks (ANNs) [30], and autoencoders [31,32] instead of traditional hand-crafted methods. Tan et al [3] proposed a CNN model with spatial pyramid pooling (CNN-SPP), utilizing SPP instead of max pooling or average pooling to capture more spatial information and facilitate better learning.…”

“…These extracted characteristics are subsequently input into a classification algorithm for the purpose of gesture categorization. Alternatively, the deep learning approach utilizes deep learning networks, such as convolutional neural networks (CNNs) [1][2][3][4][5][6][22][23][24][25][26][27][28][29], artificial neural networks (ANNs) [30], and autoencoders [31,32], to automatically extract features from the hand gestures. Deep learning networks showcase adaptability to various challenges in static hand gesture recognition, learning from extensive datasets and accommodating diverse environmental factors such as lighting conditions, complex backgrounds, and variations in hand size and skin tone.…”

Hand features extractor using hand contour – a case study

“…Based on their methods, hand gesture recognition technology is mainly divided into two categories: data gloves-based method and computer vision-based method. The computer vision-based method can be classified into two main classes [2]: static gestures [3][4][5][6][7] that are done with a hand or both hands with no movement, and dynamic gestures [8,9,2,10,11,12] that are done with a sequence of hand images following a path or a predefined behaviour. Both static and dynamic gestures are extracted from a sequence of hand images (video), but in the first, the gesture has to be the same and to be in the same position, in the second one, gesture has to be a little different in the form or in the position.…”