An improved hand gesture recognition system using keypoints and hand bounding boxes

Dang, Tuan Linh; Tran, Sy Dat; Nguyen, Thi‐Hiep; Kim, Suntae; Monet, Nicolas

doi:10.1016/j.array.2022.100251

Cited by 15 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many papers achieved excellent technical accuracy in research of both static and dynamic hand gesture recognition [25], [26], [27]. Static hand gesture recognition recognizes gestures while those poses are fixed (in the form of images) and hands do not move.…”

Section: B Gesture Recognition With Deep Learningmentioning

confidence: 99%

“…Static hand gesture recognition recognizes gestures while those poses are fixed (in the form of images) and hands do not move. On the contrary dynamic hand gesture recognition can recognize gestures in motion in the form of videos [27]. Static hand gesture recognition is often used in applications where gestures are performed slowly and the image can be recognized as a single frame, for example when interpreting sign language [25], [28].…”

Section: B Gesture Recognition With Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Hybrid Deep Learning Architecture for Dynamic Hand Gesture Recognition

Hax,

Penava,

Krodel

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Hand gestures are a form of natural communication used in human-computer interaction, however, when gestures are video-based, extraction of features for classification is complex. Current machine learning models struggle to achieve high accuracies when using videos recorded in realistic environments. In this work, we propose a hybrid architecture consisting of a recurrent neural network (RNN), including a long short-term memory layer, on top of a convolutional neural network, to recognize dynamic hand gestures recorded in realistic environments. We used a dataset of 6 dynamic hand gestures: scroll-left, scroll-right, scroll-up, scroll-down, zoom-in, and zoom-out. Our implemented inception-v3 model extracted features and provided the wrapped frame-feature map as input for the RNN, which performs the final classification. The proposed model classifies gestures with an average accuracy of 83.66%. By doing so, we intend to narrow the disparity between realistic environments and high accuracy. Finally, we compare the accuracy of our proposed dynamic hand gesture recognition model with that of the benchmark.

show abstract

Section: B Gesture Recognition With Deep Learningmentioning

confidence: 99%

Section: B Gesture Recognition With Deep Learningmentioning

confidence: 99%

A Novel Hybrid Deep Learning Architecture for Dynamic Hand Gesture Recognition

Hax,

Penava,

Krodel

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…These landmarks were used to produce features that are introduced in a Multilayer Perceptron (MLP) that classifies five different hand gestures. Another work [ 33 ] improves an HGR model by fusing features extracted from the image and features extracted from the hand landmarks.…”

Section: Related Workmentioning

confidence: 99%

Domain Adaptation with Contrastive Simultaneous Multi-Loss Training for Hand Gesture Recognition

Baptista

Santos

Silva

et al. 2023

Sensors

View full text Add to dashboard Cite

Hand gesture recognition from images is a critical task with various real-world applications, particularly in the field of human–robot interaction. Industrial environments, where non-verbal communication is preferred, are significant areas of application for gesture recognition. However, these environments are often unstructured and noisy, with complex and dynamic backgrounds, making accurate hand segmentation a challenging task. Currently, most solutions employ heavy preprocessing to segment the hand, followed by the application of deep learning models to classify the gestures. To address this challenge and develop a more robust and generalizable classification model, we propose a new form of domain adaptation using multi-loss training and contrastive learning. Our approach is particularly relevant in industrial collaborative scenarios, where hand segmentation is difficult and context-dependent. In this paper, we present an innovative solution that further challenges the existing approach by testing the model on an entirely unrelated dataset with different users. We use a dataset for training and validation and demonstrate that contrastive learning techniques in simultaneous multi-loss functions provide superior performance in hand gesture recognition compared to conventional approaches in similar conditions.

show abstract

“…Issues such as how to avoid the influence of illumination on skin color models, how to extract valid features of the hand, etc. are all problems that need to be studied 4 .…”

Section: Introductionmentioning

confidence: 99%

Design of non-contact gesture recognition control system based on embedded system

Liu,

Wang,

Hou

et al. 2024

Ninth International Symposium on Sensors, Mechatronics, and Automation System (ISSMAS 2023)

View full text Add to dashboard Cite

Compared with traditional contact-based gesture recognition systems, non-contact gesture recognition systems not only have good recognition performance, but also have advantages such as human-computer interaction, ease of use, and time and effort savings. This design is an intelligent non-contact gesture recognition device that uses the PAJ7620 sensor to collect gesture information. The embedded microcontroller identifies different gestures and displays different patterns through LED marquees, and provides voice prompts through a voice broadcast device. To improve visibility, this design also uses a TFTLCD liquid crystal display to display different gestures, and switches between gesture recognition mode and distance detection mode through four independent keys.

show abstract

An improved hand gesture recognition system using keypoints and hand bounding boxes

Cited by 15 publications

References 13 publications

A Novel Hybrid Deep Learning Architecture for Dynamic Hand Gesture Recognition

A Novel Hybrid Deep Learning Architecture for Dynamic Hand Gesture Recognition

Domain Adaptation with Contrastive Simultaneous Multi-Loss Training for Hand Gesture Recognition

Design of non-contact gesture recognition control system based on embedded system

Contact Info

Product

Resources

About