Comparative framework for vision‐based gesturing modes and implementation of robust colour‐marker detector for practical environments

Misra, Songhita; Laskar, Rabul Hussain

doi:10.1049/iet-ipr.2018.5978

Cited by 12 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The earlier researchers (Bhuyan et al, 2008; Misra & Hussain Laskar, 2019; Misra & Laskar, 2017; Misra & Laskar, 2019; Misra & Laskar, 2019b; Saboo & Singha, 2021; Singha et al, 2018) worked on the dynamic bare hand gesture‐based virtual keyboard interface system. They performed the experiments in the controlled environment using handcrafted features such as histogram, histogram oriented gradient (HOG), local binary pattern (LBP), and so forth, with the shallow architecture models, for example, support vector machine (SVM), k‐nearest neighbours (kNN) and artificial neural network (ANN).…”

Section: Related Workmentioning

confidence: 99%

“…This model is not able to work in the complex background due to dependency only on the moving information. Researchers (Misra & Hussain Laskar, 2019; Misra & Laskar, 2017; Misra & Laskar, 2019; Misra & Laskar, 2019b) developed a Gaussian mixture model (GMM)‐based hand detector with the ANN model to detect bare hand. HOG, LBP, SHIFT features were used to train the ANN model.…”

Section: Related Workmentioning

confidence: 99%

“…However, detecting and tracking the bare hand are challenging, and the complexity increases further in practical environments, for example, in a natural crowded office/home environment (Saboo & Singha, 2021; Singha et al, 2018). This is one of the reasons why most researchers (Gao et al, 2021; Misra & Hussain Laskar, 2019; Misra & Laskar, 2017; Misra & Laskar, 2019; Misra & Laskar, 2019b; Mukherjee et al, 2019; Nguyen et al, 2018; Saboo & Singha, 2021; Singha et al, 2018) implemented bare hand gesture detection work with the controlled environment using shallow architecture models. Some of the complexities in detecting gesture objects are gesticulated speed, variation due to illumination, pose, scale, size, backgrounds, occlusion and presence of imposter‐like objects.…”

Section: Introductionmentioning

confidence: 99%

“…Researchers (Bhuyan et al, 2008; Misra et al, 2018; Misra & Hussain Laskar, 2019; Misra & Laskar, 2017; Misra & Laskar, 2019; Misra & Laskar, 2019b; Saboo et al, 2021; Saboo & Singha, 2021; Singha et al, 2018) have experimented with shallow machine learning models with hand‐crafted features to recognize the limited number of hand gestures. At most, researchers (Farahi & Yazdi, 2020) have experimented on recognizing 58 gesticulated characters to avoid the variation in pattern and style.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Design and development of a vision‐based system for detection, tracking and recognition of isolated dynamic bare hand gesticulated characters

et al. 2022

View full text Add to dashboard Cite

Detection and tracking are the vital stages to form the gesture trajectory in gesture recognition. It becomes more challenging when the variations in illumination, pose, position, occlusion, scale, speed, blurring effect and complex environment are introduced. Additionally, the background feature domination effect affects the existing deep learning models. A semantic segmentation model is implemented in this work to detect the bare hand to overcome these challenges. A pre‐trained network VGG‐16 is utilized by training with the proposed NITS S‐Net database. Evaluation of the SegNet model is done on EgoHands, Oxford and OUHands databases. To track the bare hand, a SegNet‐based detection and tracking approach is proposed using Kalman filter and point‐tracker. This model achieves 97.01% accuracy (a relative improvement of ~8% from the baseline models) at 0.068 s per frame computational time on NITS hand gesture database VIIIB. The gesticulated characters, that is, alphabets, numbers, operators, special characters, are gesticulated without any constraints on the pattern/strokes. To recognize these 95 multi‐stroke gestures, a deep convolutional neural network (DCNN) is presented using AlexNet. The DCNN model achieves 97.60% (a relative improvement of ~14% from the baseline models) accuracy on the NITS hand gesture database VIIIB merged. Evaluation of the handwritten EMNIST merged (balanced) database resulted in average recognition accuracy of 91.60%.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Design and development of a vision‐based system for detection, tracking and recognition of isolated dynamic bare hand gesticulated characters

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Hand gesture movements can be recorded by non-vision devices such as electrodes directly placed in hands, gloves, inertial sensor or through vision devices such as cameras and Kinect sensor. Though the former provides a more accurate estimation of the intended gesture, the vision-based approach has shown consistent growth in the field of hand gesture (in air) particularly character recognition [1,2]. The act of gesturing in air includes with it some redundant strokes (pen-up strokes) that need to be removed to get the actual characters.…”

Section: Introductionmentioning

confidence: 99%

Segregation of meaningful strokes, a pre‐requisite for self co‐articulation removal in isolated dynamic gestures

Monsley

Yadav

Misra

et al. 2020

IET Image Processing

Self Cite

View full text Add to dashboard Cite

Gesture formation, a pre-processing step, has its importance when variations in patterns, scale, and speed come into play. Self co-articulations are intentional movements performed by an individual to complete a gesture, whose presence in the trajectory alters its original meaning. For recognition, most researchers have directly used the trajectory formed along with these self co-articulated strokes, with a few removing it using visible trait-like velocity. Usage of velocity has shortcomings as gesturing in air differs from gesturing over a solid surface; hence, we propose a gesture formation model, which incorporates global and local measures to remove these self co-articulations. The global measure uses Euclidean distance, instantaneous velocity, and polarity calculated from the complete gesture, while the local measure segments the gesture into stroke-level segments by using the minimummaximum-polarity algorithm and applies the selective bypass rules. The proposed model, when experimented on gestures patterns with premeditated speed variation, has a mean error rate of 0.0069 and 7.40% self co-articulations;individuals' natural gesticulation has a mean error rate of 0.0371 and 12.07% self co-articulations. Experimentation on each gesture of NITS hand gesture databases showed a relative improvement of 40% (accuracy 97%) over the existing baseline models.

show abstract

Scale-adaptive gesture computing: detection, tracking and recognition in controlled complex environments

Kirupakaran,

Laskar

2024

Machine Vision and Applications

View full text Add to dashboard Cite

Comparative framework for vision‐based gesturing modes and implementation of robust colour‐marker detector for practical environments

Cited by 12 publications

References 20 publications

Design and development of a vision‐based system for detection, tracking and recognition of isolated dynamic bare hand gesticulated characters

Design and development of a vision‐based system for detection, tracking and recognition of isolated dynamic bare hand gesticulated characters

Segregation of meaningful strokes, a pre‐requisite for self co‐articulation removal in isolated dynamic gestures

Scale-adaptive gesture computing: detection, tracking and recognition in controlled complex environments

Contact Info

Product

Resources

About