RETRACTED ARTICLE: Development of hand gesture recognition system using machine learning

Parvathy, Priyanka; Subramaniam, Kamalraj; Venkatesan, G. K. D. Prasanna; Karthikaikumar, P.; Varghese, Justin; Jayasankar, T.

doi:10.1007/s12652-020-02314-2

Cited by 49 publications

(23 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And when the camera is also moving, the optical flow detection will be unable to segment the situation. Parvathy et al used color histogram information to model the background information and then used the background difference method to detect the hand region, which is computationally simple and can only be applied to scenes with stable illumination and fixed cameras [16]. In general, a gesture recognition model is a machine learningbased classifier, which can classify gestures into corresponding classes by using sample data for learning [17].…”

Section: Related Workmentioning

confidence: 99%

Research on the Construction of Human-Computer Interaction System Based on a Machine Learning Algorithm

Wang

2022

Journal of Sensors

View full text Add to dashboard Cite

In this paper, we use machine learning algorithms to conduct in-depth research and analysis on the construction of human-computer interaction systems and propose a simple and effective method for extracting salient features based on contextual information. The method can retain the dynamic and static information of gestures intact, which results in a richer and more robust feature representation. Secondly, this paper proposes a dynamic planning algorithm based on feature matching, which uses the consistency and accuracy of feature matching to measure the similarity of two frames and then uses a dynamic planning algorithm to find the optimal matching distance between two gesture sequences. The algorithm ensures the continuity and accuracy of the gesture description and makes full use of the spatiotemporal location information of the features. The features and limitations of common motion target detection methods in motion gesture detection and common machine learning tracking methods in gesture tracking are first analyzed, and then, the kernel correlation filter method is improved by designing a confidence model and introducing a scale filter, and finally, comparison experiments are conducted on a self-built gesture dataset to verify the effectiveness of the improved method. During the training and validation of the model by the corpus, the complementary feature extraction methods are ablated and learned, and the corresponding results obtained are compared with the three baseline methods. But due to this feature, GMMs are not suitable when users want to model the time structure. It has been widely used in classification tasks. By using the kernel function, the support vector machine can transform the original input set into a high-dimensional feature space. After experiments, the speech emotion recognition method proposed in this paper outperforms the baseline methods, proving the effectiveness of complementary feature extraction and the superiority of the deep learning model. The speech is used as the input of the system, and the emotion recognition is performed on the input speech, and the corresponding emotion obtained is successfully applied to the human-computer dialogue system in combination with the online speech recognition method, which proves that the speech emotion recognition applied to the human-computer dialogue system has application research value.

show abstract

Section: Related Workmentioning

confidence: 99%

Research on the Construction of Human-Computer Interaction System Based on a Machine Learning Algorithm

Wang

2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…It is hoped that the intelligent level of the behavior recognition system can be improved through software design to fully optimize the read-write function of the intelligent recognition system, solve the problem of poor data processing ability of the system, and avoid the defect of reduced accuracy caused by the operation error of human factors [23]. Firstly, the edge of the key image should be detected.…”

Section: Intelligent Demand Analysis Of Behavior Recognition Systemmentioning

confidence: 99%

Design of Edge Cloud Computing Recognition System for Intelligent Needs from the Perspective of Sports Psychology

Liu

2022

Preprint

View full text Add to dashboard Cite

This paper intends to meet society’s demand for intelligent recognition system design and improve the performance of the behavioral action recognition system. Based on the previous research, the behavior recognition system is optimized. The edge Cloud Computing (CLO) technology is introduced. Also, the idea of sports psychology is integrated. The overall scheme of the behavior recognition system is designed. The accuracy, precision, and recall of the recognition system in different behaviors are analyzed by training the data set. In addition, the cloud-based behavior recognition design model is compared with other algorithms to analyze the algorithm advantages. Finally, the training and validation tests are performed on the training set of expression images using the behavior recognition system mode. It is found that the behavior recognition system model can show high accuracy in different environments, all above 80%. The results show that the edge CLO recognition system that meets intelligence needs has good accuracy, precision, and recall in both action recognition and image expression recognition. The recognition effect is the best. This paper aims to provide some ideas for the research on intelligent behavior recognition and put forward some references for the field expansion of edge CLO technology applications. Besides, the intelligence level of the behavior recognition system is improved through software design.

show abstract

“…Individuality is the source of innovation and creativity. Relevant scholars pointed out that the cultural quality education of college students should be combined with the improvement of teachers' cultural literacy, ideological and political, and focus on the comprehensive training of humanities and science of talents [19,20].…”

Section: Related Workmentioning

confidence: 99%

Analysis of Cultural Education and Behavior in Colleges and Universities Based on Image Recognition Technology

Jia

Jing

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

When the rationality and importance of cultural education in colleges and universities have been confirmed, the key question is how to better realize cultural education. This requires an in-depth understanding and grasp of the cultural education work of colleges and universities, analyzing the internal logic contained in this education system and then discussing its practical rationale. This paper proposes a multiobjective Support Vector Machine (SVM) image recognition method for college cultural and educational behaviors based on three decision-making theories. Aimed at the problem of classification errors caused by image segmentation in image recognition of cultural and educational behaviors in colleges and universities, it is found that the reason that causes the same target to be divided into different subblocks is that the ordinary SVM classifier has only two choices of “yes” and “not” in classification. It is impossible to set the conditions for the classification of cultural and educational behavior images to satisfy all the existing conditions. In order to solve the above problems, this paper combines the three decision-making ideas with the image recognition of university cultural education behaviors and designs a multiobjective SVM image recognition method of university cultural education behaviors based on the three decision-making theories. We establish a higher education service quality structure model and use LISREL to explore the causal relationship among students’ perceived service quality, university image, student’s perceived service value, student trust, student satisfaction, and student behavior intentions in the field of higher education. The empirical results show that student satisfaction has a significant direct and positive effect on student behavior. Service quality has a significant direct and positive impact on perceived value and student trust. The perceived risk of higher education services determines the image of colleges and universities, and student trust plays an important role. The image of colleges and universities acts on student satisfaction through perceived value and student trust. The image of colleges and universities has a direct impact on students’ behavioral inclination, and it acts on students’ behavioral inclination through student trust and student satisfaction. Among the influences on behavior tendency, the direct positive effect of student trust is the largest, followed by the image of colleges and universities and the quality of service.

show abstract

RETRACTED ARTICLE: Development of hand gesture recognition system using machine learning

Cited by 49 publications

References 21 publications

Research on the Construction of Human-Computer Interaction System Based on a Machine Learning Algorithm

Research on the Construction of Human-Computer Interaction System Based on a Machine Learning Algorithm

Design of Edge Cloud Computing Recognition System for Intelligent Needs from the Perspective of Sports Psychology

Analysis of Cultural Education and Behavior in Colleges and Universities Based on Image Recognition Technology

Contact Info

Product

Resources

About