Sign Language Recognition Based on Intelligent Glove Using Machine Learning Techniques

Rosero-Montalvo, Paúl D.; Godoy-Trujillo, Pamela; Flores-Bosmediano, Edison; Carrascal-Garcia, Jorge; Otero-Potosi, Santiago; Benitez-Pereira, Henry; Peluffo-Ordóñez, Diego H.

doi:10.1109/etcm.2018.8580268

Cited by 47 publications

(23 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subsequently, we evaluate the performance of three classifiers in accurately classifying the sensor's data. These classifiers are Linear SVM, Logistic Regression and Gaussian naïve Bayes algorithms [48], [49]. Particularly, each classifier is evaluated on its performance in classifying the data of a specific angle from all other angles.…”

Section: B Glove Evaluationmentioning

confidence: 99%

A Weft Knit Data Glove

Ayodele

Zaidi

Scott

et al. 2021

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Rehabilitation of stoke survivors can be expedited by employing an exoskeleton. The exercises are designed such that both hands move in synergy. In this regard often motion capture data from the healthy hand is used to derive control behaviour for the exoskeleton. Therefore, data gloves can provide a low-cost solution for the motion capture of the joints in the hand. However, current data gloves are bulky, inaccurate or inconsistent. These disadvantages are inherited because the conventional design of a glove involves an external attachment that degrades overtime and causes inaccuracies. This paper presents a weft knit data glove whose sensors and support structure are manufactured in the same fabrication process thus removing the need for an external attachment. The glove is made by knitting multifilament conductive yarn and an elastomeric yarn using WholeGarment technology. Furthermore, we present a detailed electromechanical model of the sensors alongside its experimental validation. Additionally, the reliability of the glove is verified experimentally. Lastly, machine learning algorithms are implemented for classifying the posture of hand on the basis of sensor data histograms.

show abstract

Section: B Glove Evaluationmentioning

confidence: 99%

A Weft Knit Data Glove

Ayodele

Zaidi

Scott

et al. 2021

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

“…A text-to-speech function has been added to an Android app, which transforms obtained text into loud audio files. A SVM tool used to classify the signs in several different categories [8][9][10]…”

Section: Related Workmentioning

confidence: 99%

“…Used Methodology Achieved Accuracy Su Min Lee [5] Sensor fixed gloves 92.5% Gwang Soo Hongb [6] Sensor Gloves 93.9% Pamela Godoy-Trujill [10] Sensor gloves 93.3%…”

Section: Authormentioning

confidence: 99%

Deep Learning Based Indian Sign Language Words Identification System

Jeyasheeli¹,

Indumathi

2021

Recent Trends in Intensive Computing

View full text Add to dashboard Cite

In Indian Population there is about 1 percent of the people are deaf and dumb. Deaf and dumb people use gestures to interact with each other. Ordinary humans fail to grasp the significance of gestures, which makes interaction between deaf and mute people hard. In attempt for ordinary citizens to understand the signs, an automated sign language identification system is proposed. A smart wearable hand device is designed by attaching different sensors to the gloves to perform the gestures. Each gesture has unique sensor values and those values are collected as an excel data. The characteristics of movements are extracted and categorized with the aid of a convolutional neural network (CNN). The data from the test set is identified by the CNN according to the classification. The objective of this system is to bridge the interaction gap between people who are deaf or hard of hearing and the rest of society.

show abstract

“…Meanwhile, number gesture detection textiles as human-computer interfaces are needed in smart spatial applications as a natural and simple interactive approach. Most studies in this area have focused on conventional contact-based gesture recognition interactive textiles, especially contact via wearing mechanical gloves with high detection accuracy [24][25][26][27][28][29][30][31] . However, there is a lack of research on contact-free textile design with number gesture recognition for HCI.…”

Section: Introductionmentioning

confidence: 99%

Intelligent textiles: designing a gesture-controlled illuminated textile based on computer vision

Tan

Shao

Lam

et al. 2021

Textile Research Journal

View full text Add to dashboard Cite

Artificial intelligence (AI) offers the potential for the development of e-textiles that give wearers a smart and intuitive experience. An emerging challenge in intelligent materials design is hand gesture recognition textiles. Most current research focuses on number gesture recognition via smart gloves, so there is a gap in research that studies contact-less number gesture recognition textiles via computer vision. Meanwhile, there is lack of exploration on the integration of illuminating function and number gesture recognition textiles to improve interactivity by real-time visualizing detection results. In this research, a novel interactive illuminating textile with a touch-less number gesture recognition function has been designed and fabricated by using an open-source AI model. It is used in sync with a polymeric optical fiber textile with illuminative features. The textile is color-changing, controlled by the system's mid-air interactive number gesture recognition capability and has a woven stripe pattern and a double-layer weave structure with open pockets to facilitate integration of the system's components. Also described here is a novel design process that permits textile design and intelligent technology to integrate seamlessly and in synchronization, so that design in effect mediates continuously between the physical textile and the intangible technology. Moreover, this design method serves as a reference for the integration of open-source intelligent hardware and software into e-textiles for enhancement of the intuitive function and value via economy of labor.

show abstract

Sign Language Recognition Based on Intelligent Glove Using Machine Learning Techniques

Cited by 47 publications

References 12 publications

A Weft Knit Data Glove

A Weft Knit Data Glove

Deep Learning Based Indian Sign Language Words Identification System

Intelligent textiles: designing a gesture-controlled illuminated textile based on computer vision

Contact Info

Product

Resources

About