A New Benchmark on American Sign Language Recognition using Convolutional Neural Network

HandArch: A deep learning architecture for LIBRAS hand configuration recognition

“…We separate the classic methods from the DL methods in the evaluation for simplicity. In our search for datasets, we verified that the datasets created by [5], [11], [12] were not available. Therefore, we compare our results with previous works in different sign languages such as Irish Sign Language [28], JSL [13], and others [4], [8], [29]- [31].…”

“…Both Rahman et al [5] and Sruthi et al [11] propose a novel Deep Neural Network (DNN) for SLR. Rahman et al [5] apply the DNN in four different American sign language (ASL) datasets containing 29 classes, and they obtain 100% accuracy.…”

“…Both Rahman et al [5] and Sruthi et al [11] propose a novel Deep Neural Network (DNN) for SLR. Rahman et al [5] apply the DNN in four different American sign language (ASL) datasets containing 29 classes, and they obtain 100% accuracy. Sruthi et al [11] apply the DNN in a new Indian sign language (ISL) dataset with 4,125 samples divided in 24 classes and reports an accuracy of 98,64%.…”

“…Different studies approach sign language recognition as a hand configuration classification problem by identifying the pose performed in an image or a sequence of images [3]. However, these studies do not address the applicability of this knowledge for accessibility applications because they work with hand images isolated with human assistance in controlled environments [4], [5]. For instance, there is no constant illumination or static background in a real-world scenario, making it difficult to achieve automatic hand isolation.…”

Information System for Learning Control in Teaching Russian Sign Language: Process and Data Modeling

“…Within the framework of this research, the results of such studies are of interest from the point of view of information visualization, particularly the accuracy of static and dynamic gestures, the position of the human hand, the features of a person's lip contour, etc. Instruction, July 2022 • Vol.15, No.3 If we consider the use of gestures as a way of interacting with a computer system, algorithms for converting and interpreting gesture information, as well as the corresponding software implementation, then the software tools created are associated with the use of a large number of sensors, sensors, joysticks, trackballs or touch screens, as well as complex control systems (Karpov, 2013;Myasoedova et al, 2020;Rahman et al, 2019;Ryumin et al, 2020). As Karpov notes in his works, "the currently widely used graphical and textual interfaces are focused on experienced users, and the available research practically does not touch upon the issues of human-machine communication for persons with disabilities" (Karpov, 2013).…”