Aakash Anuj

Bio: Aakash Anuj is an academic researcher from Indian Institute of Technology Kharagpur. The author has contributed to research in topics: The Internet & Mobile computing. The author has an hindex of 2, co-authored 2 publications receiving 10 citations.

VoiceMail architecture in desktop and mobile devices for the Blind people

Abstract: The advancement in computer based accessible systems has opened up many avenues for the visually impaired across a wide majority of the globe. Audio feedback based virtual environment like, the screen readers have helped Blind people to access internet applications immensely. However, a large section of visually impaired people in different countries in particular, the Indian sub-continent could not benefit much from such systems. This was primarily due to the difference in the technology required for Indian languages compared to those corresponding to other popular languages of the world. In this paper, we describe the VoiceMail system architecture that can be used by a Blind person to access e-Mails easily and efficiently. The contribution made by this research has enabled the Blind people to send and receive voice based e-Mail messages in their native language with the help of a computer or a mobile device. Our proposed system GUI has been evaluated against the GUI of a traditional mail server. We found that our proposed architecture performs much better than that of the existing GUIs.

Robust control of applications by hand-gestures

Abstract: We use the RGB-D technology of Kinect to control an application with hand-gestures. We use PowerPoint for test. The system can start/end PPT, navigate between slides, capture or release the control of the cursor, and control it through natural gestures. Such a system is useful and hygienic in the kitchen, lavatories, hospital ICUs for touch-less surgery, and the like. The challenge is to extract meaningful gestures from continuous hand motions. We propose a system that recognizes isolated gestures from continuous hand motions for multiple gestures in real-time. Experimental results show that the system has 96.48% precision (at 96.00% recall) and performs better than the Microsoft Gesture Recognition library for swipe gestures.

An insight into smartphone-based assistive solutions for visually impaired and blind people: issues, challenges and opportunities

Abstract: Blind people are confronting a number of challenges in performing activities of daily life such as reading labels on a product, identification of currency notes, exploring unknown spaces, identifying the appearance of an object of interest, interacting with digital artifacts, operating a smartphone’s user interface and selecting non-visual items on a screen. The emergence of smartphone-based assistive technologies promotes independence, ease of use and usability resulting in improved quality of life yet poses several challenging opportunities. We have reviewed research avenues in smartphone-based assistive technologies for blind people, highlighted the need for technological advancements, accessibility-inclusive interface paradigm, and collaboration between medical specialists, computer professionals, usability experts and domain users to realize the potential of ICT-based interventions for blind people. This paper analyzes a comprehensive review of the issues and challenges for visually impaired and blind people with the aim to highlight the benefits and limitations of the existing techniques and technologies. Future research ventures are also highlighted as a contribution to the field.

TetraMail: a usable email client for blind people

Abstract: Electronic Mail has become an essential tool of communication and collaboration for sighted, visually impaired, and blind people However, due to inconsistent interface design, lack of logical order of navigational items, the diverse set of screen sizes and orientations, complicated text-entry layouts, and inadequate mapping of haptic feedback, the existing email-related activities on smartphone contribute to several issues In addition, blind people also confront problems in precisely accessing the non-visual items on touchscreen interfaces to perform common email-related activities like sending, receiving, organizing, deleting, filtering, searching, and managing spam emails Due to these problems, blind people are facing difficulties not only in operating a smartphone but also in performing several email-related activities Furthermore, spam and junk emails cause frustration and contribute to cognitive overload We proposed TetraMail, a usable blind-friendly email client to overcome the challenges pertaining to the accessibility and usability of email-related activities on a smartphone The proposed email client is evaluated through an empirical study of 38 blind participants by performing 14 email activities The results of this prototype implementation show an improved user experience, accuracy in task completion, and better control over touchscreen interfaces in performing basic activities of managing emails The results demonstrate that TetraMail is an accessibility-inclusive email client enabling blind people to have a better user interaction experience and minimal cognitive overload in managing emails

Arm Gesture Recognition using a Convolutional Neural Network

Abstract: In this paper we present an approach towards arm gesture recognition that uses a Convolutional Neural Network (CNN), which is trained on Discrete Fourier Transform (DFT) images that result from raw sensor readings. More specifically, we use the Kinect RGB and depth camera and we capture the 3D positions of a set of skeletal joints. From each joint we create a signal for each 3D coordinate and we concatenate those signals to create an image, the DFT of which is used to describe the gesture. We evaluate our approach using a dataset of hand gestures involving either one or both hands simultaneously and compare the proposed approach to another that uses hand-crafted features.

Real-Time Arm Gesture Recognition Using 3D Skeleton Joint Data

Abstract: In this paper we present an approach towards real-time hand gesture recognition using the Kinect sensor, investigating several machine learning techniques. We propose a novel approach for feature extraction, using measurements on joints of the extracted skeletons. The proposed features extract angles and displacements of skeleton joints, as the latter move into a 3D space. We define a set of gestures and construct a real-life data set. We train gesture classifiers under the assumptions that they shall be applied and evaluated to both known and unknown users. Experimental results with 11 classification approaches prove the effectiveness and the potential of our approach both with the proposed dataset and also compared to state-of-the-art research works.

Deep Learning Framework for Fingerspelling System using CNN

Abstract: Sign language is used for communication among the hearing-challenged-cum-speech-challenged community. It is the language that uses facial expressions, movements of hands and other body parts. Indian Sign language (ISL) is commonly used sign language, in India. These days, online interpreters are available for translating the sign language to common language and vice versa. But it requires an expert who can translate in both ways and also they charge. Thus, the communication between the hearing-challenged-cum-speech-challenged community and the rest has become difficult and costly. This causes isolation of the hearing-challenged-cum-speech-challenged community from the rest of society. Hence, this work focuses on bridging the communication gap between the two. One important aspect of sign language is finger spelling. Through finger spelling, a word that lacks a particular sign in sign language can be expressed by spelling each alphabet of that word. Here, a vision based finger spelling system using Convolutional Neural Networks (CNN) is created. The proposed CNN model performs as par with the InceptionV3 and better than ResNet and VGG16 models.