Deep hand: How to train a cnn on 1 million hand images when your data is continuous and weakly labelled
This work presents a new approach to learning a frame-based classifier on weakly labelled
sequence data by embedding a CNN within an iterative EM algorithm. This allows the CNN …
sequence data by embedding a CNN within an iterative EM algorithm. This allows the CNN …
[PDF][PDF] A review paper on sign language recognition system for deaf and dumb people using image processing
MU Kakde, MG Nakrani, AM Rawate - International Journal of …, 2016 - academia.edu
Communications between deaf-mute and a normal person have always been a challenging
task. This paper reviews a different methods adopted to reduce barrier of communication by …
task. This paper reviews a different methods adopted to reduce barrier of communication by …
A feature covariance matrix with serial particle filter for isolated sign language recognition
As is widely recognized, sign language recognition is a very challenging visual recognition
problem. In this paper, we propose a feature covariance matrix based serial particle filter for …
problem. In this paper, we propose a feature covariance matrix based serial particle filter for …
Block-based histogram of optical flow for isolated sign language recognition
In this paper, we propose a block-based histogram of optical flow (BHOF) to generate hand
representation in sign language recognition. Optical flow of the sign language video is …
representation in sign language recognition. Optical flow of the sign language video is …
Detection of major ASL sign types in continuous signing for ASL recognition
Abstract In American Sign Language (ASL) as well as other signed languages, different
classes of signs (eg, lexical signs, fingerspelled signs, and classifier constructions) have …
classes of signs (eg, lexical signs, fingerspelled signs, and classifier constructions) have …
Signer-independent fingerspelling recognition with deep neural network adaptation
We study the problem of recognition of fingerspelled letter sequences in American Sign
Language in a signer-independent setting. Fingerspelled sequences are both challenging …
Language in a signer-independent setting. Fingerspelled sequences are both challenging …
Supporting one-time point annotations for gesture recognition
LV Nguyen-Dinh, A Calatroni… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
This paper investigates a new annotation technique that reduces significantly the amount of
time to annotate training data for gesture recognition. Conventionally, the annotations …
time to annotate training data for gesture recognition. Conventionally, the annotations …
Reconhecimento de sinais da libras utilizando descritores de forma e redes neurais artificiais
ILO Bastos - 2016 - repositorio.ufba.br
Gestos são ações corporais não-verbais voltadas para a expressão de algum significado.
Estes incluem movimentos de mãos, face, braços, dedos, entre outros, sendo abordados …
Estes incluem movimentos de mãos, face, braços, dedos, entre outros, sendo abordados …
[PDF][PDF] Recognition of Japanese sign language words represented by both arms using multi-stream HMMs
S Igari, N Fukumura - Proceedings of IMCIC-ICSIT, 2016 - iiis.org
We have been studied Japanese sign Language (JSL) recognition system. In our previous
research, we focused on only JSL words performed by the movement of the dominant arm …
research, we focused on only JSL words performed by the movement of the dominant arm …
American Sign Language fingerspelling recognition from video: Methods for unrestricted recognition and signer-independence
T Kim - arXiv preprint arXiv:1608.08339, 2016 - arxiv.org
In this thesis, we study the problem of recognizing video sequences of fingerspelled letters
in American Sign Language (ASL). Fingerspelling comprises a significant but relatively …
in American Sign Language (ASL). Fingerspelling comprises a significant but relatively …