A knowledge-based sign synthesis architecture

This paper presents the modules that comprise a knowledge-based sign synthesis architecture for Greek sign language (GSL). Such systems combine natural language (NL) knowledge, machine translation (MT) techniques and avatar technology in order to allow for dynamic generation of sign utterances. The NL knowledge of the system consists of a sign lexicon and a set of GSL structure rules, and is exploited in the context of typical natural language processing (NLP) procedures, which involve syntactic parsing of linguistic input as well as structure and lexicon mapping according to standard MT practices. The coding on linguistic strings which are relevant to GSL provide instructions for the motion of a virtual signer that performs the corresponding signing sequences. Dynamic synthesis of GSL linguistic units is achieved by mapping written Greek structures to GSL, based on a computational grammar of GSL and a lexicon that contains lemmas coded as features of GSL phonology. This approach allows for robust conversion of written Greek to GSL, which is an essential prerequisite for access to e-content by the community of native GSL signers. The developed system is sublanguage oriented and performs satisfactorily as regards its linguistic coverage, allowing for easy extensibility to other language domains. However, its overall performance is subject to current well known MT limitations.     

Effect of spatial reference and verb inflection on the usability of sign language animations

Computer-generated animations of American Sign Language (ASL) can improve the accessibility of information, communication, and services for the significant number of deaf adults in the US with difficulty in reading English text. Unfortunately, there are several linguistic aspects of ASL that current automatic generation or translation systems cannot produce (or are time-consuming for human animators to create). To determine how important such phenomena are to user satisfaction and the comprehension of ASL animations, studies were conducted in which native ASL signers evaluated ASL animations with and without: establishment of spatial reference points around the virtual human signer representing entities under discussion, pointing pronoun signs, contrastive role shift, and spatial inflection of ASL verbs. It was found that adding these phenomena to ASL animations led to a significant improvement in user comprehension of the animations, thereby motivating future research on automating the generation of these animations.     

Computer animated visual translation from natural language to sign language

Computer animation and visualization can facilitate communication between the hearing impaired and those with normal speaking capabilities. This paper presents a model of a system that is capable of translating text from a natural language into animated sign language. Techniques have been developed to analyse language and transform it into sign language in a systematic way. A hand motion coding method as applied to the hand motion representation, and control has also been investigated. Two translation examples are also given to demonstrate the practicality of the system.     

手语识别、翻译与生成综述

手语研究是典型的多领域交叉研究课题,涉及计算机视觉、自然语言处理、跨媒体计算、人机交互等多个方向,主要包括离散手语识别、连续手语翻译和手语视频生成.手语识别与翻译旨在将手语视频转换成文本词汇或语句,而手语生成是根据口语或文本语句合成手语视频.换言之,手语识别翻译与手语生成可视为互逆过程.文中综述了手语研究的最新进展,介...     

自然手语动作序列生成的研究

文章探讨了如何让在手语新闻播报中的卡通人按照自然手语的语法规则而非正常人的语法规则来打手语。首先整理了现代汉语自然手语的规则并将其形式化,并建立了正常汉语到汉语自然手语转换的形式规则库;从而实现了现代汉语文本到相应的自然手语的手语动作序列的自动生成。最后将其嵌入到通过手语合成技术和卡通动画的手语新闻播报系统中,使其在线输出的是符合聋人习惯的自然手语。     

基于状态机的手语动画自动生成技术

目前,手语的资源主要是图片、视频和动画。由于这些资源相对比较固定,无法动态扩展,不能满足手语动画自动生成的需求。论文将状态机应用于手语动画生成中,设计了基于状态机的手语动画自动生成技术算法,并将该算法应用到公交报站手语自动生成系统中。实验结果表明,生成的手语动作流畅,准确率达97%,具有良好的市场应用前景。     

基于VRML虚拟人的维文手语库的构建

维吾尔语的手语合成有助于改善维吾尔族聋哑人与听力正常人进行自然交流,也可以应用于计算机辅助维吾尔哑语教学、维文电视节目播放等方面。维文手语库是维吾尔语手语合成的基础。通过分析维吾尔手语的特点,采用关键帧插值技术来控制VRML虚拟人的手势动作,利用Visual C++和OpenGL环境实现了一个维吾尔文的手势编辑系统,通过手势运动数据驱动虚拟人来实时显示当前的手势状态。通过该系统,收集了常用的维吾尔语词汇及32个维吾尔字母的手势运动数据。     

A human-machine cooperative system for generating sign language animation using thermal image

We propose a new approach aimed at sign language animation by skin region detection on an infrared image. To generate several kinds of animations expressing personality and/or emotion appropriately, conventional systems require many manual operations. However, a promising way to realize a lower workload is to manually refine an animation made automatically with a dynamic image of real motion. In the proposed method, a 3D CG model corresponding to a characteristic posture in sign language is made automatically by pattern recognition on a thermal image, and then a person’s hand in the CG model is set. The hand part is made manually beforehand. If necessary, the model can be replaced manually by a more appropriate model corresponding to training key frames and/or the model can be refined manually. In our experiments, a person experienced in using sign language recognized the Japanese sign language of 71 words expressed as animation with 88.3% accuracy, and three persons experienced in using sign language also recognized the sign language animation representing three emotions (neutral, happy and angry) with 88.9% accuracy. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

Rotation,Translation and Scale Invariant Sign Word Recognition Using Deep Learning

Communication between people with disabilities and people who do not understand sign language is a growing social need and can be a tedious task. One of the main functions of sign language is to communicate with each other through hand gestures. Recognition of hand gestures has become an important challenge for the recognition of sign language. There are many existing models that can produce a good accuracy, but if the model test with rotated or translated images, they may face some difficulties to make good performance accuracy. To resolve these challenges of hand gesture recognition, we proposed a Rotation, Translation and Scale-invariant sign word recognition system using a convolutional neural network (CNN). We have followed three steps in our work: rotated, translated and scaled (RTS) version dataset generation, gesture segmentation, and sign word classification. Firstly, we have enlarged a benchmark dataset of 20 sign words by making different amounts of Rotation, Translation and Scale of the original images to create the RTS version dataset. Then we have applied the gesture segmentation technique. The segmentation consists of three levels, i) Otsu Thresholding with YCbCr, ii) Morphological analysis: dilation through opening morphology and iii) Watershed algorithm. Finally, our designed CNN model has been trained to classify the hand gesture as well as the sign word. Our model has been evaluated using the twenty sign word dataset, five sign word dataset and the RTS version of these datasets. We achieved 99.30% accuracy from the twenty sign word dataset evaluation, 99.10% accuracy from the RTS version of the twenty sign word evolution, 100% accuracy from the five sign word dataset evaluation, and 98.00% accuracy from the RTS version five sign word dataset evolution. Furthermore, the influence of our model exists in competitive results with state-of-the-art methods in sign word recognition.     

Towards subject independent continuous sign language recognition: A segment and merge approach

This paper presents a segment-based probabilistic approach to robustly recognize continuous sign language sentences. The recognition strategy is based on a two-layer conditional random field (CRF) model, where the lower layer processes the component channels and provides outputs to the upper layer for sign recognition. The continuously signed sentences are first segmented, and the sub-segments are labeled SIGN or ME (movement epenthesis) by a Bayesian network (BN) which fuses the outputs of independent CRF and support vector machine (SVM) classifiers. The sub-segments labeled as ME are discarded and the remaining SIGN sub-segments are merged and recognized by the two-layer CRF classifier; for this we have proposed a new algorithm based on the semi-Markov CRF decoding scheme. With eight signers, we obtained a recall rate of 95.7% and a precision of 96.6% for unseen samples from seen signers, and a recall rate of 86.6% and a precision of 89.9% for unseen signers.     

A belief-based sequential fusion approach for fusing manual signs and non-manual signals

Most of the research on sign language recognition concentrates on recognizing only manual signs (hand gestures and shapes), discarding a very important component: the non-manual signals (facial expressions and head/shoulder motion). We address the recognition of signs with both manual and non-manual components using a sequential belief-based fusion technique. The manual components, which carry information of primary importance, are utilized in the first stage. The second stage, which makes use of non-manual components, is only employed if there is hesitation in the decision of the first stage. We employ belief formalism both to model the hesitation and to determine the sign clusters within which the discrimination takes place in the second stage. We have implemented this technique in a sign tutor application. Our results on the eNTERFACE’06 ASL database show an improvement over the baseline system which uses parallel or feature fusion of manual and non-manual features: we achieve an accuracy of 81.6%.     

基于索引结构的手语词库的设计

随着人机交互应用的日益广泛,手语识别技术得到了很大的重视与发展。基于对当前手语识别技术的研究, 针对手语模板库存在的缺点及中国手语的特点,对手语词库进行设计,并通过建立基于索引结构的手语词库,提高了 手语识别的准确性和效率。     

聋哑学校语文辅助教学系统研究

为了达到辅助老师教聋哑学生语文的目的,开发一套文本翻译成手语的教学系统。采用改进的结巴分词对课文内容进行分词,课文句子转化成词语序列,使用系统编辑功能对词语序列进行编辑,使其满足文法手语要求;同时建立虚拟人,采用关键帧技术制作手语动画,使用Unity3D游戏引擎完成手语动画合成和动画之间的过渡,实现课文内容自动翻译成手语的辅助教学系统。该研究对聋哑学生语文教学有特殊的意义,具有一定的实用价值。     

基于VRML的手语合成系统中人体模型的运动实现

人体建模技术是实现手语合成系统的前提,采用VRML(V irtualRealityModeling Language)三维人体建模技术可以提高人体建模的性能,为手语合成系统打下良好的基础。在基于VRML三维人体模型的设计中,分析了人体模型的控制变化原理及仿射变换方法;采用线框模型实现了三维人体模型的建立,运用仿射变换方法实现人体模型的手臂控制运动。实验结果证明该方法可行有效。     

Bangla language modeling algorithm for automatic recognition of hand-sign-spelled Bangla sign language

Because of using traditional hand-sign segmentation and classification algorithm,many diversities of Bangla language including joint-letters,dependent vowels etc.and representing 51 Bangla written characters by using only 36 hand-signs,continuous hand-sign-spelled Bangla sign language(BdSL)recognition is challenging.This paper presents a Bangla language modeling algorithm for automatic recognition of hand-sign-spelled Bangla sign language which consists of two phases.First phase is designed for hand-sign classification and the second phase is designed for Bangla language modeling algorithm(BLMA)for automatic recognition of hand-sign-spelled Bangla sign language.In first phase,we have proposed two step classifiers for hand-sign classification using normalized outer boundary vector(NOBV)and window-grid vector(WGV)by calculating maximum inter correlation coefficient(ICC)between test feature vector and pre-trained feature vectors.At first,the system classifies hand-signs using NOBV.If classification score does not satisfy specific threshold then another classifier based on WGV is used.The system is trained using 5,200 images and tested using another(5,200×6)images of 52 hand-signs from 10 signers in 6 different challenging environments achieving mean accuracy of 95.83%for classification with the computational cost of 39.972 milliseconds per frame.In the Second Phase,we have proposed Bangla language modeling algorithm(BLMA)which discovers all"hidden characters"based on"recognized characters"from 52 hand-signs of BdSL to make any Bangla words,composite numerals and sentences in BdSL with no training,only based on the result of first phase.To the best of our knowledge,the proposed system is the first system in BdSL designed on automatic recognition of hand-sign-spelled BdSL for large lexicon.The system is tested for BLMA using hand-sign-spelled 500 words,100 composite numerals and 80 sentences in BdSL achieving mean accuracy of 93.50%,95.50%and 90.50%respectively.     

基于关键帧的连续手语语句识别算法研究

目前,对于动态手语的识别大多只是针对手语词汇的,对连续的手语语句的识别研究以及相应成果较少,原因在于难以对其进行有效的分割。提出了一种基于加权关键帧的手语语句识别算法。关键帧可以看作是手语词汇的基本组成单元,根据关键帧即可得到相关词汇,并将其组成连续的手语语句,从而避免了对手语语句直接做分割的难点。借助于体感设备,首先提出了一种基于手语轨迹的自适应关键帧提取算法,然后根据关键帧包含的语义对其进行加权处理,最后设计了基于加权关键帧序列的识别算法,得到连续的手语语句。实验证明,设计的算法可以实现对连续手语语句的实时识别。     

Sign language applications: preliminary modeling

For deaf persons to have ready access to information and communication technologies (ICTs), the latter must be usable in sign language (SL), i.e., include interlanguage interfaces. Such applications will be accepted by deaf users if they are reliable and respectful of SL specificities—use of space and iconicity as the structuring principles of the language. Before developing ICT applications, it is necessary to model these features, both to enable analysis of SL videos and to generate SL messages by means of signing avatars. This paper presents a signing space model, implemented within a context of automatic analysis and automatic generation, which are currently under development.

ASL Recognition by the Layered Learning Model Using Clustered Groups

American Sign Language (ASL) images can be used as a communication tool by determining numbers and letters using the shape of the fingers. Particularly, ASL can have an key role in communication for hearing-impaired persons and conveying information to other persons, because sign language is their only channel of expression. Representative ASL recognition methods primarily adopt images, sensors, and pose-based recognition techniques, and employ various gestures together with hand-shapes. This study briefly reviews these attempts at ASL recognition and provides an improved ASL classification model that attempts to develop a deep learning method with meta-layers. In the proposed model, the collected ASL images were clustered based on similarities in shape, and clustered group classification was first performed, followed by reclassification within the group. The experiments were conducted with various groups using different learning layers to improve the accuracy of individual image recognition. After selecting the optimized group, we proposed a meta-layered learning model with the highest recognition rate using a deep learning method of image processing. The proposed model exhibited an improved performance compared with the general classification model.     

Automatic sign language analysis: a survey and the future beyond lexical meaning

Research in automatic analysis of sign language has largely focused on recognizing the lexical (or citation) form of sign gestures, as they appear in continuous signing, and developing algorithms that scale well to large vocabularies. However, successful recognition of lexical signs is not sufficient for a full understanding of sign language communication. Nonmanual signals and grammatical processes, which result in systematic variations in sign appearance, are integral aspects of this communication but have received comparatively little attention in the literature. In this survey, we examine data acquisition, feature extraction and classification methods employed for the analysis of sign language gestures. These are discussed with respect to issues such as modeling transitions between signs in continuous signing, modeling inflectional processes, signer independence, and adaptation. We further examine works that attempt to analyze nonmanual signals and discuss issues related to integrating these with (hand) sign gestures. We also discuss the overall progress toward a true test of sign recognition systems -dealing with natural signing by native signers. We suggest some future directions for this research and also point to contributions it can make to other fields of research. Web-based supplemental materials (appendices), which contain several illustrative examples and videos of signing, can be found at www.computer.org/publications/dlib.     

Modelling and recognition of the linguistic components in American Sign Language

The manual signs in sign languages are generated and interpreted using three basic building blocks: handshape, motion, and place of articulation. When combined, these three components (together with palm orientation) uniquely determine the meaning of the manual sign. This means that the use of pattern recognition techniques that only employ a subset of these components is inappropriate for interpreting the sign or to build automatic recognizers of the language. In this paper, we define an algorithm to model these three basic components form a single video sequence of two-dimensional pictures of a sign. Recognition of these three components are then combined to determine the class of the signs in the videos. Experiments are performed on a database of (isolated) American Sign Language (ASL) signs. The results demonstrate that, using semi-automatic detection, all three components can be reliably recovered from two-dimensional video sequences, allowing for an accurate representation and recognition of the signs.