An algorithm on sign words extraction and recognition of continuous Persian sign language based on motion and shape features of hands

Zadghorban, Masoud; Nahvi, Manoochehr

doi:10.1007/s10044-016-0579-2

Cited by 33 publications

(20 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The majority of works concerning gesture and SL recognition uses cameras or other external devices for data acquisition (e.g. [2,3,9,10,12,18,20,22,23,[38][39][40][41]). The main advantage of this solution is the acquisition of all data required for a perfect SL translation, such as position, configuration and movement of the hands, facial expressions, position and movement of the body.…”

Section: State Of the Artmentioning

confidence: 99%

Recognition and Classification of Dynamic Hand Gestures by a Wearable Data-Glove

2020

View full text Add to dashboard Cite

This paper introduces a complete work-flow for the translation of dynamic isolated signs based on data acquired from a data-glove. A sign language translation system based on a wearable device represents indeed a more efficient solution with respect to cameras or position trackers for helping speech-impaired people on a daily basis. The paper describes the different steps required for a sign language translation, namely segmentation, feature extraction and classification, together with the custom data-glove used for data-acquisition. The paper presents also experimental results, comparing different machine learning classifiers and discussing their performances both in terms of translation accuracy and computational time. The proposed work-flow has been tested both on data acquired from a custom data-glove and on a public database, and it outperforms those of other works in literature. The reported analysis suggests a multi-layer perceptron neural network as the most suitable classifier for the realization of a wearable sign language translation system.

show abstract

Section: State Of the Artmentioning

confidence: 99%

Recognition and Classification of Dynamic Hand Gestures by a Wearable Data-Glove

2020

View full text Add to dashboard Cite

show abstract

“…Erosion is a morphological process to erode or reduce the width of the surface size of an area or object. The erosion image of f by the element structure of matrix B shown in the equation (4). Morphological closing is dilation operation on an image followed by erosion operation shown in equation (5).…”

Section: B Segmentationmentioning

confidence: 99%

“…Pattern identification result of BISINDO alphabets is not uniform or heterogeneous. Some scientific studies about the identification of hand shape that representing a letter [3], [4], [5], [6].…”

Section: Introductionmentioning

confidence: 99%

Recognition of Bisindo Alphabets Based on Chain Code Contour and Similarity of Euclidean Distance

Indra

Madenda

Wibowo

2017

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

In Indonesia, there are two forms of sign language practiced in the community, i.e., Indonesian sign language or known as BISINDO, and Indonesian sign language system or known as SIBI. In this study, we conduct research about recognition of Bisindo alphabets using contour chain code for the method of feature extraction and similarity of Euclidean distance for the method of recognition. The features used are the probability of chain code generated from contour following and the formation of chain code. The proposed method in this study consisted of five section, i.e., input test image, segmentation, edge detection, feature extraction and matching process of the alphabet. In the testing of the proposed method, we used 52 images of hand gestures used as test images. The images are in the form of static images and 26 images of hand gestures used as reference images which represent 26 alphabets BISINDO from A to Z, where the images stored in the database. The test images of different shapes and sizes with image references. For recognition, we do the matching between the probability of the test image chain code with the probability of the reference image chain code using Euclidean distance. The measurement result of Euclidean distance in this study was generated average accuracy rate of similarity above 94%. This indicates that the method proposed in this study was effective and produce the level of similarity of BISINDO alphabets was accurate

show abstract

“…At present, everyone's research content is gradually turning to the research of multi-target, complex motion, and complex background video human motion gesture recognition. The classic video human motion gesture recognition methods are mainly as follows: (1) template matching method [1,2]; (2) state space method [3];…”

Section: Introductionmentioning

confidence: 99%

Human Motion Gesture Recognition Algorithm in Video Based on Convolutional Neural Features of Training Images

2020

IEEE Access

View full text Add to dashboard Cite

The main work of human motion gesture recognition is to recognize and analyze the behavior of human objects in the video. Although the current research in the field of human motion gesture recognition has achieved certain results, the human motion gesture recognition in real life scenes has great effects due to factors such as camera movement, target scale transformation, dynamic background, viewing angle, and illumination. This article first proposes a new method of constructing human motion posture features to describe human behavior. This method is based on deep convolutional neural network features and topic models. Experiments have verified that compared with the traditional feature map extracted from the convolutional neural network fully connected layer, the feature map extracted from the convolutional neural network convolutional layer is not only lower in dimension but also has higher discrimination. Secondly, based on the feature map of the convolutional neural network, the training map downsampling strategy is used to overcome the interference caused by the object's scale change and shape change. Finally, based on the basketball gesture recognition method, the behavior performance of the legs and arms in 9 basketball actions of walking, running, jumping, standing dribbling, walking dribbling, running dribbling, shooting, passing and receiving is analyzed. As well as the corresponding signal waveform characteristics, a two-stage data division method for basketball is proposed. The unit action data is extracted for analysis to realize feature extraction. In order to select the most suitable classifier for basketball gesture recognition, the constructed feature vector uses four Different classifiers are trained to construct different classifiers to realize the division of actions. INDEX TERMS Convolutional neural networks; training Images; human motion gesture recognition; classifier; feature vector Xiangui Bu was born in WeiShan, China, in 1981. Master of Physical Education, master of Education doctor, associate professor, master's supervisor, head of boxing course of Shandong Sport University, the first famous teacher of Shan dong Sport University. Visiting scholar of

show abstract

An algorithm on sign words extraction and recognition of continuous Persian sign language based on motion and shape features of hands

Cited by 33 publications

References 24 publications

Recognition and Classification of Dynamic Hand Gestures by a Wearable Data-Glove

Recognition and Classification of Dynamic Hand Gestures by a Wearable Data-Glove

Recognition of Bisindo Alphabets Based on Chain Code Contour and Similarity of Euclidean Distance

Human Motion Gesture Recognition Algorithm in Video Based on Convolutional Neural Features of Training Images

Contact Info

Product

Resources

About