A Conditional Random Field Based Indian Sign Language Recognition System under Complex Background

Choudhury, Ananya; Talukdar, Anjan Kumar; Sarma, Kandarpa Kumar

doi:10.1109/csnt.2014.185

Cited by 18 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two of the commonly used hand segmentation techniques are skin color segmentation and background subtraction [8]. Here we have used a novel technique proposed by us in [7] which is robust to various background conditions. In this technique, a combination of skin color detection, frame differencing and contour matching is employed.…”

Section: Hand Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

An Adaptive Thresholding-Based Movement Epenthesis Detection Technique Using Hybrid Feature Set for Continuous Fingerspelling Recognition

et al. 2021

Self Cite

View full text Add to dashboard Cite

Sign language recognition systems are gaining importance in recent times as these have established themselves as important elements of human-computer interaction. Also these provide an opportunity for the deaf and hearing impaired to communicate with the common people without the need of an interpreter. Yet there are plenty of challenges in this field which are worth exploring and solutions formulated. In this paper, we have addressed the design of a continuous fingerspelling recognition system which segments a fingerspelling sequence into meaningful extracts and non-sign patterns and thereby recognizes the meaningful signs. Sign segmentation is carried out by means of a unique set of features which comprises of shape matching, velocity change and displacement of centroid between successive frames. Specialized techniques like adaptive thresholding and finite state machine model are also incorporated into our system for efficient classification of sign and movement epenthesis frames. We have validated the performance of our proposed system taking into account the continuous fingerspelling alphabets of American Sign Language considering both native and non-native signers and have obtained an accuracy of almost 91.29%. Our proposed system also has the potential to tackle complex backgrounds involving multiple objects, backgrounds with multiple signers and different brightness conditions.

show abstract

Section: Hand Segmentationmentioning

confidence: 99%

“…So, we have introduced a contour processing operation to counteract with such background situations. The detailed working of this operation for single as well as double-handed signs is described in [7].…”

Section: Hand Segmentationmentioning

confidence: 99%

An Adaptive Thresholding-Based Movement Epenthesis Detection Technique Using Hybrid Feature Set for Continuous Fingerspelling Recognition

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…[7] uses low cost packaging material, velostat for making piezo resistive sensors that detects a bend in fingers and the data generated is map to a character set by implementing a Minimum Mean Square Error machine learning algorithm. M. Delliraj and S. Vijayga Kumar propose a system with a flex sensor and IMU (Inertial Measurement Unit) to recognize sign symbol, speech synthesis chip for voice output and speech recognizing module for converting voice to sign symbol, interfaced with microcontroller [8]. [9][10] presents the sensor based technique.…”

Section: Literature Reviewmentioning

confidence: 99%

Hand Motion-Recognition in an Intelligent Communication Module

Nagpal¹,

Mittra²,

Agrawal³

2019

IJITEE

View full text Add to dashboard Cite

our country India consists of very high population. Almost 9 millions of population in this world can be counted as a deaf or dumb people or both. We all know that the most valuable gift from the god given to human is the capability to watch, hear, spoke & to give response as per the situation arises. We all know communication is one of the most important medium through which one may carve up his/her feelings or express the information to others. The key points in communication are ability of listening and speak the word but so many from us are unlucky because they are not gifted by this ability from the god these are deaf & dumb and people. Now a days so many researches are going on to solve difficulties of these people of our society because they had to face very hard to communicate with normal person. It is too hard for mute(deaf & dumb) people to transmit their information to the normal people. As all normal people are not fully trained to understand different sign lingo, the communication between these two types of people becomes too complex. At the time emergency or other days whenever a mute (Deaf & Dumb) people are travelling passing a message (data) becomes too hard. Due to this disability one that has hearing and speaking disability doesn’t want to stand and face the race with normal person. Since the communication for the mute people is image (Visibility), not acoustic (Audio). For these mute people Hand motion plays a very part for communication. The data transmission between mute-deaf & normal people is always a very challenging job. Deaf people make use of sign language or gestures to make understand what he/she trying to say but it is impossible to understand by hearing people. The admittance to various communication based technologies plays an essential role for these (mute) handicapped peoples. Developing a small and compressed gadget for these mute people is a difficult task. Deaf-Dumb people find a difficulty in communicating with normal people and hence they always stay apart in their societies. Basically deaf-dumb ones uses various sign language for communication, & they always face lots of difficulty while communicating with normal people because they all not able to understand sign language every time. Hence there is always a hurdle in communication between these two type of peoples. There are so many researches has done in regulate to search a simple and easy way for mute people to communicate with the normal people and articulate themselves to the rest of the real world. So many improvements have been done in sign language but all are based on American gesture (sign) Language. Our research work is purely designed to provide an aid to this deaf-mute by developing and designing a smart communication module which will help to renovate sign language to text & speech communication with other and to help them lead a life in a much better way. Our paper represents a static gesture recognition algorithm that will be designed and implemented will be used in the smart communication system to bridge the communication gap between deaf & dumb and normal people. If the algorithm is implemented completely it can be can be also used to capture and analyze emotions of the people in area where high security is desired.

show abstract

“…In [10] an approach was proposed to develop an electronic instrument that can translate the sign language into speech to provide the communication between the mute people with general public. This also developed a data base for different signs which are called by signs world atlas.…”

Section: Related Workmentioning

confidence: 99%

Curvilinear Tracing Approach for Extracting Kannada Word Sign Symbol from Sign Video

Kagalkar¹,

Gumaste²

2017

IJIGSP

View full text Add to dashboard Cite

Abstract-Gesture based communications are utilized as a primary method of correspondence, however, the differing qualities in the sign image portrayal limit its use to district bound. There is a tremendous assorted quality in the sign image portrayal from one nation to another, one state to another. In India, there is distinctive gesturebased communication watched for each state locale. It is henceforth exceptionally troublesome for one area individual to convey to other utilizing a signature image. This paper proposes a curvilinear tracing approach for the shape portrayal of Kannada communication via gestures acknowledgment. To build up this approach, a dataset is consequently made with all Swaragalu, Vyanjanagalu, Materials and Numbers in Kannada dialect. The arrangement of the dataset is framed by characterizing a vocabulary dataset for various sign images utilized as a part of regular interfacing. In the portrayal of gesturebased communication for acknowledgment, edge elements of hand areas are thought to be an ideal element portrayal of communication through signing. In the preparing of gesture-based communication, the agent includes assumes a critical part in arrangement execution. For the developed approach of sign language detection, where a single significant transformation is carried out, a word level detection is then performed. To represent the processing efficiency, a set of cue symbols is used for formulating a word. This word symbols are then processed to evaluate the performance for sign language detection. Word processing is carried out as a recursive process of a single cue symbol representation, where each frame data are processed for a curvilinear shape feature. The frame data are extracted based on the frame reading rate and multiple frames are processed in successive format to extract the region of interest. A system outline to process the video data and to give an optimal frame processing for sign recognition a word level process is performed.Index Terms-Curvilinear feature; leap forward tracing; support vector machine, kannada sign language.

show abstract

A Conditional Random Field Based Indian Sign Language Recognition System under Complex Background

Cited by 18 publications

References 8 publications

An Adaptive Thresholding-Based Movement Epenthesis Detection Technique Using Hybrid Feature Set for Continuous Fingerspelling Recognition

An Adaptive Thresholding-Based Movement Epenthesis Detection Technique Using Hybrid Feature Set for Continuous Fingerspelling Recognition

Hand Motion-Recognition in an Intelligent Communication Module

Curvilinear Tracing Approach for Extracting Kannada Word Sign Symbol from Sign Video

Contact Info

Product

Resources

About