There is a persistent communication barrier between the deaf and normal community because a norma... more There is a persistent communication barrier between the deaf and normal community because a normal person has no or limited fluency with the sign language. A person with hear-impairment has to express himself via interpreters or text writing.This inability to communicate effectively between the two groups affects their interpersonal relationships.There are about 0.24 million Pakistanis who are either deaf or mute and they communicate through Pakistan Sign Language(PSL). In this research work a system for recognizing hand gestures for Pakistan Sign Language alphabets in unimpeded environment is proposed. A digital camera is used to acquire PSL alphabet’s images withrandom background. These images are preprocessedfor hand detection using skin classification filter. The system uses discrete wavelet transform (DWT) for feature extraction.Artificial neural network(ANN) with back-propagation learning algorithm is employed torecognize the sign feature vectors. The dataset contains500 samples of Pakistan Sign Language alphabets with various background environments. The experiments show that the classification accuracy of the proposed system for the selected PSL alphabets is 86.40%.
There is a persistent communication barrier between the deaf and normal community because a norma... more There is a persistent communication barrier between the deaf and normal community because a normal person has no or limited fluency with the sign language. A person with hear-impairment has to express himself via interpreters or text writing.This inability to communicate effectively between the two groups affects their interpersonal relationships.There are about 0.24 million Pakistanis who are either deaf or mute and they communicate through Pakistan Sign Language(PSL). In this research work a system for recognizing hand gestures for Pakistan Sign Language alphabets in unimpeded environment is proposed. A digital camera is used to acquire PSL alphabet’s images withrandom background. These images are preprocessedfor hand detection using skin classification filter. The system uses discrete wavelet transform (DWT) for feature extraction.Artificial neural network(ANN) with back-propagation learning algorithm is employed torecognize the sign feature vectors. The dataset contains500 samples of Pakistan Sign Language alphabets with various background environments. The experiments show that the classification accuracy of the proposed system for the selected PSL alphabets is 86.40%.
Uploads
Papers by Saleem Ata
has no or limited fluency with the sign language. A person with hear-impairment has to express himself via
interpreters or text writing.This inability to communicate effectively between the two groups affects their
interpersonal relationships.There are about 0.24 million Pakistanis who are either deaf or mute and they
communicate through Pakistan Sign Language(PSL). In this research work a system for recognizing hand
gestures for Pakistan Sign Language alphabets in unimpeded environment is proposed. A digital camera is
used to acquire PSL alphabet’s images withrandom background. These images are preprocessedfor hand
detection using skin classification filter. The system uses discrete wavelet transform (DWT) for
feature extraction.Artificial neural network(ANN) with back-propagation learning algorithm is employed
torecognize the sign feature vectors. The dataset contains500 samples of Pakistan Sign Language alphabets
with various background environments. The experiments show that the classification accuracy of the
proposed system for the selected PSL alphabets is 86.40%.
has no or limited fluency with the sign language. A person with hear-impairment has to express himself via
interpreters or text writing.This inability to communicate effectively between the two groups affects their
interpersonal relationships.There are about 0.24 million Pakistanis who are either deaf or mute and they
communicate through Pakistan Sign Language(PSL). In this research work a system for recognizing hand
gestures for Pakistan Sign Language alphabets in unimpeded environment is proposed. A digital camera is
used to acquire PSL alphabet’s images withrandom background. These images are preprocessedfor hand
detection using skin classification filter. The system uses discrete wavelet transform (DWT) for
feature extraction.Artificial neural network(ANN) with back-propagation learning algorithm is employed
torecognize the sign feature vectors. The dataset contains500 samples of Pakistan Sign Language alphabets
with various background environments. The experiments show that the classification accuracy of the
proposed system for the selected PSL alphabets is 86.40%.