TY - GEN
T1 - A Virtual Assistance for Visually Impaired People to Recognize Fabric Pattern and Color Using Human Computer Interaction Logic
AU - Panicker, M. S.Bravishma
AU - Mohandas, R.
AU - Hariharan, Shanmugasundaram
AU - Devi, K. Nirmala
AU - Chaitanya, M. S.K.
AU - Mishra, Rashmi
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Modern advancements in technology have paved the way for innovative solutions to assist visually impaired individuals in their daily lives. This study presents a virtual assistance system designed to recognize fabric patterns and colors using a combination of deep learning and human-computer interaction techniques. The system employs high-quality image acquisition methods, bilateral filtering, and histogram equalization to preprocess images, enhancing their quality for subsequent analysis. Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are integrated to form a Hybrid Fabric Pattern Recognition Network (HFPRN) that accurately identifies fabric patterns. Additionally, the system utilizes RGB color space conversion for precise color detection. Voice command capabilities via Amazon Alexa and tactile feedback mechanisms further enhance user interaction. Experimental results demonstrate the proposed system's high accuracy, with the HFPRN achieving 97% accuracy in fabric pattern recognition and 95% accuracy in color detection. This comprehensive solution significantly improves the autonomy and quality of life for visually impaired individuals by providing real-time, accurate feedback on fabric patterns and colors.
AB - Modern advancements in technology have paved the way for innovative solutions to assist visually impaired individuals in their daily lives. This study presents a virtual assistance system designed to recognize fabric patterns and colors using a combination of deep learning and human-computer interaction techniques. The system employs high-quality image acquisition methods, bilateral filtering, and histogram equalization to preprocess images, enhancing their quality for subsequent analysis. Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are integrated to form a Hybrid Fabric Pattern Recognition Network (HFPRN) that accurately identifies fabric patterns. Additionally, the system utilizes RGB color space conversion for precise color detection. Voice command capabilities via Amazon Alexa and tactile feedback mechanisms further enhance user interaction. Experimental results demonstrate the proposed system's high accuracy, with the HFPRN achieving 97% accuracy in fabric pattern recognition and 95% accuracy in color detection. This comprehensive solution significantly improves the autonomy and quality of life for visually impaired individuals by providing real-time, accurate feedback on fabric patterns and colors.
KW - Color Detection
KW - Convolutional Neural Networks
KW - Deep Learning
KW - Fabric Pattern Recognition
KW - Human-Computer Interaction
KW - Recurrent Neural Networks
KW - Virtual Assistance
KW - Visually Impaired
UR - http://www.scopus.com/inward/record.url?scp=85218413749&partnerID=8YFLogxK
U2 - 10.1109/ICCES63552.2024.10860143
DO - 10.1109/ICCES63552.2024.10860143
M3 - Conference contribution
AN - SCOPUS:85218413749
T3 - Proceedings of the 9th International Conference on Communication and Electronics Systems, ICCES 2024
SP - 1230
EP - 1237
BT - Proceedings of the 9th International Conference on Communication and Electronics Systems, ICCES 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 9th International Conference on Communication and Electronics Systems, ICCES 2024
Y2 - 16 December 2024 through 18 December 2024
ER -