Fingerspelling Identification For American Sign Language Based On Resnet-18
Journal: International Journal of Advanced Networking and Applications (Vol.13, No. 01)Publication Date: 2021-08-28
Authors : ZHANG Han-wen; HU Ying; ZOU Yong-jia; WU Cheng-yu;
Page : 4816-4820
Keywords : Convolutional Neural Network; Data augmentation; Resnet-18; Sign language recognition;
Abstract
Sign language as the main communication channel for deaf and hearing people, plays a very important role in daily life. With the rapid development of the field of deep learning, the field of sign language recognition has ushered in new opportunities. Aiming at the small number of sign language samples and low detection accuracy, an American sign language detection method based on Resnet-18 and data augmentation is proposed. First, the sign language picture is adjusted to 64×64 size using the filling method, and then the data is augmented by methods such as chromaticity change, rotation, and noise addition to increase the diversity of data samples and improve the robustness of the detection method. The experimental results show that the accuracy of the sign language recognition method based on Resnet-18 can reach 99%, which provides a new method for sign language recognition.
Other Latest Articles
- MIND MAPPING: A METACOGNITIVE APPROACH TO ELEVATE ACHIEVEMENT IN MATHEMATICS OF SECONDARY SCHOOL STUDENTS
- SIGNIFICANCE OF NEUROECONOMICS IN MEDIA CORPORATIONS SURVIVAL IN THE AGE OF DIGITALIZATION
- CONSUMPTİON, CONSUMER BEHAVİOR AND NEW HABİTS ACQUİRED BY CONSUMERS AS A RESULT OF COVID-19 MEASURES
- Performance Analysis On Bangla Handwritten Digit Recognition Using CNN And Transfer Learning
- RPTRA CONCEPT IN THE ARCHIPELAGO: BASED ON AN EQUALITY AND LEGAL PROTECTION APPROACH
Last modified: 2021-08-31 19:00:56