SIGN LANGUAGE RECOGNITION SYSTEM USING PYTHON AND OPENCV
Er. Manisha Vaidya1, Himanshu Tambuskar2, Gaurav Khopde3, Snehal Ghode4, Sushrut Deogirkar5,
*1Assistant Professor, *2,3,4,5 Students Department of Computer Science and Engineering,
Priyadarshini J L College of Engineering, Nagpur-440027,Maharashtra, India.
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract: Sign language recognition systems are becoming increasingly important for bridging the communication gap between hearing-impaired individuals and the hearing population. In this context, Python, OpenCV (Open-Source Computer Vision) and Mediapipe framework have emerged as powerful tools for developing sign language recognition systems. Python is a widely-used programming language with an extensive range of libraries and modules for computer vision, machine learning, and image processing, making it ideal for developing sign language recognition algorithms. OpenCV is an open-source computer vision library that provides a wide range of functionalities for image and video analysis, such as image filtering, feature detection, and object tracking. Mediapipe is a cross-platform framework for building machine learning pipelines, specifically designed for processing media data, including audio, video, and images. The main purpose of this paper is to demonstrate the methodology with the use of these technologies in sign language recognition systems involves capturing video or image data of sign language gestures and processing it using computer vision and machine learning algorithms to recognize the gestures and translate them into spoken or written language. Machine learning algorithms such as CNNs, SVMs, or RNNs can be used to train and classify the sign language gestures. However, these systems still face challenges, such as variability in sign language gestures and real-time processing. Ongoing research in this field aims to address these challenges and improve the accuracy and usability of sign language recognition systems.
Keywords: Data collection, Preprocessing, Hand landmarks detection, Training module, Sign recognition.