SPORT REFEREE HAND SIGNS RECONGITION

Abstract

The battleground Players and their general environment is not quite as same as the conventional games like (Football, Cricket). Similarly, they face exceptional difficulties while playing on the Basketball court. So there should be research done to address these difficulties while carrying out Basketball Referees Hand Sign. The objective ofthis project is to develop image recognition algorithms to recognize hand signs in basketball game. This report explores different techniques used for the recognition of hand signs. Different stages involving image processing like the pre processing stage, segmentation and feature extraction will be studied and discussed. Finally the end product ofthe algorithms will be written in the software called Jupiter Notebook. This project uses the Tensor flow object detection API. The main advantage of using these technique is that they provides features extraction and detection that is suitable for person recognition. There are multiple of detections in our project for referee detection we are detecting the referee with whistle and we are successfully detecting the referee with accuracy ranging between 80 to 90%. This Project report discusses the most suitable deep-learning models for real time object detection and recognition and evaluates on the detection and recognition ofthree Referee Signs. The results of this Project are discussed in previous heading, along with answers to the research questions formulated in Design and Methodology, some concluding remarks and future work.