Hybrid Task Cascade Region-Based Convolutional Neural Network is Used to Analyse Cricket Scores

Cricket scorecards reflect both teams' batting and bowling statistics. It usually contains each team's runs, wickets, and overs, as well as each batter's strike rate and bowler's data. The scoreboard also lists extras like wides, no-balls and wickets. Players, coaches, and analysts need a cricket scorecard to analyse performance, identify strengths and shortcomings, and make strategic choices. The Hybrid Task Cascade regions-Based convolutional neural networks (HTC-RCNN) is a computer vision model for object detection and instance segmentation. This novel design blends Cascade and Mask Region-based Convolutional Neural Networks (Mask R-CNN) models. Cricket scorecards are evaluated using Hybrid Task Cascade regions with convolutional neural networks. Cricket scorecards include each player's runs, wickets, and other statistics. Cricket scorecards may be automatically extracted and evaluated using the Hybrid Task Cascade regions with a convolutional neural networks model. Hybrid Task Cascade regions with convolutional neural networks multi-stage cascade design accurately identifies and segments objects. The model can detect and classify player names, runs scored, wickets were taken, batting and bowling statistics, and other significant cricket scorecard components. The Hybrid Task Cascade regions with convolutional neural networks model can automate the retrieval of important cricket scoreboard data, saving time and effort. This automatic analysis may help cricket match summaries, player evaluations, and statistical insights. Post-processing refines and verifies extracted data. According to experiments, the suggested technique beats current approaches in accuracy and efficiency. The suggested method correctly identifies team, player, and run names at 96.1%, 98.7%, and 97.3%, respectively.