학술논문

Understanding and Analyzing Methods of Character Identification in Movies
Document Type
Conference
Source
2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS) Intelligent Computing and Control Systems (ICICCS), 2020 4th International Conference on. :788-795 May, 2020
Subject
Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
Industries
TV
Face recognition
Semantics
Motion pictures
Control systems
Classification algorithms
Character identification
graph matching
error-correcting graph matching (ECGM)
optical character recognition (OCR)
multiple kernel learning (MKL)
earthmover distance (EMD)
Language
Abstract
Film and television industry is one of the fastest- growing sectors across the globe. Character identification and its method classification have attracted a lot of attention from researchers because of its applications in video summarization, personalized video retrieval, and semantic video analysis. In this paper, we study and analyze 14 algorithms categorizing them into three categories and compare them based on various parameters and present our findings in a tabular form.