Monitor systems are ubiquitously deployed in public areas. However, monitor systems face a major challenge regarding long-distance object recognition. Super-resolution constitutes a popular choice to address this challenge. Since super-resolution methods are used in many applications, it is necessary to understand these methods and make a comparative study of them. In this paper, we perform a comparative study on six super-resolution methods over two recognition algorithms. The paper evaluates super-resolution performance based on recognition accuracy, and serves as a summary assessment of image super-resolution algorithms.
No takes yet. Share an insight, caveat, or question.
Yang et al. (2018) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: