Scholarlink

The idea of transforming raw data into a clean data set is known as data preprocessing. Before feeding the dataset into the algorithm, it undergoes preprocessing to identify any missing values, noisy data, or other irregularities. In Sect. 1 of this paper, the architecture of Residual and Recurrent Convolutional networks (RRCN) is introduced. There is a list of RRCN’s benefits over CNN as well. Section 2 discusses the need for preprocessing. Section 4 discusses several data preprocessing procedures. This step also discusses the various data processing implementation steps. These procedures involve reading the photographs, turning them to grayscale, shrinking them, normalizing them, applying noise-reduction filters, and then transforming them back to color images. Section 5 discusses the significance of data preprocessing in RRCN algorithm followed by conclusion as Sect. 6.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Data Extraction and Preprocessing in Residual Recurrent Convolutional Network (RRCN) for Video Super Resolution

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Deekshitha Arasa,
  • S. Sivaramakrishnan,
  • Sneha Sharma

摘要

The idea of transforming raw data into a clean data set is known as data preprocessing. Before feeding the dataset into the algorithm, it undergoes preprocessing to identify any missing values, noisy data, or other irregularities. In Sect. 1 of this paper, the architecture of Residual and Recurrent Convolutional networks (RRCN) is introduced. There is a list of RRCN’s benefits over CNN as well. Section 2 discusses the need for preprocessing. Section 4 discusses several data preprocessing procedures. This step also discusses the various data processing implementation steps. These procedures involve reading the photographs, turning them to grayscale, shrinking them, normalizing them, applying noise-reduction filters, and then transforming them back to color images. Section 5 discusses the significance of data preprocessing in RRCN algorithm followed by conclusion as Sect. 6.