Method and system for estimating blur kernel size

US10311560B2 · kind B2 · utility

Assignee

• Huazhong University of Science and Technology · CN

Inventors

• Nong Sang · Hubei, CN
• Lerenhan Li · Hubei, CN
• Luxin Yan · Hubei, CN
• Changxin Gao · Hubei, CN
• Yuanjie Shao · Hubei, CN
• Juncai Peng · Hubei, CN
• Shiwei Zhang · Hangzhou City, CN
• Jin Wang · Tangxia, CN

Key dates

• Filing date: Sep 19, 2017
• Grant date: Jun 4, 2019
• Expiry date: Feb 10, 2038

Classification

• Technology area (CPC G): Physics
• CPC primary: G06T2207/20084
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

A method for estimating a blur kernel size, the method including: (1) pre-processing a blurred image, to obtain an image, so that a size of the image satisfies an image input size of a multi-class convolutional neural network (CNN); (2) inputting the image into a multi-class CNN with completed training, to obtain a blur-kernel-size probability distribution vector; and (3) comparing each element in the blur-kernel-size probability distribution vector, so that an estimated blur kernel size of the blurred image is the blur kernel size corresponding to a largest element. The invention also provides a system for estimating a blur kernel size. The system includes an image pre-processing module, a training-set synthesizing module, a multi-class CNN module, and a blur kernel size estimation module.