Methods and systems using improved convolutional neural networks for image processing

US11107189B2 · kind B2 · utility

Assignee

• Intel Corporation · US

Inventors

• Shandong Wang · Beijing, CN
• Yiwen Guo · Beijing, CN
• Anbang Yao · Beijing, CN
• Dongqi Cai · Beijing, CN
• Libin Wang · Dongxing District, CN
• Lin Xu · Fremont, US
• Ping Hu · Beijing, CN
• Wenhua Cheng · Shanghai, CN
• Yurong Chen · Beijing, CN

Key dates

• Filing date: Apr 7, 2017
• Grant date: Aug 31, 2021
• Expiry date: Apr 7, 2037

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V10/82
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Methods and systems are disclosed using improved Convolutional Neural Networks (CNN) for image processing. In one example, an input image is down-sampled into smaller images with a smaller resolution than the input image. The down-sampled smaller images are processed by a CNN having a last layer with a reduced number of nodes than a last layer of a full CNN used to process the input image at a full resolution. A result is outputted based on the processed down-sampled smaller images by the CNN having a last layer with a reduced number of nodes. In another example, shallow CNN networks are built randomly. The randomly built shallow CNN networks are combined to imitate a trained deep neural network (DNN).