Long Bao

Title: Long Bao: Innovator in Image Denoising Technologies

Introduction

Long Bao is a prominent inventor based in San Diego, CA. He has made significant contributions to the field of image processing, particularly in the area of image denoising. With a total of 2 patents, his work has garnered attention for its innovative approaches and practical applications.

Latest Patents

Long Bao's latest patents focus on systems and methods for image denoising using deep convolutional networks. The first patent describes a method that includes computing noise data by subtracting a noisy image from a corresponding ground truth image. It involves clustering noise values based on intensity values, permuting locations of the noise values, and generating a synthetic noise image. This synthetic image is then added to the ground truth image to create a synthetic noisy image, which is used for training a neural network to perform image denoising. The second patent outlines a method for denoising an image that involves receiving an input image and supplying it to a trained convolutional neural network (CNN). This CNN includes a multi-scale residual dense block and an atrous spatial pyramid pooling module, which together compute a denoised version of the input image.

Career Highlights

Long Bao is currently employed at Samsung Electronics Co., Ltd., where he continues to develop cutting-edge technologies in image processing. His work has not only advanced the field but has also contributed to the company's reputation as a leader in innovation.

Collaborations

Throughout his career, Long Bao has collaborated with notable colleagues, including Zengli Yang and Shuangquan Wang. These partnerships have fostered a collaborative environment that encourages the exchange of ideas and enhances the quality of their innovations.

Conclusion

Long Bao's contributions to image denoising technologies exemplify the impact of innovative thinking in the field of image processing. His patents reflect a commitment to advancing technology and improving the capabilities of neural networks in practical applications.