Jinming Su

Title: Innovations of Jinming Su in Image Segmentation

Introduction

Jinming Su is a notable inventor based in Beijing, China. He has made significant contributions to the field of image processing, particularly in the area of salient object segmentation. His innovative approach combines advanced techniques to enhance the accuracy of image analysis.

Latest Patents

Jinming Su holds a patent for an "Image salient object segmentation method and apparatus based on reciprocal attention between foreground and background." This method involves obtaining a feature map from a training image using a convolutional neural backbone network. It further includes the steps of acquiring initial feature responses for both foreground and background, updating these responses through a reciprocal attention weight matrix, and training a convolutional neural network model to achieve precise segmentation results.

Career Highlights

Jinming Su is affiliated with Beihang University, where he continues to advance research in image processing technologies. His work has garnered attention for its innovative methodologies and practical applications in various fields.

Collaborations

He collaborates with esteemed colleagues such as Jia Qi Li and Changqun Xia, contributing to a dynamic research environment that fosters innovation and development in technology.

Conclusion

Jinming Su's contributions to image segmentation through his patented methods exemplify the intersection of technology and creativity. His work continues to influence advancements in image processing and related fields.