Stephen Shapiro

Title: Innovations of Stephen Shapiro

Introduction

Stephen Shapiro is an accomplished inventor based in Torrance, CA. He holds 2 patents that showcase his expertise in machine learning and image segmentation technologies. His work has significantly contributed to advancements in the field of computer vision.

Latest Patents

One of his latest patents is titled "Machine learning based image segmentation training with contour accuracy evaluation." This invention focuses on improving the accuracy of predicted segmentation masks. It involves extracting a ground-truth RGB image buffer and a binary contour image buffer from a ground-truth RGB image container for segmentation training. The process includes generating predicted segmentation masks, computing segmentation loss, and generating improved binary contours to enhance the accuracy of the predicted segmentation masks.

Another notable patent is "Hybrid video segmentation aided by optical flow for objects in motion." This invention outlines methods and systems for applying gamma adjustments to frames of an input video. It generates gamma-adjusted frames, applies segmentation techniques, and combines segmentation masks with optical flow maps to create hybrid segmentation masks.

Career Highlights

Stephen Shapiro has worked with prominent companies such as Sony Group Corporation and Sony Pictures Entertainment, Inc. His experience in these organizations has allowed him to develop and refine his innovative ideas in technology.

Collaborations

Some of his notable coworkers include Mengyu Chen and Miaoqi Zhu. Their collaboration has likely contributed to the success of his projects and patents.

Conclusion

Stephen Shapiro's contributions to machine learning and image segmentation are noteworthy. His patents reflect his innovative spirit and dedication to advancing technology in the field.