This inventor holds 2 USPTO granted patents. Top assignee: Yonsei University. Active years: 2024-2025.
Company Filing History:
Years Active: 2024-2025
Title: Cheolhyun Mun: Innovator in Artificial Intelligence and Image Segmentation
Introduction
Cheolhyun Mun is a prominent inventor based in Seoul, South Korea. He has made significant contributions to the field of artificial intelligence, particularly in image segmentation technologies. With a total of 2 patents, Mun's work is at the forefront of innovation in this rapidly evolving area.
Latest Patents
Cheolhyun Mun's latest patents include a method and device for segmenting objects in images using artificial intelligence. This method involves obtaining an image containing at least one object, inputting it into a segmentation model, and segmenting the objects based on values output by the model. The learning process utilizes images as learning data, estimating the size of objects and applying different weightings to the pixels based on their estimated sizes. This approach is encapsulated in a size-weighted loss function that enhances the model's training.
Another notable patent is the CAM-based weakly supervised learning object localization device and method. This invention includes a feature map extractor that captures the feature map from the last convolutional layer of a convolutional neural network (CNN). It also features a weight vector binarization unit and a class activation map generation unit, which work together to facilitate effective object localization based on the processed feature maps.
Career Highlights
Cheolhyun Mun is affiliated with Yonsei University, where he continues to advance his research and development in artificial intelligence. His academic background and ongoing projects contribute to the university's reputation as a leading research institution in technology and innovation.
Collaborations
Mun collaborates with notable colleagues, including Jewook Lee and Pilhyeon Lee. Their combined expertise fosters a dynamic research environment that enhances the development of innovative solutions in their field.
Conclusion
Cheolhyun Mun's contributions to artificial intelligence and image segmentation are noteworthy. His patents reflect a commitment to advancing technology and improving methodologies in object localization and segmentation. Through his work at Yonsei University and collaborations with esteemed colleagues, Mun continues to shape the future of innovation in this critical area.