This inventor holds 3 USPTO granted patents. Top assignee: Eygs LLP. Active years: 2025-2026.
Company Filing History:
Years Active: 2025-2026
Title: Marcin Plata: Innovator in Image Denoising Technology
Introduction
Marcin Plata is a notable inventor based in Wrocław, Poland. He has made significant contributions to the field of image processing, particularly in the area of document denoising. With a total of 3 patents, his work focuses on enhancing the quality of noisy documents for better readability and optical character recognition.
Latest Patents
One of Marcin Plata's latest patents is titled "Methods and apparatus for end-to-end unsupervised multi-document blind image denoising." This innovative technology addresses the challenge of removing various types of noise from documents without the need for paired target cleaned documents. The multi-document blind image denoiser effectively preserves the contents of documents, making them suitable for optical character recognition. The system integrates a Mixture of Experts with a cycle-consistent GAN as the base network, which allows it to remove multiple types of noise, including salt & pepper noise, blurred and/or faded text, and watermarks from documents at various levels of intensity.
Career Highlights
Marcin Plata has established himself as a key figure in the field of image processing. His work has garnered attention for its innovative approach to solving complex problems related to document clarity and readability. His contributions are not only valuable for academic research but also have practical applications in various industries.
Collaborations
Marcin has collaborated with talented individuals such as Hamid Reza Motahari-nezad and Mehrdad Jabbarzadeh Gangeh. These collaborations have further enriched his research and development efforts, leading to advancements in the technology he specializes in.
Conclusion
Marcin Plata's work in image denoising technology exemplifies the impact of innovation in enhancing document quality. His patents reflect a commitment to improving optical character recognition and document processing, making significant strides in the field.