Masaaki Matsumura

Papers

Total Citations

H-Index

About

Masaaki Matsumura is a researcher whose work sits at the intersection of evolutionary computation and image processing. His primary research focus is on the development of adaptive, evolutionary pixel predictors for image and video coding. Matsumura’s key contribution lies in pioneering the use of genetic programming (GP) to dynamically generate pixel prediction algorithms, moving beyond the fixed, non-adaptive methods used in standards like JPEG and H.264. His most cited work, "A study on an evolutionary pixel predictor and its properties" (2009), established the foundational properties of this approach. To address the high computational cost of evolving predictors, he introduced an innovative acceleration technique using edge-based class separation, detailed in his 2010 paper. While his citation counts (totaling around 20) are modest, his work represents a significant conceptual shift—applying evolutionary principles to a domain traditionally dominated by static algorithms. Matsumura’s research offers a compelling vision for more flexible, self-optimizing compression systems, making him a notable figure in the niche field of evolutionary image coding.