Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Fresh data on Machine Learning are pre sented in a new report. According to news reporting originating in Los Angeles, California, by NewsRx journalists, research stated, "This study examines the lon gstanding need and challenge of providing contextual analysis of historical imag es stored in digital visual archives and the accessibility of retrieving context ual information from these historical archives. Contextual analysis is essential for disciplines such as history and art history, as it allows for the contextua lization of artwork and historical sources with historical narratives, which, in turn, enhances understanding of the artistic or political expression in the con tents of cultural products." The news reporters obtained a quote from the research from the University of Cal ifornia Los Angeles (UCLA), "To address this challenge, a novel approach is prop osed utilizing computer vision to trace the circulation and dissemination of his torical photographs in their original contexts. This method involves first using YOLO v7 to crop historical images from pictorial magazines, then training machi ne learning models on the cropped printed images plus another large dataset of o riginal historical photographs, and comparing the similarity of images between t he datasets of printed images and original photographs. To ensure accuracy of im age similarities between the two subsets with distinct image qualities, an ensem ble of three machine learning models-Vision Transformer, EfficientNetv2, and Swi n Transformerwas developed. Through this system, contexts in the circulation of historical photographs were discovered and new insights regarding the editing st rategies of propaganda magazines in East Asia during WWII were uncovered. These outcomes offer supporting evidence for previous research in the history and art historical disciplines, and demonstrate the potential of computer vision for unc overing new information from digital visual archives."
NETL
NSTL