На информационном ресурсе применяются рекомендательные технологии (информационные технологии предоставления информации на основе сбора, систематизации и анализа сведений, относящихся к предпочтениям пользователей сети "Интернет", находящихся на территории Российской Федерации)

Feedbox

12 подписчиков

AI extracts speech bubbles from comic strips

Author: Kyle Wiggers / Source: VentureBeat

Above: A two-story-high mural dominates one side of Hero City. Batman, Robin, and founder/VC Tim Draper strike heroic poses. It was painted by DC Comics artist Jim Lee.

Segmentation — partitioning an image or scan into multiple segments, or sets of pixels — is a task at which artificial intelligence (AI) excels.

Case in point: Researchers at Google parent company Alphabet’s DeepMind recently revealed in an academic paper that they’d developed a system capable of segmenting CT scans with “near-human performance.” Now, scientists at the University of Potsdam in Germany have developed an AI segmentation tool for a slightly more cartoony medium: comics.

In a paper published on the preprint server Arxiv.org (“Deep CNN-based Speech Balloon Detection and Segmentation for Comic Books“), they describe a neural network (i.e., layers of mathematical functions modeled after biological neurons) that can detect and isolate speech bubbles in graphic novels and comic books. During tests involving a dataset containing speech bubbles with “wiggly tails” and “curved corners,” it achieved an F1 score (a measure of a test’s accuracy) of 0.94, which the researchers claim is state-of-the-art.

“Speech balloons usually consist of a carrier, [a symbolic device used to hold the text,] and a tail connecting the carrier to its root character from which the text emerges. Both tails and carriers come in a variety of shapes, outlines, and degrees of wiggliness,” the researchers explain. “It … pays to classify [speech bubbles] as different classes,…

Click here to read more

The post AI extracts speech bubbles from comic strips appeared first on FeedBox.

Ссылка на первоисточник

Картина дня

наверх