RT DETR v2 r50vd model fine tuned on about 11k Manga, Webtoon, Manhua and Western Comic style Images for text and speech bubble detection. Training Image Size = 640. Training Images were resized, not cropped. Tall Webtoons were split vertically. Classes are: 0: bubble 1: text bubble (text inside bubbles) 2: text free (text outside bubbles)
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy