PGNet

2000년 도입 · 논문 2편에서 사용

PGNet is a point-gathering network for reading arbitrarily-shaped text in real-time. It is a single-shot text spotter, where the pixel-level character classification map is learned with proposed PG-CTC loss avoiding the usage of character-level annotations. With a PG-CTC decoder, we gather high-level character classification vectors from two-dimensional space and decode them into text symbols without NMS and RoI operations involved, which guarantees high efficiency. Additionally, reasoning the relations between each character and its neighbors, a graph refinement module (GRM) is proposed to optimize the coarse recognition and improve the end-to-end performance.

출처: PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network

소개 논문: PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network