TSER: A Two-Stage Character Segmentation Network With Two-Stream Attention and Edge Refinement

Segmenting characters in an image is a classic yet challenging task in computer vision. Correctly determining boundaries of adhesive characters with various scales and shapes is essential for character segmentation, especially for separating handwritten characters. Nevertheless, there is seldom work...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE access 2020, Vol.8, p.205216-205230
Hauptverfasser:	Zhang, Jinyingming, Liu, Jin, Xu, Xiongwei, Gong, Peizhu, Duan, Mingyang
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial neural networks Boundaries cascaded edge refinement network Character segmentation Computer vision deep learning Feature extraction Handwriting Image segmentation Machine learning Object detection Object recognition Proposals Semantics Shape Task analysis two-stream attention mechanism
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!