Pixel-Anchor: A Fast Oriented Scene Text Detector with Combined Networks

Abstract

Recently, semantic segmentation and general object detection frameworks have been widely adopted by scene text detecting tasks. However, both of them alone have obvious shortcomings in practice. In this paper, we propose a novel end-to-end trainable deep neural network framework, named Pixel-Anchor, which combines semantic segmentation and SSD in one network by feature sharing and anchor-level attention mechanism to detect oriented scene text. To deal with scene text which has large variances in size and aspect ratio, we combine FPN and ASPP operation as our encoder-decoder structure in the semantic segmentation part, and propose a novel Adaptive Predictor Layer in the SSD. Pixel-Anchor detects scene text in a single network forward pass, no complex post-processing other than an efficient fusion Non-Maximum Suppression is involved. We have benchmarked the proposed Pixel-Anchor on the public datasets. Pixel-Anchor outperforms the competing methods in terms of text localization accuracy and run speed, more specifically, on the ICDAR 2015 dataset, the proposed algorithm achieves an F-score of 0.8768 at 10 FPS for 960 x 1728 resolution images.

arXiv comment10 pages, 11 figures, 3 tables

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network
• Synthetic Data for Text Localisation in Natural Images
• Face Attention Network: An Effective Face Detector for the Occluded Faces
• Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
• Single Shot Text Detector with Regional Attention
• Shape Robust Text Detection with Progressive Scale Expansion Network
• Sliding Line Point Regression for Shape Robust Scene Text Detection
• Fused Text Segmentation Networks for Multi-oriented Scene Text Detection

Cited by in corpus (5)

• Pyramid Mask Text Detector
• See More Than Once -- Kernel-Sharing Atrous Convolution for Semantic Segmentation
• Geometry Normalization Networks for Accurate Scene Text Detection
• RRPN++: Guidance Towards More Accurate Scene Text Detection
• Location-Aware Feature Selection Text Detection Network