一种改进的图像中的文本检测模型

An improved text detection model in image

本文提出了一种基于深度神经网络的高效自然场景文本检测模型IEAST(Improved EAST).该模型基于EAST(An Efficient and Accurate Scene Text Detector)进行了一系列改进,同时结合了物体检测以及实例分割的思想,通过用Inception Module替换原本特征融合的方式、加入Path Aggregation的思想以及采用Fuzzy Mask来提升模型的整体性能.IEAST是一段式模型,其不仅检测准度上不落后于绝大多数二段式State-of-the-art的文本检测模型,还能保证极快的检测速度.

Image Text Detection is the process of accurately locating text area in given images,which is the important prerequisite of OCR(Optical Character Recognition).This paper introduces Improved IEAST(Improved EAST)which is an efficient and accurate scene text detection model based on deep neural network.This model which combines the knowledge of both object detection and instance segmentation is a variant of EAST(An Efficient and Accurate Scene Text Detector)with several improvements.By replacing conv3x3feature merging with inception module,adding the idea of Path Aggregation and adopting Fuzzy Mask during training,IEAST gains improvements in performance with little compensation.Though IEAST is a one-stage model,it outperforms most of state-of-theart two-stage text detection models by not only maintaining comparable accuracy but also inferencing faster.IEAST shows good result on ICDAR(International Conference on Document Analysis and Recognition)2015dataset.