###
计算机系统应用:2020,29(6):175-180
本文二维码信息
码上扫一扫!
基于FCN的图像中文字目标语义分割
(南京航空航天大学 机电学院, 南京 210016)
Semantic Segmentation of Character Targets in Images Based on FCN
(College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 89次   下载 95
投稿时间:2019-10-28    修订日期:2019-11-20
中文摘要: 本文提出一种基于全卷积神经网络的图像中文字目标语义分割算法和一种新的数据集制作与增广方法. 该算法首先采用改进全卷积神经网络对图像中的文字目标进行初步分割, 然后利用大津法进行二值化处理, 划分出目标的大致区域, 最后用全连接条件随机场算法进行修正, 得到最终结果. 该算法在测试集上准确率为85.7%, 速度为0.181秒/幅, 为图像目标区域的进一步分析做准备.
Abstract:This study proposes an algorithm for semantic segmentation of targets in images based on fully convolutional neural networks and a new method to make and augment dataset. The algorithm primarily segments the targets from images using improved fully convolutional neural networks, OTSU method is applied to binarize images and segment the general areas of targets, finally, the fully connected conditional random field algorithm is used to correct the general areas of targets and get the final results. This algorithm achieves the accuracy of 85.7% and speed of 0.181 second per image on test set, and prepares for further analysis of targets in images.
文章编号:7426     中图分类号:    文献标志码:
基金项目:
引用文本:
刘信良,王静秋.基于FCN的图像中文字目标语义分割.计算机系统应用,2020,29(6):175-180
LIU Xin-Liang,WANG Jing-Qiu.Semantic Segmentation of Character Targets in Images Based on FCN.COMPUTER SYSTEMS APPLICATIONS,2020,29(6):175-180

用微信扫一扫

用微信扫一扫