典型文献
Label Enhancement for Scene Text Detection
文献摘要：
Segmentation-based scene text detection has drawn a great deal of attention, as it can describe the text instance with arbitrary shapes based on its pixel-level prediction. However, most segmentation-based methods suffer from complex post-processing to separate the text instances which are close to each other, resulting in considerable time consumption during the inference procedure. A label enhancement method is proposed to construct two kinds of training labels for segmentation-based scene text detection in this paper. The label distribution learning (LDL) method is used to overcome the problem brought by pure shrunk text labels that might result in sub-optimal detection perfor?mance. The experimental results on three benchmarks demonstrate that the proposed method can consistently improve the performance with?out sacrificing inference speed.
文献关键词：
中图分类号：
作者姓名：
MEI Junjun;GUAN Tao;TONG Junwen
作者机构：
State Key Laboratory of Mobile Network and Mobile Multimedia Technology,Shenzhen 518055,China;ZTE Corporation,Shenzhen 518057,China
文献出处：
引用格式：
[1]MEI Junjun;GUAN Tao;TONG Junwen-.Label Enhancement for Scene Text Detection)[J].中兴通讯技术（英文版）,2022(04):89-95
A类：
B类：
Label,Enhancement,Scene,Text,Detection,Segmentation,scene,text,detection,has,drawn,great,deal,attention,can,describe,arbitrary,shapes,its,pixel,level,prediction,However,most,segmentation,methods,suffer,from,complex,post,processing,separate,instances,which,are,close,each,other,resulting,considerable,consumption,during,inference,procedure,enhancement,proposed,construct,two,kinds,training,labels,this,paper,distribution,learning,LDL,used,overcome,problem,brought,by,pure,shrunk,that,might,sub,optimal,experimental,results,three,benchmarks,demonstrate,consistently,improve,performance,out,sacrificing,speed
AB值：
0.653693
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
