Can Machine Automatically Discover Text Image from Overall Perspective

Jiang Wei,Wu Jiayi,Yao Chao

Table 3 Evaluation in TextDis dataset

Methods Precision (%) Recall (%) F-Measuremen Proposed Method 80.5 91.3 85.5 Bai[1] 93.7 95.4 94.6 Zhang[8] 75.4 97.9 85.1 Yao[13] 80.8 90.2 85.3 Neumann[14] 52.5 98.4 68.5