|
| Abstract: |
| To remove handwritten texts from an image of a document taken by smart phone, an intelligent removal method was proposed that combines dewarping and Fully Convolutional Network with Atrous Convolutional and Atrous Spatial Pyramid Pooling (FCN-AC-ASPP). For a picture taken by a smart phone, firstly, the image is transformed into a regular image by the dewarping algorithm. Secondly, the FCN-AC-ASPP is used to classify printed texts and handwritten texts. Lastly, handwritten texts can be removed by a simple algorithm. Experiments show that the classification accuracy of the FCN-AC-ASPP is better than FCN, DeeplabV3+, FCN-AC. For handwritten texts removal effect, the method of combining dewarping and FCN-AC-ASPP is superior to FCN-AC-ASP alone. |
| Key words: handwritten texts printed texts classification FCN-AC-ASPP smart phone |
| DOI：10.11916/j.issn.1005-9113.23017 |
| Clc Number:TP391.1 |
| Fund: |
|
| Descriptions in Chinese: |
| 使用智能手机去除手写体的方法 方海泉1,2 浙江工业大学 公共管理学院，杭州 310023； 2. 浙江星算科技有限公司，杭州310023） 摘要：针对智能手机拍摄的文档图像手写体去除效果不够理想的问题，提出一种将图像去扭曲和全卷积神经网络-空洞卷积-空洞空间金字塔池化（FCN-AC-ASPP）相结合的手写体去除方法。对于智能手机拍摄的图像，首先通过图像去扭曲算法将图像转换为规则图像。然后使用FCN-AC-ASPP对印刷体和手写体进行分类。分类之后，通过简单算法就可以去除手写体。实验表明，FCN-AC-ASPP算法的分类精度优于FCN、DeeplabV3+、FCN-AC。并且，对于智能手机拍摄的文档图像的手写体去除效果，将图像去扭曲和FCN-AC-ASPP相结合的方法优于单独使用FCN-AC-ASP的方法。 关键词：手写体；印刷体；分类；FCN-AC-ASPP；智能手机 |
