Document images classification based on deep learning

被引：2

作者：

Hu, Biao ^{[1
]}

Ergu, Daji ^{[1
]}

Yang, Huan ^{[1
]}

Liu, Kuiyi ^{[1
]}

Cai, Ying ^{[1
]}

机构：

[1] Southwest Minzu Univ, Key Lab Elect & Informat Engn, State Ethn Affairs Commiss, Chengdu 610041, Peoples R China

来源：

7TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND QUANTITATIVE MANAGEMENT (ITQM 2019): INFORMATION TECHNOLOGY AND QUANTITATIVE MANAGEMENT BASED ON ARTIFICIAL INTELLIGENCE | 2019年 / 162卷

基金：

中国国家自然科学基金;

关键词：

Financial business; Convolutional neural network; Image classification;

D O I：

10.1016/j.procs.2019.12.018

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In the financial business, there are cumbersome and error-prone manual procedures and long workflows. In this paper, MSCNN model is proposed to solve automatically identify and classify images such as documents. First, the image data is preprocessed to enhance the image features. Then, the image is extracted by the cross-connect structure and multi-channel convolution. Finally, the image is classified by softmax layer. The experimental results on the dataset show that the proposed model has a high classification accuracy in image classification. (C) 2020 The Authors. Published by Elsevier B.V.

引用

页码：514 / 522

页数：9

共 23 条

[1]

Brito Carlos S. N., 2016, ARXIV160100701V1QBIO

[2]

Chan Tsung-Han, 2014, ARXIV14043606V2CSCV

[3]

Duan Jinbao, 2017, DOCUMENT IMAGE RECOG

[4]

Goodfellow I., 2013, ICML

[5]

Graham Benjamin, 2015, ARXIV14126071V4CSLG

[6]

Huang Ximei, 2012, RES TEXT IMAGE CLASS

[7]

Jiang Shasha, 2004, DESIGN IMPLEMENTATIO

[8] Has expansion of mobile phone and internet use spurred financial inclusion in the SAARC countries? [J].

Lenka, Sanjaya Kumar ;

Barik, Rajesh .

FINANCIAL INNOVATION, 2018, 4 (01)

[9]

Li L, 2017, PROC ASME DES ENG TE

[10]

[李翌昕 Li Yixin], 2019, [信号处理, Journal of Signal Processing], V35, P747

← 1 2 3 →