EAML: ensemble self-attention-based mutual learning network for document image classification

2021 ◽  
Author(s):  
Souhail Bakkali ◽  
Zuheng Ming ◽  
Mickaël Coustaty ◽  
Marçal Rusiñol
Keyword(s):  
Image Classification ◽  
Document Image ◽  
Mutual Learning ◽  
Learning Network

Document Image Classification: Progress over Two Decades

2021 ◽  
Author(s):  
Li Liu ◽  
Zhiyu Wang ◽  
Taorong Qiu ◽  
Qiu Chen ◽  
Yue Lu ◽  
...  
Keyword(s):  
Image Classification ◽  
Document Image

Feature Learning for Footnote-Based Document Image Classification

2017 ◽  
pp. 643-650 ◽  
Author(s):  
Sherif Abuelwafa ◽  
Mohamed Mhiri ◽  
Rachid Hedjam ◽  
Sara Zhalehpour ◽  
Andrew Piper ◽  
...  
Keyword(s):  
Image Classification ◽  
Feature Learning ◽  
Document Image

scholarly journals Efficient and accurate document image classification algorithms for low-end copy pipelines

2016 ◽  
Vol 2016 (1) ◽  
Author(s):  
Wen-Hsiung Huang ◽  
Yung-Yao Chen ◽  
Pei-Yu Lin ◽  
Che-Hao Hsu ◽  
Kai-Lung Hua
Keyword(s):  
Image Classification ◽  
Document Image ◽  
Classification Algorithms

Document Image Classification Method Based on Graph Convolutional Network

2021 ◽  
pp. 317-329
Author(s):  
Yangyang Xiong ◽  
Zhongjian Dai ◽  
Yan Liu ◽  
Xiaotian Ding
Keyword(s):  
Image Classification ◽  
Document Image ◽  
Classification Method ◽  
Convolutional Network

scholarly journals Statistics Learning Network Based on the Quadratic Form for SAR Image Classification

2019 ◽  
Vol 11 (3) ◽  
pp. 282 ◽  
Author(s):  
Chu He ◽  
Bokun He ◽  
Xinlong Liu ◽  
Chenyao Kang ◽  
Mingsheng Liao
Keyword(s):  
Quadratic Form ◽  
Image Classification ◽  
Degrees Of Freedom ◽  
Image Interpretation ◽  
Sar Image ◽  
Statistical Features ◽  
Image Description ◽  
Linear Transformations ◽  
Sar Images ◽  
Learning Network

The convolutional neural network (CNN) has shown great potential in many fields; however, transferring this potential to synthetic aperture radar (SAR) image interpretation is still a challenging task. The coherent imaging mechanism causes the SAR signal to present strong fluctuations, and this randomness property calls for many degrees of freedom (DoFs) for the SAR image description. In this paper, a statistics learning network (SLN) based on the quadratic form is presented. The statistical features are expected to be fitted in the SLN for SAR image representation. (i) Relying on the quadratic form in linear algebra theory, a quadratic primitive is developed to comprehensively learn the elementary statistical features. This primitive is an extension to the convolutional primitive that involves both nonlinear and linear transformations and provides more flexibility in feature extraction. (ii) With the aid of this quadratic primitive, the SLN is proposed for the classification task. In the SLN, different types of statistics of SAR images are automatically extracted for representation. Experimental results on three datasets show that the SLN outperforms a standard CNN and traditional texture-based methods and has potential for SAR image classification.

Sign in / Sign up

Export Citation Format

Share Document