Landform Image Classification Based on Discrete Cosine Transformation and Deep Network

Fang Liu; Lixia Lu; Guangwei Huang; Hongjuan Wang; Xin Wang

doi:10.3788/AOS201838.0620001

Acta Optica Sinica, Volume. 38, Issue 6, 0620001(2018)

Landform Image Classification Based on Discrete Cosine Transformation and Deep Network

Fang Liu^*, Lixia Lu, Guangwei Huang, Hongjuan Wang, and Xin Wang

Author Affiliations

Faculty of Information Technology, Beijing University of Technology, Beijing 100022, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(13)

Fig. 1. (a) Original image and (b) energy distribution after DCT

Download full size

Fig. 2. Structure of CNN

Download full size

Fig. 3. Three-dimensional spectrum diagram. (a) DCT coefficient spectrum of original image; (b) spectrum after the coefficient selection

Download full size

Fig. 4. Structure of DCT-CNN model

Download full size

Fig. 5. Flow chart of landform image classification algorithm based on DCT and deep network

Download full size

Fig. 6. Example images in database. (a) UC Merced LU database; (b) UAV landing landform database

Download full size

Fig. 7. Classification performance of each method when the number of training samples is different. (a) UC Merced LU database; (b) UAV landing landform database

Download full size

Fig. 8. Image classification confusion matrix for UAV landing landform database

Download full size

Table 1. Layer parameters of DCT-CNN network structure

View table

Table 1. Layer parameters of DCT-CNN network structure

Layer	Type	Patch size	Stride	Zero padding	Output size
x	Input				128×128
h₁	Convolution	5×5	1	2	128×128×32
h₂	ReLU
h₃	Mean pooling	3×3	2		64×64
h₄	Convolution	3×3	2	0	32×32×32
h₅	ReLU
h₆	Max pooling	3×3	2		16×16
h₇	Convolution	7×7	1	2	14×14×64
h₈	ReLU
h₉	Max pooling	3×3	2		7×7
h₁₀	Convolution	7×7	1	0	1×1×64
h₁₁	ReLU
h₁₂	Convolution	1×1	1	0	1×1×10
o	SVM				n(class)

Table 2. Effect of different methods on classification of UC Merced LU database
View table
Table 2. Effect of different methods on classification of UC Merced LU database
Method Accuracy /% SD Training time /h
Method 1 84.25 0.78 0.8
Method 2 95.76 0.28 1.0
Method 3 92.83 0.52 3.3

Table 3. Effect of different methods on classification of UVA landing landform database
View table
Table 3. Effect of different methods on classification of UVA landing landform database
Method Accuracy/% SD Training time /h
Method 1 83.73 0.85 1.0
Method 2 94.38 0.34 1.3
Method 3 92.10 0.61 3.9

Table 4. Comparison of the classification accuracy of different methods for UC Merced LU database
View table
Table 4. Comparison of the classification accuracy of different methods for UC Merced LU database
Method Accuracy /% SD
RF 79.25 0.82
LDA-RF 82.92 0.69
CS-CNN^[5] 92.86 0.59
PSR^[15] 89.10 0.69
MS-DCNN^[16] 91.34 0.63
DCT-CNN 95.76 0.28

Table 5. Comparison of the classification accuracy of different methods for UAV landing landform database
View table
Table 5. Comparison of the classification accuracy of different methods for UAV landing landform database
Method Accuracy /% SD
RF 77.10 0.70
LDA-RF 80.23 0.74
CS-CNN^[5] 91.78 0.62
DCT-SAE^[12] 86.49 0.96
MS-DCNN^[16] 90.16 0.71
DCT-CNN 94.38 0.34

Tools

Get Citation

Copy Citation Text

Fang Liu, Lixia Lu, Guangwei Huang, Hongjuan Wang, Xin Wang. Landform Image Classification Based on Discrete Cosine Transformation and Deep Network[J]. Acta Optica Sinica, 2018, 38(6): 0620001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Optics in Computing

Received: Oct. 17, 2017

Accepted: --

Published Online: Jul. 9, 2018

The Author Email: Liu Fang (liufang@bjut.edu.cn)

DOI:10.3788/AOS201838.0620001

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Layer parameters of DCT-CNN network structure

Table 1. Layer parameters of DCT-CNN network structure

Table 2. Effect of different methods on classification of UC Merced LU database

Table 2. Effect of different methods on classification of UC Merced LU database

Table 3. Effect of different methods on classification of UVA landing landform database

Table 3. Effect of different methods on classification of UVA landing landform database

Table 4. Comparison of the classification accuracy of different methods for UC Merced LU database

Table 4. Comparison of the classification accuracy of different methods for UC Merced LU database

Table 5. Comparison of the classification accuracy of different methods for UAV landing landform database

Table 5. Comparison of the classification accuracy of different methods for UAV landing landform database