Texture Images Classification Algorithm Combining Wavelet Transform and Capsule Network

Zhiyong Tao; jie Li; Xiaoliang Tang

doi:10.3788/LOP57.241002

Journals >Laser & Optoelectronics Progress >Volume 57 >Issue 24 >Page 241002 > Article

Laser & Optoelectronics Progress
Vol. 57, Issue 24, 241002 (2020)

Texture Images Classification Algorithm Combining Wavelet Transform and Capsule Network

Zhiyong Tao¹, jie Li^1、2、*, and Xiaoliang Tang²

Author Affiliations

¹School of Electronic Information Engineering, Liaoning Technical University, Huludao, Liaoning 125105, China

²Quanzhou Institute of Equipment Manufacturing Haixi Institutes, Chinese Academy of Sciences, Quanzhou, Fujian 362000, China

show less

DOI: 10.3788/LOP57.241002 Cite this Article Set citation alerts

Zhiyong Tao, jie Li, Xiaoliang Tang. Texture Images Classification Algorithm Combining Wavelet Transform and Capsule Network[J]. Laser & Optoelectronics Progress, 2020, 57(24): 241002 Copy Citation Text

show less

Fig. 1. Structure of matrix capsule network

Download full size

Fig. 2. Structure of wavelet capsule network

Download full size

Fig. 3. KTH data set

Download full size

Fig. 4. KTD data set

Download full size

Fig. 5. UIUC data set

Download full size

Fig. 6. Classification accuracies of DWTCapsNet on different texture data sets. (a) Train set; (b) test set

Download full size

Fig. 7. Visualization of DWTCapsNet output feature

Download full size

Fig. 8. Images after adding different levels of Gaussian noise

Download full size

Fig. 9. Classification accuracies of wavelet capsule network at different noise levels (KTH dataset)

Download full size

Layer	Output size	DWTCapsNet
Conv	64×64	kernel size: 7×7, stride: 2, with padding
DWT	32×32	wavelet decomposition
Dense block_1	32×32	$[\begin{array}{l} 1 \times 1 Conv \\ 3 \times 3 Conv \end{array}]$ ×6
Transition	32×32	kernel size: 1×1, stride: 1
Transition	16×16	2×2max pooling, stride: 2
Dense block_2	16×16	$[\begin{array}{l} 1 \times 1 Conv \\ 3 \times 3 Conv \end{array}]$ ×12
Reduce Channel	16×16	kernel size: 3×3, stride: 1, with padding
PrimaryCaps	pose: 16×16×128 activation: 16×16×8	kernel size: 1×1, stride: 1
ConvCaps	pose: 7×7×256activation: 7×7×16	kernel size: 3×3, stride: 2
Class Capsule	pose: E×16activation: E	kernel size: 1×1, stride: 1

Table 1. Structural parameter of wavelet capsule network

Data set	KTH	KTD	UIUC
Train set	3564	3136	700
Test set	1188	1344	300
Class	11	28	25
Type	color	gray	gray
Total number of images	4752	4480	1000

Table 2. Division of different data sets

Type	Model	KTH /%	KTD /%	UIUC /%	Reference
Traditional algorithm	LBP	89.3	97.8	88.1	Ref. [24]
	ILBP	96.9	99.7	91.9	Ref. [25]
	FLBP	94.3	99.2	91.3	Ref. [26]
	GPBMFD	--	--	90.30	Ref. [27]
	LQC	96.39	--	92.62	Ref. [28]
	SLGP	95.60	--	--	Ref. [29]
	LCCMSP	93.32	99.69	--	Ref. [30]
	LQPAT	83.76	96.92	--	Ref. [31]
CNN-based algorithm	T-CNN-3	99.4	73.2	--	Ref. [32]
	VisualNet	72.4	97.8	--	Ref. [33]
	VGG-VD-16	97.8	99.5	93.3	Ref. [11]
	Deep-TEN	84.5	--	--	Ref. [34]
	LFV	82.6	--	--	Ref. [35]
DWTCapsNet		99.92	99.79	91.74	ours

Table 3. Classification accuracies of different texture classification algorithms

Data set	KTH-color	KTH-gray
Accuracy	99.92	96.88

Table 4. Classification accuracies of DWTCapsNet on color and gray texture images unit: %

Data set	KTH	KTD	UIUC
DenseNet	98.20	99.66	87.07
DWTDenseNet	99.38	99.72	87.83

Table 5. Classification result of DWTDenseNet unit: %

Data set	KTH	KTD	UIUC
MatrixCapsNet	93.18	84.73	45.31
DenseCapsNet	93.91	99.01	88.12

Table 6. Classification result of DenseCapsNet unit: %

Rotation angle /(°)	Accuracy /%	Rotation angle /(°)	Accuracy /%	Rotation angle /(°)	Accuracy /%
0	99.71	120	41.26	240	41.26
30	67.25	150	57.10	270	50.99
60	44.60	180	96.66	300	43.11
90	51.27	210	64.27	330	62.00

Table 7. Classification accuracy of wavelet capsule network on rotating image data set

Zhiyong Tao, jie Li, Xiaoliang Tang. Texture Images Classification Algorithm Combining Wavelet Transform and Capsule Network[J]. Laser & Optoelectronics Progress, 2020, 57(24): 241002

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information