Image Annotation Based on Convolutional Neural Network and Topic Model

Symbol	Meaning of symbol	Symbol	Meaning of symbol
M	Size of training set	N	Number of vocabulary
K	Number of topics	w	Vocabulary
z	Potential topic	θ	Proportion of topic
α	Parameter of model	β	Parameter of model
γ	Variational parameter α	φ	Variational parameter β
P_dir	Dirichlet distribution	Mult(·)	Polynomial distribution

Table 2. Parameters of different layers of CNN

View table

Table 2. Parameters of different layers of CNN

Type ofnetwork layer	K_f	F	S	P	D_f
conv1	96	11×11	4	0	55×55×96
Max-Pooling1	-	3×3	2	0	27×27×96
conv2	256	5×5	1	2	27×27×256
Max-Pooling2	-	3×3	2	0	13×13×256
conv3	384	3×3	1	1	13×13×384
conv4	384	3×3	1	1	13×13×384
conv5	256	3×3	1	1	13×13×256
Max-Pooling5	-	3×3	2	0	6×6×256

Table 3. Annotation results of different models on Corel5K
View table
Table 3. Annotation results of different models on Corel5K
Model Visual feature AP AR F1
PLSA-WORDS TVS 0.121 0.221 0.191
fc7 0.217 0.275 0.269
HGDM TVS 0.293 0.321 0.263
fc7 0.305 0.364 0.297
Proposed model fc7 0.380 0.490 0.420

Table 4. Annotation results of all image annotation models on common datasets

View table

Table 4. Annotation results of all image annotation models on common datasets

Model	Corel5K			IAPR TC-12
Model	AR	AP	F1	AR	AP	F1
MBRM	0.25	0.24	0.25	0.23	0.24	0.24
JEC	0.32	0.27	0.29	0.29	0.28	0.29
TagProp-ML	0.37	0.31	0.34	0.25	0.48	0.33
2PKNN	0.40	0.39	0.40	0.32	0.49	0.39
CNN-R	0.41	0.32	0.37	0.31	0.49	0.37
CNN-MSE	0.35	0.41	0.38	0.35	0.40	0.37
Proposed model	0.49	0.38	0.43	0.40	0.44	0.42

Tools

Get Citation

Copy Citation Text

Lei Zhang, Ming Cai. Image Annotation Based on Convolutional Neural Network and Topic Model[J]. Laser & Optoelectronics Progress, 2019, 56(20): 201004

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites