Forgery Numeral Handwriting Detection Based on Fire Module Convolutional Neural Network

Layer name	Output size	Filter size/stride	s_1×1	e_1×1	e_3×3	Dimension
Input image	224×224×3
Conv1	54×54×96	11×11/4				34,944
Maxpool1	27×27×96	3×3/2
Fire2	27×27×256		32	128	128	44,320
Fire3	27×27×384		48	192	192	104,880
Fire4	27×27×384		48	192	192	111,024
Fire5	27×27×512		64	256	256	188,992
Maxpool5	13×13×512	3×3/2
Fire6	13×13×512		64	256	256	197,184
Conv7	15×15×256	1×1/1				131,328
Maxpool7	7×7×256	3×3/2
FC8	7×7×1000					12,545,000
FC9	1×1×2					2002

Table 2. Composition of dataset
View table
Table 2. Composition of dataset
Dataset 3 4 6 7 8 9
Normal handwriting 540 593 599 599 604 597
Forgery handwriting 621 612 616 614 600 614

Table 3. Classification and loss performances of number of neurons in fully connected layer
View table
Table 3. Classification and loss performances of number of neurons in fully connected layer
Parameter 500 1000 2000
Test accuracy /% 95.28 96.32 93.98
Loss value 0.14 0.11 0.25
Train time /min 13 13 14

Table 4. Results of training and testing of proposed network
View table
Table 4. Results of training and testing of proposed network
Forgerynumeral Trainaccuracy /% Lossvalue Testaccuracy /%
3 99.60 0.03 99.20
4 96.40 0.11 96.32
6 98.40 0.07 98.32
7 98.40 0.04 98.72
8 99.20 0.01 99.60
9 97.80 0.06 98.00

Table 5. Parameter comparison of FNNet and AlexNet
View table
Table 5. Parameter comparison of FNNet and AlexNet
Network Mean test accuracy /% Parameter quantity
AlexNet 95.35 58,289,538
FNNet 98.36 13,228,346

Tools

Get Citation

Copy Citation Text

Ying Chen, Shuhui Gao. Forgery Numeral Handwriting Detection Based on Fire Module Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221019

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites