Author Affiliations
College of Electrics and Information, Xi'an Polytechnic University, Xi'an, Shaanxi 710048, Chinashow less
Fig. 1. Examples of digital printing defects. (a) PASS tracks; (b) uneven inkjet; (c) ink leakage; (d) fabric wrinkles
Fig. 2. RGB color space histogram equalization processing results. (a) PASS tracks; (b) uneven inkjet; (c) ink leakage; (d) fabric wrinkles
Fig. 3. Gaussian filtering processing results. (a) PASS tracks; (b) uneven inkjet; (c) ink leakage; (d) fabric wrinkles
Fig. 4. Adjustment results of image resolution based on local mean algorithm. (a) Before resolution adjustment; (b) after resolution adjustment
Fig. 5. Image data enhancement results. (a) Original image; (b) flip vertically; (c) horizontal mirroring; (d) rotate 90°; (e) rotate 180°; (f) rotate 270°
Fig. 6. Flow chart of classification algorithm
Fig. 7. Topological structure of convolutional neural network
Fig. 8. Samples of digital printing defect data set. (a)--(d) PASS tracks; (e)--(h) uneven inkjet; (i)--(l) ink leakage; (m)--(p) fabric wrinkles
Fig. 9. Total loss rate curve
Fig. 10. Kappa coefficient value predicted by different CNN models
Type of defect | Cause of formation | Appearance shape | Probability of occurrence |
---|
PASS tracks | Nozzle clogging,motor step deviation | Narrow linear | High | Uneven inkjet | Uneven inkjet output debugging | Flat | Low | Ink leakage | Inkjet pressure instability | Dotted | Medium | Fabric wrinkles | Uneven cloth press | Strip | Low |
|
Table 1. Comparison of defect features in digital printing
Objective function | Accuracy/% |
---|
Softmax cross entropy | 98.14 | Classification cross entropy | 96.42 | Binary cross entropy | 81.29 | Mean square loss | 88.02 | Hinge loss | 74.92 | ROC AUC score | 77.33 |
|
Table 2. Classification accuracy corresponding to different objective functions
Optimization | Accuracy/% |
---|
Adaptive moment estimation | 98.21 | Stochastic gradient descent | 74.84 | Root mean square propagation | 65.38 | Momentum gradient descent | 92.73 | Adaptive sub-gradient method | 81.67 |
|
Table 3. Classification accuracy corresponding to different optimization algorithms
Defectclassification | Performance /% | Averageaccuracy /% | Standarddeviation |
---|
1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 |
---|
Validation set | 98.17 | 98.53 | 96.33 | 95.00 | 98.33 | 96.17 | 95.61 | 98.41 | 95.27 | 96.18 | 96.80 | 0.0133 | Test set | PASS tracks | 92 | 94 | 89 | 95 | 85 | 93 | 86 | 90 | 88 | 91 | 90.30 | 0.0316 | Uneven inkjet | 94 | 98 | 97 | 96 | 91 | 89 | 92 | 92 | 93 | 90 | 93.20 | 0.0286 | Ink leakage | 98 | 100 | 93 | 97 | 94 | 95 | 100 | 98 | 96 | 97 | 96.80 | 0.0223 | Fabric wrinkles | 100 | 93 | 96 | 95 | 98 | 96 | 97 | 94 | 95 | 94 | 95.80 | 0.0199 |
|
Table 4. Performance index of each defect classification
CNN model | LeNet5 | AlexNet | VGG16 | GoogLeNet | Proposed |
---|
Training/min | 76 | 92 | 114 | 136 | 65 | Testing/ms | 15 | 64 | 153 | 124 | 10 |
|
Table 5. Training and testing time of different CNN models