Various Generative Adversarial Networks Model for Synthetic Prohibitory Sign Image Generation
Source abstract
Abstract
A synthetic image is a critical issue for computer vision. Traffic sign images synthesized from standard models are commonly used to build computer recognition algorithms for acquiring more knowledge on various and low-cost research issues. Convolutional Neural Network (CNN) achieves excellent detection and recognition of traffic signs with sufficient annotated training data. The consistency of the entire vision system is dependent on neural networks. However, locating traffic sign datasets from most countries in the world is complicated. This work uses various generative adversarial networks (GAN) models to construct intricate images, such as Least Squares Generative Adversarial Networks (LSGAN), Deep Convolutional Generative Adversarial Networks (DCGAN), and Wasserstein Generative Adversarial Networks (WGAN). This paper also discusses, in particular, the quality of the images produced by various GANs with different parameters. For processing, we use a picture with a specific number and scale. The Structural Similarity Index (SSIM) and Mean Squared Error (MSE) will be used to measure image consistency. Between the generated image and the corresponding real image, the SSIM values will be compared. As a result, the images display a strong similarity to the real image when using more training images. LSGAN outperformed other GAN models in the experiment with maximum SSIM values achieved using 200 images as inputs, 2000 epochs, and size 32 × 32.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Image Processing Techniques · Generative Adversarial Networks and Image Synthesis · Image and Signal Denoising Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Information Management, Chaoyang University of Technology, Taichung 41349, Taiwan
Faculty of Information Technology, Satya Wacana Christian University, Salatiga 50711, Indonesia
School of Creative Technologies, the University of Portsmouth, Portsmouth PO1 2UP, UK
Funding
Ministry of Science and Technology, Taiwan
References (58)
Show source-provided references
1. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
2. ImageNet classification with deep convolutional neural networks10.1145/3065386 ↗
3. Dewi, C., Chen, R.C., and Liu, Y.-T. (2020, January 26–28). Taiwan Stop Sign Recognition with Customize Anchor. Proceedings of the ICCMS 20, Brisbane, QLD, Australia.10.1145/3408066.3408078 ↗
4. Selecting critical features for data classification based on machine learning methods10.1186/s40537-020-00327-4 ↗
5. Stallkamp, J., Schlipsing, M., Salmen, J., and Igel, C. (August, January 31). The German Traffic Sign Recognition Benchmark: A multi-class classification competition. Proceedings of the International Joint Conference on Neural Networks, San Jose, CA, USA.
6. Zhu, Z., Liang, D., Zhang, S., Huang, X., Li, B., and Hu, S. (2016, January 27–30). Traffic-Sign Detection and Classification in the Wild. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.232 ↗
7. Mogelmose, A., Trivedi, M.M., and Moeslund, T.B. (2012, January 11–15). Learning to detect traffic signs: Comparative evaluation of synthetic and real-world datasets. Proceedings of the Proceedings—International Conference on Pattern Recognition, Tsukuba, Japan.
8. Deep Learning Approach for Intelligent Intrusion Detection System10.1109/ACCESS.2019.2895334 ↗
9. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
10. Improved boundary equilibrium generative adversarial networks10.1109/ACCESS.2018.2804278 ↗
11. StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks10.1109/TPAMI.2018.2856256 ↗
12. Dewi, C., Chen, R.-C., and Liu, Y.-T. (2019, January 23–25). Similar Music Instrument Detection via Deep Convolution YOLO-Generative Adversarial Network. In Proceedings of the 2019 IEEE 10th International Conference on Awareness Science and Technology (iCAST), Morioka, Japan.10.1109/ICAwST.2019.8923404 ↗
13. Isola, P., Zhu, J.Y., Zhou, T., and Efros, A.A. (2017, January 21–26). Image-to-image translation with conditional adversarial networks. Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA.10.1109/CVPR.2017.632 ↗
14. Thermal to visible facial image translation using generative adversarial networks10.1109/LSP.2018.2845692 ↗
15. Median Filtered Image Restoration and Anti-Forensics Using Adversarial Networks10.1109/LSP.2017.2782363 ↗
16. Zhang, H., Goodfellow, I., Metaxas, D., and Odena, A. (2019, January 9–15). Self-attention generative adversarial networks. Proceedings of the 36th International Conference on Machine Learning, ICML, Long Beach, CA, USA.
17. Tai, S.-K., Dewi, C., Chen, R.-C., Liu, Y.-T., Jiang, X., and Yu, H. (2020). Deep learning for traffic sign recognition based on spatial pyramid pooling with scale analysis. Appl. Sci., 10.10.3390/app10196997 ↗
18. Integrating Gesture Control Board and Image Recognition for Gesture Recognition Based on Deep Learning
19. Traffic Sign Recognition Using a Multi-Task Convolutional Neural Network10.1109/TITS.2017.2714691 ↗
20. Radford, A., Metz, L., and Chintala, S. (2016, January 2–4). Unsupervised Representation learning with Deep Convolutional GANs. Proceedings of the International Conference on Learning Representations, San Juan, Puerto Rico.
21. Mao, X., Li, Q., Xie, H., Lau, R.Y.K., Wang, Z., and Smolley, S.P. (2017, January 22–29). Least Squares Generative Adversarial Networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.304 ↗
22. Arjovsky, M., Chintala, S., and Bottou, L. (2017, January 6–11). Wasserstein generative adversarial networks. Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, Australi.
23. Dwibedi, D., Misra, I., and Hebert, M. (2017, January 22–29). Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.146 ↗
24. Georgakis, G., Mousavian, A., Berg, A.C., and Košecká, J. (2017, January 12–16). Synthesizing training data for object detection in indoor scenes. Proceedings of the Robotics: Science and Systems, Cambridge, MA, USA.10.15607/RSS.2017.XIII.043 ↗
25. Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., and Krishnan, D. (2017, January 21–26). Unsupervised pixel-level domain adaptation with generative adversarial networks. Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA.10.1109/CVPR.2017.18 ↗
26. Dewi, C., Chen, R.-C., and Tai, S.-K. (2020). Evaluation of Robust Spatial Pyramid Pooling Based on Convolutional Neural Network for Traffic Sign Recognition System. Electronics, 9.10.3390/electronics9060889 ↗
27. Li, Q., Qu, H., Liu, Z., Zhou, N., Sun, W., Sigg, S., and Li, J. (2019). AF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization Systems. IEEE Transactions on Emerging Topics in Computational Intelligence, IEEE.
28. Abe, K., Iwana, B.K., Holmer, V.G., and Uchida, S. (2017, January 26–29). Font creation using class discriminative deep convolutional generative adversarial networks. Proceedings of the 4th Asian Conference on Pattern Recognition, ACPR 2017, Nanjing, China.10.1109/ACPR.2017.99 ↗
29. Du, Y., Zhang, W., Wang, J., and Wu, H. (2019, January 24–27). DCGAN based data generation for process monitoring. Proceedings of the 2019 IEEE 8th Data Driven Control and Learning Systems Conference, DDCLS 2019, Dali, China.10.1109/DDCLS.2019.8908922 ↗
30. The research of virtual face based on Deep Convolutional Generative Adversarial Networks using TensorFlow10.1016/j.physa.2019.01.036 ↗
31. Anas, E.R., Onsy, A., and Matuszewski, B.J. (2020, January 14–17). CT Scan Registration with 3D Dense Motion Field Estimation Using LSGAN. Proceedings of the Communications in Computer and Information Science, Chennai, India.10.1007/978-3-030-52791-4_16 ↗
32. Deep generative adversarial neural networks for compressive sensing MRI10.1109/TMI.2018.2858752 ↗
33. On the Effectiveness of Least Squares Generative Adversarial Networks10.1109/TPAMI.2018.2872043 ↗
34. Retinal optical coherence tomography image classification with label smoothing generative adversarial network10.1016/j.neucom.2020.04.044 ↗
35. Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities10.1007/s11263-019-01265-2 ↗
36. A 3D attention residual encoder–decoder least-square GAN for low-count PET denoising10.1016/j.nima.2020.164638 ↗
37. Sun, D., Yang, K., Shi, Z., and Chen, C. (2018, January 5–7). A new mimicking attack by LSGAN. Proceedings of the International Conference on Tools with Artificial Intelligence, ICTAI, Boston, MA, USA.10.1109/ICTAI.2017.00074 ↗
38. Study of Restrained Network Structures for Wasserstein Generative Adversarial Networks (WGANs) on Numeric Data Augmentation10.1109/ACCESS.2020.2993839 ↗
39. Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss10.1109/TMI.2018.2827462 ↗
40. Modeling EEG Data Distribution with a Wasserstein Generative Adversarial Network to Predict RSVP Events10.1109/TNSRE.2020.3006180 ↗
41. Multimodal Transformer with Multi-View Visual Representation for Image Captioning10.1109/TCSVT.2019.2947482 ↗
42. The 2015 super-resolution microscopy roadmap10.1088/0022-3727/48/44/443001 ↗
43. Assessment of structural similarity in CT using filtered backprojection and iterative reconstruction: A phantom study with 3D printed lung vessels10.1259/bjr.20160519 ↗
44. Image quality assessment: From error visibility to structural similarity10.1109/TIP.2003.819861 ↗
45. Deshmukh, A., and Sivaswamy, J. (2019, January 8–11). Synthesis of optical nerve head region of fundus image. Proceedings of the International Symposium on Biomedical Imaging, Venice, Italy.10.1109/ISBI.2019.8759414 ↗
46. Zhou, Y., Yu, M., Ma, H., Shao, H., and Jiang, G. (2019, January 28–30). Weighted-to-spherically-Uniform SSIM objective quality evaluation for panoramic video. Proceedings of the International Conference on Signal Processing Proceedings, ICSP, Weihai, China.10.1109/ICSP.2018.8652269 ↗
47. Mathieu, M., Couprie, C., and LeCun, Y. (2016, January 2–4). Deep multi-scale video prediction beyond mean square error. Proceedings of the 4th International Conference on Learning Representations, ICLR 2016—Conference Track Proceedings, San Juan, Puerto Rico.
48. A universal image quality index10.1109/97.995823 ↗
49. Weight analysis for various prohibitory sign detection and recognition using deep learning10.1007/s11042-020-09509-x ↗
50. A survey on Image Data Augmentation for Deep Learning10.1186/s40537-019-0197-0 ↗
51. Smart Augmentation Learning an Optimal Data Augmentation Strategy10.1109/ACCESS.2017.2696121 ↗
52. Gesture recognition based on CNN and DCGAN for calculation and text output10.1109/ACCESS.2019.2901930 ↗
53. Kim, S., Jang, J., and Kim, C.O. (2020). A run-to-run controller for a chemical mechanical planarization process using least squares generative adversarial networks. J. Intell. Manuf.10.1007/s10845-020-01639-1 ↗
54. Typical wind power scenario generation for multiple wind farms using conditional improved Wasserstein generative adversarial network10.1016/j.ijepes.2019.105388 ↗
55. DA-DCGAN: An Effective Methodology for DC Series Arc Fault Diagnosis in Photovoltaic Systems10.1109/ACCESS.2019.2909267 ↗
56. Data-driven modelling of nonlinear spatio-temporal fluid flows using a deep convolutional generative adversarial network10.1016/j.cma.2020.113000 ↗
57. Synthesizing Chest X-Ray Pathology for Training Deep Convolutional Neural Networks10.1109/TMI.2018.2881415 ↗
58. Turner, R., Hung, J., Frank, E., Saatci, Y., and Yosinski, J. (2019, January 9–15). Metropolis-Hastings generative adversarial networks. Proceedings of the 36th International Conference on Machine Learning, ICML 2019, Long Beach, CA, USA.