Multi-scale Convolutional Neural Networks for Natural Scene License Plate Detection
We consider the problem of license plate detection in natural scenes using Convolutional Neural Network (CNN). CNNs are global trainable multi-stage architectures that automatically learn shift invariant features from the raw input images. Additionally, they can be easily replicated over the full input making them widely used for object detection. However, such detectors are currently limited to single-scale architecture in which the classifier only use the features extracted by last stage. In this paper, a multi-scale CNN architecture is proposed in which the features extracted by multiple stages are fed to the classifier. Furthermore, additional subsampling layers are added making the presented architecture also easily replicated over the full input. We apply the proposed architecture to detect license plates in natural sense images, and it achieves encouraging detection rate with neither handcrafted features nor controlling the image capturing process.
KeywordsLicense plate detection convolutional neural networks natural scene
Unable to display preview. Download preview PDF.
- 2.Frome, A., Cheung, G., Abdulkader, A., Zennaro, M., Wu, B., Bissacco, A., Adam, H., Neven, H., Vincent, L.: Large-scale Privacy Protection in Google Street View. In: Proc. of Int. Conf. on Computer Vision, pp. 2373–2380 (2009)Google Scholar
- 3.Matas, J., Zimmermann, K.: Unconstrained License Plate and Text Localization and Recognition. In: Proc. of Int. Conf. on Intelligent Transportation Systems, pp. 572–577 (2005)Google Scholar
- 4.Bai, H., Liu, C.: A Hybrid License Plate Extraction Method Based on Edge Statistics and Morphology. In: Proc. of Int. Conf. on Pattern Recognition, pp. 831–834 (2004)Google Scholar
- 6.Dlagnekov, L.: License Plate Detection using AdaBoost. Technical report, Computer Science and Engineering, San Diego (2004)Google Scholar
- 7.Zhang, H., Jia, W., He, X., Wu, Q.: Learning Based License Plate Detection Using Global and Local Features. In: Proc. of Int. Conf. on Pattern Recognition, pp. 1102–1105 (2006)Google Scholar
- 9.LeCun, Y., Huang, F.-J., Bottou, L.: Learning Methods for Generic Object Recognition with Invariance to Pose and Lighting. In: Proc. of Computer Vision and Pattern Recognition Conference, pp. 97–104 (2004)Google Scholar
- 11.Osadchy, M., LeCun, Y., Miller, M.: Synergistic Face Detection and Pose Estimation with Energy-Based Models. Journal of Machine Learning Research 8, 1197–1215 (2007)Google Scholar
- 12.Chen, Y.N., Han, C.C., Wang, C.T., Jeng, B.S., Fan, K.C.: The Application of a Convolution Neural Network on Face and License Plate Detection. In: Proc. of Int. Conf. on Pattern Recognition, pp. 552–555 (2006)Google Scholar
- 14.Sermanet, P., LeCun, Y.: Traffic Sign Recognition with Multi-Scale Convolutional Networks. In: Proc. of Int. Joint Conf. on Neural Networks, pp. 2809–2813 (2011)Google Scholar