透過您的圖書館登入
IP:3.129.92.57
  • 期刊

基於機器學習之車牌影像解析度增強技術

Learning-Based Super-Resolution for Car License Plate Images

摘要


由一張低解析度的車牌影像去辨識出車牌號碼是一件困難的事。本研究提出一種基於基底分類與基於機器學習法的車牌超解析度影像重建方法。我們的方法先將車牌影像中的單一字元切割出並投影至正交區域保留投影(OLPP)空間中,再使用貝氏分類器找出所屬的字元類別,再利用所定義的成本函數修正由貝氏分類器的錯誤分類結果,最後再經由類別判定的步驟得到每個字元最有可能的分類。根據輸入字符分類的結果,我們可以選擇最合適的基底集合進行高解析度字符影像的重建。最後將各個字元重建的結果合成為一張高解析度的車牌影像。

並列摘要


In this paper, we propose a method based on classified bases and example-based super-resolution to reconstruct the high-resolution details of a single low-resolution car license-plate image. The proposed method first uses the Bayesian classifier to classify individual characters of a license plate in the Orthogonal Locality Preserving Projections (OLPP) subspace. The proposed cost function in the refinement step then corrects the initial classification result to further improve the classification accuracy. Based on the refined classification result, in the final class decision step, the best basis set is determined to reconstruct the high-resolution image. Our experimental results show that the proposed method effectively improves the visual quality of reconstructed high-resolution license plate images.

參考文獻


Hsieh, P.L.(2010).Recognition of Blurred License Plate Images.Proceedings of the 2010 IEEE International Workshop on Information Forensics and Security.(Proceedings of the 2010 IEEE International Workshop on Information Forensics and Security).:
Park, J.S.,Lee, S.W.(2008).An Example-Based Face Hallucination Method for Single-Frame, Low-Resolution Facial Images.IEEE Transactions on Image Processing.17,1806-1816.
Sroubek, F.(2007).A Unified Approach to Superresolution and Multichannel Blind Deconvolution.IEEE Transactions on Image Processing.16,2322-2332.
Yang, J.C.(2008).Image Super-Resolution as Sparse Representation of Raw Image Patches.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.(Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition).:

延伸閱讀