基於局部學習對車牌影像超解析化
Abstract
由於監視攝影器材被廣泛地架設，視訊監控系統更顯得其重要性。這些攝影器材所儲存之視訊紀錄（Video Record）也常常變成警方辦案時重要之協助資源，藉由車牌辨識，可以找出違規車輛。為了節省成本，這些監視攝影機之解析度通常都不可能太高，加上監視器材通常被架設在路旁高處，監視器材與車子之間必然存在著相當大之距離；因此，超解析化可以讓原本太小而模糊不清之影像，將其放大而較不失真，可以看得更清楚，以利於後續之應用。
本論文先針對監視器之低解析度影像進行車牌擷取動作，接著再將取得之低解析度車牌進行超解析化之方法；本論文使用以學習為基礎之演算法，利用流形學習（Manifold Learning）之局部線性嵌入（Locally Linear Embedding, 簡稱LLE）概念，將輸入之低解析度車牌影像，經由事先取得一群高解析度及其對應低解析度之影像配對，藉由LLE之概念，從低解析度部分找出相似之局部幾何（Local Geometry），再利用其對應之高解析度部分，產生此輸入影像對應高解析度之模樣，組合成一張對應之高解析度車牌影像。
本論文提出之超解析化方法所產生的清楚車牌與使用一般放大方法在同樣放大倍率之下，細節上顯得更清楚及平滑。此外，此方法僅需使用單張影像即可，相較於傳統使用多張或連續影像，利用前後影像關係提升解析度之方法來得更快速及方便。
Surveillance camera equipment is mounted, video surveillance systems even more important. Video records are often turned into the police handling assistance resources through license plate recognition. License plate recognition (LPR) usually plays an important role in video surveillance systems. In order to save costs, the resolution of these surveillance cameras is usually not too high, the objective of super- resolution (SR) on license plate images is to enhance the resolution of those images. In this paper, we propose a learning-based SR approach on license plate images. First, several high-resolution (HR) license plate images and the generated corresponding LR ones are first collected as the training images. Next, the clustered HR and LR patch pairs are obtained from the training images. Then, license plates are extracted from a LR traffic surveillance image and cut into overlapped patches, and the clustered HR and LR patch pairs are used to generate the HR patch for each cut LR patch by using locally linear embedding (LLE) algorithm. Finally, the HR license plate images can be reconstruction. Preliminary experiments on realistic image data demonstrate the applicability of the proposed approach.
Surveillance camera equipment is mounted, video surveillance systems even more important. Video records are often turned into the police handling assistance resources through license plate recognition. License plate recognition (LPR) usually plays an important role in video surveillance systems. In order to save costs, the resolution of these surveillance cameras is usually not too high, the objective of super- resolution (SR) on license plate images is to enhance the resolution of those images. In this paper, we propose a learning-based SR approach on license plate images. First, several high-resolution (HR) license plate images and the generated corresponding LR ones are first collected as the training images. Next, the clustered HR and LR patch pairs are obtained from the training images. Then, license plates are extracted from a LR traffic surveillance image and cut into overlapped patches, and the clustered HR and LR patch pairs are used to generate the HR patch for each cut LR patch by using locally linear embedding (LLE) algorithm. Finally, the HR license plate images can be reconstruction. Preliminary experiments on realistic image data demonstrate the applicability of the proposed approach.
Description
Keywords
超解析化, 流形學習, 局部線性嵌入, 車牌偵測, super-resolution, manifold learning, locally linear embedding, license plate detection