Abstract
The alphabet computer recognition methods are widely applied in many areas. The clarity of the alphabet is first key step. This paper proposes a kind of image clarity algorithm for alphabet. The key frames in the surveillance video are analyzed in frequency domain to identify the key parameters causing alphabet illegibility and restore the surveillance video. The experiment results illustrate the algorithm can well restore the key frames of the alphabet in the video which can be widely applied in the vehicle plate recognition.
Publisher
Trans Tech Publications, Ltd.
Reference5 articles.
1. Gong Yonggang, sparse express license plate recognition algorithm based on local HOG features [J], the computer simulation, 2011, Vol. 28, NO. 4: 367-370.
2. Wei Gao, Haizhou Ai and Shihong Lao. Adaptive Contour Features in Oriented Granular Space for Human Detection and Segmentation[C]. In CVPR, 2009. 5.
3. John Wright, Allen Yang, Arvind Ganesh, Shankar Sastry and Yi Ma. Robust Face Recognitionvia Sparse Representation[C], in PAMI, (2008).
4. Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]. Proceedings of CVPR'05. San Diego: IEEE Computer Society, 2005. 886－993.
5. Zhang Guangjun. Visual measurement [M]. Beijing: science press, (2008).