论文标题
使用固定小波变换，嗯和EM算法的边缘检测
Edge Detection using Stationary Wavelet Transform, HMM, and EM algorithm
论文作者
论文摘要
固定小波变换（SWT）是用于边缘分析的有效工具。本文提出了使用基于SWT的隐藏Markov模型（WHMM）的新的边缘检测技术，并提出了预期最大化（EM）算法。 SWT系数包含隐藏状态，它们指示SWT系数拟合到边缘模型中。 Laplacian和Gaussian模型用于检查状态的信息是边缘或没有边缘。该模型由EM算法训练，并采用Viterbi算法来恢复状态。该算法可以有效地应用于嘈杂的图像。
Stationary Wavelet Transform (SWT) is an efficient tool for edge analysis. This paper a new edge detection technique using SWT based Hidden Markov Model (WHMM) along with the expectation-maximization (EM) algorithm is proposed. The SWT coefficients contain a hidden state and they indicate the SWT coefficient fits into an edge model or not. Laplacian and Gaussian model is used to check the information of the state is an edge or no edge. This model is trained by an EM algorithm and the Viterbi algorithm is employed to recover the state. This algorithm can be applied to noisy images efficiently.
