目前基于小波變換的圖像壓縮方案比較普遍。而二維小波只是一維小波的張量積，基
函數(shù)的支撐區(qū)域由區(qū)間擴展為正方形，只有有限個方向。Contourlet 變換是一種圖像的多尺度幾何分析工具，能夠稀疏表示圖像，非線性逼近能力很強，它的基函數(shù)則具有方向性，各向異性。本文在分析了Contourlet 變換的基礎(chǔ)上，對變換后的重要系數(shù)和其位置進行了編碼。對標(biāo)準(zhǔn)圖像barbara 進行測試，實驗結(jié)果表明：基于Contourlet 變換的方案和基于小波變換的方案相比，峰值信噪比平均提高約0.5dB，且采用Contourlet 變換能夠較好地保留圖像中的紋理，圖像的主觀視覺質(zhì)量較好。
關(guān)鍵詞：圖像壓縮 Contourlet 小波變換
Abstract: The image compression method based on wavelet is used more widely nowadays. However, two dimensional wavelet is the tensor product of the one dimensional wavelet whose support region of basis function is extended from interval to square. It has only a few directions. Contourlet is a new image multiscale geometric analysis tool, which could represent image sparsely and has strong capability of nonlinear approximation. The basis function of contourlet is multi-directional and anisotropic. This paper analyzes the contourlet transform and coding the significant coefficients and its position. The standard test image Barbara is tested and experimental result shows that comparison with scheme based on wavelet the PSNR of the scheme using contourlet increases about 0.5dB and using contourlet could retains the texture of the image and get superior subject vision quality.
Key words: Image compression; Contourlet; Wavelet transform