PSNR(Peak Signalto Noise Ratio):峰值信噪比
峰值信噪比(PSNR),一種評(píng)價(jià)圖像的客觀標(biāo)準(zhǔn)。它具有局限性,PSNR是
“PeakSignaltoNoiseRatio”的縮寫。peak的中文意思是頂點(diǎn)。而radio的意思是比率或比列的。整個(gè)意思就是到達(dá)噪音比率的頂
點(diǎn)信號(hào),psnr是一般是用于最大值信號(hào)和背景噪音之間的一個(gè)工程項(xiàng)目。通常在經(jīng)過(guò)影像壓縮之后,輸出的影像通常都會(huì)有某種程度與原始影像不一樣。為了衡
量經(jīng)過(guò)處理后的影像品質(zhì),我們通常會(huì)參考PSNR值來(lái)認(rèn)定某個(gè)處理程序夠不夠令人滿意。它是原圖像與處理圖像之間均方誤差相對(duì)于(2^n-1)^2的對(duì)數(shù)
值(信號(hào)最大值的平方,n是每個(gè)采樣值的比特?cái)?shù)),它的單位是dB。公式如下:
 |
| PSNR+10*log10((2^n-1)^2/MSE) |
PSNR=10*log10((2^n-1)^2/MSE)
其中,MSE是原圖像與處理圖像之間均方誤差。公式中的符號(hào)采用了MATLAB的用法。
Peak就是指8bits表示法的最大值255。MSE指MeanSquareError,I(角標(biāo)n)指原始影像第n個(gè)pixel值,P(角標(biāo)n)指經(jīng)處理后的影像第n個(gè)pixel值。PSNR的單位為dB。所以PSNR值越大,就代表失真越少。
PSNR是最普遍,最廣泛使用的評(píng)鑒畫質(zhì)的客觀量測(cè)法,不過(guò)許多實(shí)驗(yàn)結(jié)果都顯
示,PSNR的分?jǐn)?shù)無(wú)法和人眼看到的視覺品質(zhì)完全一致,有可能PSNR較高者看起來(lái)反而比PSNR較低者差。這是因?yàn)槿搜鄣囊曈X對(duì)于誤差的敏感度并不是絕
對(duì)的,其感知結(jié)果會(huì)受到許多因素的影響而產(chǎn)生變化(例如:人眼對(duì)空間頻率較低的對(duì)比差異敏感度較高,人眼對(duì)亮度對(duì)比差異的敏感度較色度高,人眼對(duì)一個(gè)區(qū)域
的感知結(jié)果會(huì)受到其周圍鄰近區(qū)域的影響)。
The phrase peak signal-to-noise ratio, often abbreviated PSNR, is an engineering term for the ratio between the maximum possible power of a signal and the power of corrupting noise
that affects the fidelity of its representation. Because many signals
have a very wide dynamic range, PSNR is usually expressed in terms of
the logarithmic decibel scale.
The PSNR is most commonly used as a measure of quality of reconstruction in image compression etc. It is most easily defined via the mean squared error (MSE) which for two m×n monochrome images I and K where one of the images is considered a noisy approximation of the other is defined as:
The PSNR is defined as:
Here, MAXI is the maximum pixel value of the image. When the pixels are represented using 8 bits per sample, this is 255. More generally, when samples are represented using linear PCM with B bits per sample, MAXI is
- 2B ? 1.
For color images with three RGB
values per pixel, the definition of PSNR is the same except the MSE is
the sum over all squared value differences divided by image size and by
three.
Typical values for the PSNR in image compression are between 30 and 40 dB.
峰值信噪比(經(jīng)常縮寫為PSNR)是一個(gè)表示信號(hào)最大可能功率和影響它的表示精度的破壞性噪聲功率的比值的工程術(shù)語(yǔ)。由于許多信號(hào)都有非常寬的動(dòng)態(tài)范圍,峰值信噪比常用對(duì)數(shù)分貝單位來(lái)表示。
峰值信噪比經(jīng)常用作圖像壓縮等領(lǐng)域中信號(hào)重建質(zhì)量的測(cè)量方法,它常簡(jiǎn)單地通過(guò)均方差(MSE)進(jìn)行定義。兩個(gè)m×n單色圖像I和K,如果一個(gè)為另外一個(gè)的噪聲近似,那么它們的的均方差定義為:
峰值信噪比定義為:
其中,MAXI是表示圖像點(diǎn)顏色的最大數(shù)值,如果每個(gè)采樣點(diǎn)用 8 位表示,那么就是 255。更為通用的表示是,如果每個(gè)采樣點(diǎn)用 B 位線性脈沖編碼調(diào)制表示,那幺 MAXI 就是
- 2B ? 1.
對(duì)于每點(diǎn)有RGB三個(gè)值的彩色圖像來(lái)說(shuō)峰值信噪比的定義類似,只是均方差是所有方差之和除以圖像尺寸再除以 3。
圖像壓縮中典型的峰值信噪比值在 30 到 40dB 之間。