ArtsComputer ScienceComputer VisionDigital ImagingInformation TheoryData CompressionDigital Image ProcessingDigital Signal ProcessingImage CompressionImage ProcessingLossy Data CompressionLossless Image CompressionLossy Source CodingSignal-to-noise RatioTexture CompressionWavelet CompressionWavelet-based CompressionWavelet-based FilteringWavelet-based Texture Analysis
When we compress a variety of images of different types using a fixed wavelet filter, it is seen that the peak signal-to-noise ratio (PSNR) values vary widely from image to image. This large variation in PSNR by as much as 30 dB, can mainly be attributed to a characteristic of the image known as Image Activity Measure (IAM). In this paper, we analyze a set of textures and images to determine the best measure of image activity. We show that such IAM is very effective in capturing the activities differentiating between various images. This IAM also links well with the PSNR value of the image in the lossy coding context. We establish this linkage in the form of an IAM-PSNR equation.
6
Adaptive wavelet filters in image coders-how important are they?