Image Compression Using the Wavelet Transform on Textural Regions of Interest

This paper suggests a new image compression scheme, using the discrete wavelet transformation (DWT), which is based on attempting to preserve the texturally important image characteristics. The main point of the proposed methodology lies on that, the image is divided into regions of textural significance employing textural descriptors as criteria and fuzzy clustering methodologies. These textural descriptors include cooccurrence matrices based measures and coherence analysis derived features. While rival image compression methodologies utilizing the DWT apply it to the whole original image, the herein presented novel approach involves a more sophisticated scheme in the application of the DWT. More specifically, the DWT is applied separately to each region in which the original image is partitioned and, depending on how it has been texturally clustered, its relative number of the wavelet coefficients to keep is then, determined. Therefore, different compression ratios are applied to the above specified image regions. The reconstruction process of the original image involves the linear combination of its corresponding reconstructed regions. An experimental study is conducted to qualitatively assessing the proposed compression approach. Moreover, this experimental study aims at comparing different textural measures in terms of their results concerning the quality of the reconstructed image.