IEEE International Conference on Image Processing

http://deic.uab.cat/~jbartrina/docs/articles/2009_09-BAS-ELSEVIER_CVIU-JPEG2000_ROI_Coding_Through_Component_Priority_for_Digital_Mammography.pdf

JPEG2000 ROI coding through component priority for digital mammography

Region of interest (ROI) coding is a mechanism deployed in several image coding systems to enable different degrees of coding priority to specific regions of the image. JPEG2000 standard provides two ROI coding methods. However, both of them are based in mechanisms that scale the quantized coefficients. This compels to encode the additional bit-planes needed for the scaling, causing a penalization in the overall coding performance, and the ROIs can not be modified without a complete re-encoding of the image. This paper introduces two ROI coding methods that use rate-distortion optimization techniques to prioritize arbitrary ROIs over the rest of the image without penalizing the overall coding performance. Experimental results suggest that the proposed methods achieve a close to optimal accuracy, improving the Implicit ROI coding method in terms of ROI rate distortion performance.

JPEG2000 Arbitrary ROI Coding through Rate-Distortion Optimization Techniques

The main contribution of this article is introducing an intelligent classifier to distinguish between benign and malignant areas of micro-calcification in companded mammogram image which is not proved or addressed elsewhere. This method does not require any manual processing technique for classification, thus it can be assimilated for identifying benign and malignant areas in intelligent way. Moreover it gives good classification responses for compressed mammogram image. The goal of the proposed method is twofold: one is to preserve the details in Region of Interest (ROI) at low bit rate without affecting the diagnostic related information and second is to classify and segment the micro-calcification area in reconstructed mammogram image with high accuracy. The prime contribution of this work is that details of ROI and Non-ROI regions extracted using multi-wavelet transform are coded at variable bit rate using proposed Region Based Set Partitioning in Hierarchical Trees (RBSPIHT) before storing or transmitting the image. Image reconstructed during retrieval or at the receiving end is preprocessed to remove the channel noise and to enhance the diagnostic contrast information. Then the preprocessed image is classified as normal or abnormal (benign or malignant) using Probabilistic neural network. Segmentation of cancerous region is done using Fuzzy C-means Clustering (FCC) algorithm and the cancerous area is computed. The experimental result shows that the proposed model performance is good at achieving high sensitivity of 97.27%, specificity of 94.38% at an average compression rate and Peak Signal to Noise Ratio (PSNR) of 0.5bpp and 58dB respectively.

/pdf/intelligent-detection-and-classification-of-vwzukknct4.pdf

Intelligent detection and classification of microcalcification in compressed mammogram image

Because of storage, transmission bandwidth, picture archiving, communication constraints and the limitations of the conventional compression methods, the medical imagery need to be compressed selectively to reduce the transmission time and storage costs while maintaining high diagnostic image quality. The contextual medical image compression (MIC) provides high spatial resolution and contrast sensitivity requirements for the diagnostic purpose. In this context, a novel approach called context modeling of medical image compression based on wavelet transform has been proposed in this work. In medical images, contextual region is an area which contains the most useful information and must be coded carefully without appreciable distortion. The proposed context based method yields significantly better compression rates with better image quality defined in terms of image quality metrics (IQM) than the general methods of compression. The experimental results have been tested on several ultrasound medical images and the obtained results have been compared with results of the standard methods namely general scaling, Maxshift, Implicit and EBCOT of selective image coding. It has been found that the proposed algorithm shows better and improved results defined in terms of IQM performance based on subjective and objective analysis as compared to the standard methods.

Dwt based context modeling of medical image compression

The IWT allows both lossy and lossless compression using a single bitstream. In this paper, a low-complexity, efficient embedded hybrid-coding algorithm so-called embedded subband partitioning block arithmetic coding (ESPBA) is presented. The new algorithm firstly selects a segmentation threshold based on the integer powers of two. All image coefficients above this threshold are encoded using simple quadtree partitioning scheme. The residual image coefficients below the threshold are encoded using block arithmetic coding based on context modeling. Experimental results show that ESPBA method has better PSNR performance than based-IWT SPIHT for lossy compression. The lossless compression performance of the presented method is comparable to JPEG-LS and SPIHT.

Embedded hybrid coding for lossy to lossless image compression using integer wavelet transform

Image compression based on region of interest (ROI) means to code the important regions in an image with high quality and to code other regions (Background-BG) with relatively low quality. Based on this idea, a flexible ROI image coding method called multiple bitplanes up-down shift (MBUShift) is presented. First, the new method divides all original bitplanes into three parts according to different importance of ROI and BG bitplanes. Second, the most significant ROI and BG bitplanes are shifted up, the least significant ROI and BG bitplanes are shifted down, and another bitplanes are not shifted. Third, the improved SPECK algorithm based on quadtree partitioning is applied for encoder and decoder. The unique characteristics of the new method lie in the combination of good ROI compression performance and low algorithm complexity. Experimental results indicate that the proposed method significantly outperforms the previous ROI coding schemes in overall ROI coding performance.

New Region of Interest Image Coding Based on Multiple Bitplanes Up-Down Shift Using Improved SPECK Algorithm

Efficient image storage and transmission is in great demand for remote sensing image community. The region of interest image coding in JPEG2000 offers a fast and efficient implementation for coding and transmitting remote sensing images. It allows ROIs of the image are of higher importance than background (BG). In this paper, a new and efficient scaling-based method so-called multiple bitplanes up-down shift (MBUShift) is described. The new method shifts up partial most significant bitplanes of ROI above the maximum BG bitplane and shifts down the partial least significant bitplanes of BG below the original minimum ROI bitplane. Then, the general significant bitplanes of ROI and BG coefficients are obtained in the original position. The experiments on remote sensing images show the presented method supports ROI coding of both arbitrary shape and arbitrary scaling without shape coding. Additionally, it can handle complexity multiple ROIs of arbitrary shapes efficiently.

New region of interest coding for remote sensing image based on multiple bitplanes up-down shift

Using the reversible biorthogonal integer wavelet transform (RB-IWT) for compression of image has many advantages. For example, through the use of appropriate techniques, a lossless decoding image can be reconstructed. This point is very significant for medical and remote sensing image processing. However, the RB-IWT has low lossy image compression efficiency. The main reason is the image coefficients of RB-IWT based have smaller dynamic change value and worse energy compaction than those by the discrete wavelet transform. In this paper, the optimal scaling factor (OSF) is proposed for the RB-IWT. The OSF optimizes the coefficient distribution of the image subbands. Experimental results show that the presented method based on the OSF has better lossy compression performance than the general IWT and is comparable to the Daubechies 9/7 wavelet filter.

Li-bao Zhang

Papers

Embedded hybrid coding for lossy to lossless image compression using integer wavelet transform

New Region of Interest Image Coding Based on Multiple Bitplanes Up-Down Shift Using Improved SPECK Algorithm

New region of interest coding for remote sensing image based on multiple bitplanes up-down shift

Efficient Embedded Image Compression Using Optimal Reversible Biorthogonal Integer Wavelet Transform