Search

Computer technologies apply wildly in food area such as quality assurance and recognized. For this purpose, the extent of food should be segmented to process further. In this paper, a segmentation method is proposed to separate object from background combining thresholding with region-growing based methods First, the Region of interest (ROI) is detected by colour attributes. Secondly, the contrast gray image is computed from an optimal linear combination of the RGB colour components. Finally, the smooth-areas are gathered by region-growing method inside those objects. Simulation result shows that the proposed technique improves the quality assurance and recognized in terms of area and boundary mark more precisely. [ABSTRACT FROM AUTHOR]

The set partitioning in hierarchical trees (SPIHT) algorithm is an efficient method for lossy and lossless coding of natural image. This paper modified the original SPIHT algorithm, according to the characteristic that the wavelet coefficients of medical images are more centered on the low frequency than those of natural images. It is based on the idea of insignificant correlation of wavelet coefficient among the high frequency subbands respectively. In this scheme, the modified SPIHT proposes dictator to reduce the interband redundancy. Experimental results show that the proposed technique improves the quality of the reconstructed medical image in both PSNR and perceptual result when compare to JPEG2000 and original SPIHT at the same bit rate. [ABSTRACT FROM AUTHOR]

Blocking effect is the major drawbacks in DCT-based codec at low bit-rate. This kind of degradation probably will affect the judgment of a final user. In this paper, a powerful post-processing filter is proposed in DCT frequency domain. The proposed algorithm uses a shift block within four adjacent DCT blocks to reduce computational complexity. By slightly modifying several DCT coefficients in the shift block, the artifacts that result from quantized and de-quantized process are alleviated. In our simulation results, our scheme can take best quality in both objective and subjective metrics. [ABSTRACT FROM AUTHOR]