An improved image compression algorithm using binary space partition scheme and geometric wavelets

Frei-Chen bases based lossy digital image compression technique

In the big data era, image compression is of significant importance in today’s world. Importantly, compression of large sized images is required for everyday tasks; including electronic data communications and internet transactions. However, two important measures should be considered for any compression algorithm: the compression factor and the quality of the decompressed image. In this paper, we use Frei-Chen bases technique and the Modified Run Length Encoding (RLE) to compress images. The Frei-Chen bases technique is applied at the first stage in which the average subspace is applied to each 3 × 3 block. Those blocks with the highest energy are replaced by a single value that represents the average value of the pixels in the corresponding block. Even though Frei-Chen bases technique provides lossy compression, it maintains the main characteristics of the image. Additionally, the Frei-Chen bases technique enhances the compression factor, making it advantageous to use. In the second stage, RLE is applied to further increase the compression factor. The goal of using RLE is to enhance the compression factor without adding any distortion to the resultant decompressed image. Integrating RLE with Frei-Chen bases technique, as described in the proposed algorithm, ensures high quality decompressed images and high compression rate. The results of the proposed algorithms are shown to be comparable in quality and performance with other existing methods.

Wavelet compression of off-axis digital holograms using real/imaginary and amplitude/phase parts

Compression of digital holograms allows one to store, transmit, and reconstruct large sets of holographic data. There are many digital image compression methods, and usually wavelets are used for this task. However, many significant specialties exist for compression of digital holograms. As a result, it is preferential to use a set of methods that includes filtering, scalar and vector quantization, wavelet processing, etc. These methods in conjunction allow one to achieve an acceptable quality of reconstructed images and significant compression ratios. In this paper, wavelet compression of amplitude/phase and real/imaginary parts of the Fourier spectrum of filtered off-axis digital holograms is compared. The combination of frequency filtering, compression of the obtained spectral components, and extra compression of the wavelet decomposition coefficients by threshold processing and quantization is analyzed. Computer-generated and experimentally recorded digital holograms are compressed. The quality of the obtained reconstructed images is estimated. The results demonstrate the possibility of compression ratios of 380 using real/imaginary parts. Amplitude/phase compression allows ratios that are a factor of 2-4 lower for obtaining similar quality of reconstructed objects.

Research and improvement of ECG compression algorithm based on EZW

Embedded zerotree wavelet (EZW) is an efficient compression method that has advantages in coding, but its multilayer structure information coding reduces signal compression ratio. This paper studies the optimization of the EZW compression algorithm and aims to improve it. First, we used lifting wavelet transformation to process electrocardiograph (ECG) signals, focusing on the lifting algorithm. Second, we utilized the EZW compression coding algorithm, through the ECG information decomposition to determine the feature detection value. Then, according to the feature information, we weighted the wavelet coefficients of ECG (through the coefficient as a measure of weight) to achieve the goal of improved compression benefit.