Search

Genomic sequencing has become increasingly prevalent, generating massive amounts of data and facing a significant challenge in long-term storage and transmission. A solution that reduces the storage and transfer requirements without compromising data integrity is needed. The effectiveness of neural networks has already been endorsed in tasks like image and speech compression. Adapting them to recognize the intricate patterns in genomic sequences could help to find more redundancies and reduce storage requirements. The proposed method, called DNACoder, leverages deep learning techniques to achieve significant compression ratios while preserving the essential information in genomic data and offers a high-performance compression for genomic sequences in any data format. The results of the experiments clearly demonstrate the effectiveness of the method and its potential applications in genomic data storage. Our proposed method improves compression by 21.1% on bits per base compared to existing compressors on the benchmarked dataset. By using a deep learning prediction model that is structured as a convolutional layer followed by an attention-based long short-term memory network, we propose a novel lossless and reference-free compression approach (DNACoder), which can also be utilized as a reference-based compressor. The experimental outcome on the tested data illustrates that the advocated compression algorithm's CNN-LSTM model makes generalizations effectively for genomic sequence data and outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

A new lossless image compression scheme for natural color images which is based on double level Reversible Color Transform(RCT) and Bi-level Burrows Wheeler Compression Algorithm(BBWCA) is proposed. The first level RCT from RGB to HSV provide higher reduction in number of unique hue components, thus gives higher compression in case of natural images. The first level RCT followed by the second level RCT from HSV to YUV helps to yield small number of unique Y component values. DC level shifting and twos complement operation will be applied as preprocessing steps to second level RCT. The result of double level RCT is used as the input to BBWCA, in which row-wise BWT followed by column-wise BWT is applied. The compressed image data is formed by using move-to-front(MTF), Run-length-encoding and Entropy coding. The proposed method using double level RCT with BBWCA results in high compression by taking advantage of reduction in hue components of natural images. Among the different color space compared, the proposed method achieves better compression and is well suited for small and large size natural images. Proposed method make use of a double level RCT on the existing BBWCA algorithm and resulted in improving the compression ratio by 46 percentage. [ABSTRACT FROM AUTHOR]

In this paper a new approach of edge-based quantization for the compression of gray scale images using an Adaptive Block Truncation Coding technique (ABTC-EQ) is proposed, to improve the compression ratio (CR) with high picture quality. Quantization is done based on the edge information contained in each block of pixels of the image. Conventional BTC method retains the visual quality of the reconstructed image but it shows some artifacts near the edges. In conventional BTC and variants, same quantization is done for all pixel values with different block sizes so that CR is static for images with a fixed block size. But in the case of proposed method since the quantization is done based on the edge information, CR become dynamic and consequently achieves better visual quality with better CR. The experimental analysis based on subjective and quantitative analysis proved that the proposed method outperforms other BTC variants. [ABSTRACT FROM AUTHOR]

Super Resolution based on Compressed Sensing (CS) considers low resolution (LR) image patch as the compressive samples of its high resolution (HR) patch. Compressed sensing based image acquisition systems acquire less number of random linear measurements without first collecting all the pixel values. But using these compressive measurements directly to reconstruct the image causes quality issues. In this paper an image super-resolution method with two level sparsity based reconstruction via patch based image interpolation and dictionary learning is proposed. The first level reconstruction generates a low resolution image from random samples and the interpolation scheme used in this algorithm reduces the HR-LR patch coherency due to neighborhood issue which is a major drawback of single image super resolution algorithms. The dictionary based reconstruction phase generates the high resolution image from the low resolution output of the first level reconstruction phase. The experimental results proved that the proposed two level reconstruction scheme recovers more details of the image and yields improved results from very few samples (around 35-45%) than the state-of-the-art algorithms which uses low resolution image itself as input. The results are compared by considering both PSNR values and visual perception. [ABSTRACT FROM AUTHOR]

This paper describes a novel transform domain oblivious image watermarking method that combines Fuzzy-ART clustering and image normalization to design a watermarking system that is robust to any type of attacks like geometric attacks, jpeg compression, noise attacks and other image processing attacks. The use of Fuzzy ART clustering as a pre-processing step helps in the accurate selection of locations for watermark insertion so that the watermarked image is robust as well as perceptually invisible. The watermark is embedded adaptively using Just Noticeable Distortion (JND) mask that ensures the required quality for the watermarked image. The loss of synchronization in case of geometric attacks is corrected using image normalization technique that makes the watermark detectable even in the case of geometric attacks. Replicated copies of the binary watermark image are used to create a composite watermark that is scrambled using Arnold Transform which gives better reliability in extraction. Normalized Correlation (NC) is used as the verification metric. [ABSTRACT FROM AUTHOR]