Jpeg Image Compression Using Discrete Cosine Transform - A Survey

Raid, A. M.; Khedr, Wael M.; El-Dosuky, M. A.; Ahmed, Wesam

doi:10.48550/arxiv.1405.6147

Cited by 7 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following it is showed a figure that represent various applications of a DCT on image: In Figure 1 it is possible see the differences of compressed images, the first image is the raw, the second has a 8 coefficients of compression and the last image has 64 coefficients of compression, more coefficients increase the percentage of compression and automatically increments the losing of information. Overtime are combined these two family but with minimal final result [7]. Any method explained till now has been developed in particular for images, after we introduce how to configure and use Re-Pair algorithm on images [8].…”

Section: Lossy Compression Methodsmentioning

confidence: 99%

A Study for Image Compression Using Re-Pair Text-based Algorithm

Luca¹,

Maria²,

Sannino³

et al. 2019

FSP

View full text Add to dashboard Cite

The compression is an important topic in computer science which allows we to storage more amount of data on our data storage. There are several techniques to compress any file. In this manuscript will be described the most important algorithm to compress images such as JPEG and it will be compared with another method to retrieve good reason to not use this method on images. So to compress the text the most encoding technique known is the Huffman Encoding which it will be explained in exhaustive way. In this manuscript will showed how to compute a text compression method on images in particular the method and the reason to choice a determinate image format against the other. The method studied and analyzed in this manuscript is the Re-Pair algorithm which is purely for grammatical context to be compress. At the and it will be showed the good result of this application.

show abstract

Section: Lossy Compression Methodsmentioning

confidence: 99%

A Study for Image Compression Using Re-Pair Text-based Algorithm

Luca¹,

Maria²,

Sannino³

et al. 2019

FSP

View full text Add to dashboard Cite

show abstract

“…At receiver, the reverse process is done according to Eq. 4, where F(U, V) and Q(U, V) represent the coefficient of frequency and quantization matrixes, respectively [19].…”

Section: Quantizationmentioning

confidence: 99%

A reliable image compression algorithm based on block luminance adopting deep learning for video surveillance application

Khairy

Al‐Makhlasawy

2022

Journal of Electrical Systems and Inf Technol

View full text Add to dashboard Cite

Video surveillance systems are essential as other application domain. Handling efficient and reliable for underground projects as well surveillance image is so significant to ensure security and safety. The wireless channels are efficient as data transferring media. On the other hand, the bandwidth may be limited for some environmental conditions. Hence, the image compression algorithm is very important to be conducted and applied to save the transmission bandwidth. This paper presents an image compression algorithm for video surveillance. The method is based on the concept of luminance variation of image. The image compression method is expected to achieve a reasonable compression ratio with acceptable quality. With another meaning, the compressed image size is decreased and consumes a smaller transmission bandwidth via the wireless channel compared with the original image size. The method adopts a deep learning approach to improve the quality with limited bandwidth. The proposed method is abbreviated as DLBL (deep learning block luminance). DLBL implemented and tested on some tested bed images. The performance of the proposed method is compared with some ones considering the same conditions. Some measurable criteria are taken into consideration for performance evaluation. The criteria are the compression ratio (CR), peak signal-to-noise ratio (PSNR) and structure similarity index measure (SSIM). From the experiments results, the proposed method showed significant and efficient performance compared with some other related ones. This is clear from the values of CR, PSNR and SSIM.

show abstract

“…One way to do convert pixel intensities to said representation is using the Discrete Cosine Transform (DCT). The DCT is an orthogonal linear mapping from the pixel domain to the frequency domain, DCT : x ∈ R ↦ → z ∈ R , and IDCT is its inverse [9,10]. Given a natural image x, DCT transforms the image into a representation in the frequency domain z = DCT(x) and IDCT transforms this representation back into the pixel domain x = IDCT(z).…”

Section: Images In the Frequency Domainmentioning

confidence: 99%

“…Given a natural image x, DCT transforms the image into a representation in the frequency domain z = DCT(x) and IDCT transforms this representation back into the pixel domain x = IDCT(z). We chose the DCT to transform perturbations into the frequency domain because it reduces distortions near the image boundary [9] better than the discrete Fourier transform does [10].…”

Section: Images In the Frequency Domainmentioning

confidence: 99%

Toward Few-step Adversarial Training from a Frequency Perspective

Wang

Cornelius

Martin

2020

Proceedings of the 1st ACM Workshop on Security and Privacy on Artificial Intelligence

View full text Add to dashboard Cite

We investigate adversarial-sample generation methods from a frequency domain perspective and extend standard ∞ Projected Gradient Descent (PGD) to the frequency domain. The resulting method, which we call Spectral Projected Gradient Descent (SPGD), has better success rate compared to PGD during early steps of the method. Adversarially training models using SPGD achieves greater adversarial accuracy compared to PGD when holding the number of attack steps constant. The use of SPGD can, therefore, reduce the overhead of adversarial training when utilizing adversarial generation with a smaller number of steps. However, we also prove that SPGD is equivalent to a variant of the PGD ordinarily used for the ∞ threat model. This PGD variant omits the sign function which is ordinarily applied to the gradient. SPGD can, therefore, be performed without explicitly transforming into the frequency domain. Finally, we visualize the perturbations SPGD generates and find they use both high and low-frequency components, which suggests that removing either high-frequency components or lowfrequency components is not an effective defense.

show abstract

Jpeg Image Compression Using Discrete Cosine Transform - A Survey

Cited by 7 publications

References 9 publications

A Study for Image Compression Using Re-Pair Text-based Algorithm

A Study for Image Compression Using Re-Pair Text-based Algorithm

A reliable image compression algorithm based on block luminance adopting deep learning for video surveillance application

Toward Few-step Adversarial Training from a Frequency Perspective

Contact Info

Product

Resources

About