Visual data compression for multimedia applications

Ebrahimi, Touradj; Kunt, M.

doi:10.1109/5.687832

Cited by 42 publications

(17 citation statements)

References 110 publications

(96 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A possible alternative to KLT is the discrete cosine transform (performed via FFT), which yields performance similar to KLT [51] [45].…”

Section: Feed-forward Neural Compressormentioning

confidence: 99%

“…In particular, two international organizations (ISO/IEC and ITU-T) have been involved in the standardization of images, audio and video data. A complete overview of recent standards and trends in visual information compression is out of the scope of this work and can be found in [45][51] [52]. A brief summary is provided here for convenience of description.…”

Section: Review Of Recent Standardsmentioning

confidence: 99%

“…Video compression techniques have been classified into four main classes: waveform, object-based, model-based and fractal coding techniques [45].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Video Compression by Neural Networks

Vigliano

Parisi

Uncini

Intelligent Multimedia Processing With Soft Computing

View full text Add to dashboard Cite

Abstract. In this chapter a general overview of most common approaches to video compression is first provided. Standardization issues are briefly discussed and most recent neural compression techniques reviewed. In addition, a particularly effective novel neural paradigm is introduced and described. The new approach is based on a proper quad-tree segmentation of video frames and is capable to yield a considerable improvement with respect to existing standards in high quality video compression. Experimental tests are described to demonstrate the efficacy of the proposed solution.

show abstract

“…A possible alternative to KLT is the discrete cosine transform (performed via FFT), which yields performance similar to KLT [51] [45].…”

Section: Feed-forward Neural Compressormentioning

confidence: 99%

Section: Review Of Recent Standardsmentioning

confidence: 99%

See 1 more Smart Citation

Video Compression by Neural Networks

Vigliano

Parisi

Uncini

Intelligent Multimedia Processing With Soft Computing

View full text Add to dashboard Cite

show abstract

“…Even if accurate segmentation can be performed, there is the added problem of representing the images into constituent regions effectively and efficiently to meet the multiple requirements of compression, indexing and retrieval. Segmentation based image coding, also known as the second generation image coding, was once regarded as a very promising image compression method and was actively pursued by researchers in the 1980s [6]. However, its full potential was never realized due to the algorithmic and computer hardware limitations of the time.…”

Section: Introductionmentioning

confidence: 99%

“…Although it is possible to index images in the compressed domain of transform-based image coding, such as JPEG (DCT) [3] and Wavelet [4], the compressed image streams of these models are not directly usable and quite complicated processing is required to compute image features for image indexing and recognition purposes. To meet the new requirements, segmentation-based approach [5], or the "second generation" image coding [6], which divides image into meaningful regions, may provide a better solution than transform-based models. However, current state of the art computer visionhmage processing techniques are still not mature enough yet to ensure accurate segmentation of the images into meaningful regions (objects).…”

Section: Introductionmentioning

confidence: 99%

Constraint adaptive segmentation for color image coding and content-based retrieval

Qiu

2001 IEEE Fourth Workshop on Multimedia Signal Processing (Cat. No.01TH8564)

View full text Add to dashboard Cite

-We present a constraint adaptive image segmentation technique designed to achieve the combined purposes of color image coding/compression, indexing and content-based retrieval. An image is segmented into homogeneous squared regions of variable sizes such that it can be encoded very emciently [7]. From the segmented image, we derive an effective and efficient image content description feature termed the region and color co-occurrence matrix (RACOM) as image index for content-based indexing and retrieval. Experimental results are presented to demonstrate that RACOM is a very effective image content description features and has comparable performance to state of the art methods, colour correlogram [8] and MPEG7 colour structure histogram [9], in content-based image retrieval from large image databases.

show abstract