Bi-level image compression technique using neural networks

Sahami, Sadid; Shayesteh, Mahrokh G.

doi:10.1049/iet-ipr.2011.0079

Cited by 11 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to produce a trustworthy, effective image, they now employ a multipath routing approach. The previously compressed image was transferred to a single channel [23]. K. Rajkumar et al , offer a multiwavelet transform coding solution for lossless picture compression.…”

Section: In the Year 2010] Somasundaram And Vimala Suggested A New St...mentioning

confidence: 99%

Subject review: Image Compression Techniques

Amal Abbas Kadhim,

Wedad Abdul Khuder Naser,

Safana Hyder Abbas

2023

Global J. Eng. Technol. Adv.

View full text Add to dashboard Cite

show abstract

Section: In the Year 2010] Somasundaram And Vimala Suggested A New St...mentioning

confidence: 99%

Subject review: Image Compression Techniques

Amal Abbas Kadhim,

Wedad Abdul Khuder Naser,

Safana Hyder Abbas

2023

Global J. Eng. Technol. Adv.

View full text Add to dashboard Cite

show abstract

“…For evaluation of the compression rate, the total bit of the original image 24-bit with 512×512 pixel is divided by the average bit of compressed image. Generally, the compression rate before Huffman coding is computed as follows Equation 22 (Sahami and Shayesteh, 2012): Table 2. Average bit length of Huffman code of JPEG compression with QF = 50 and TMT image compression using an adaptive psychovisual threshold with QS = 0 JPEG image TMT image compression compression QF = 50 Table 3.…”

Section: Evaluation Measurementmentioning

confidence: 99%

Adaptive Tchebichef Moment Transform Image Compression Using Psychovisual Model

Ernawan

Abu

Suryana

2013

Journal of Computer Science

View full text Add to dashboard Cite

An extension of the standard JPEG image compression known as JPEG-3 allows rescaling of the quantization matrix to achieve a certain image output quality. Recently, Tchebichef Moment Transform (TMT) has been introduced in the field of image compression. TMT has been shown to perform better than the standard JPEG image compression. This study presents an adaptive TMT image compression. This task is obtained by generating custom quantization tables for low, medium and high image output quality levels based on a psychovisual model. A psychovisual model is developed to approximate visual threshold on Tchebichef moment from image reconstruction error. The contribution of each moment will be investigated and analyzed in a quantitative experiment. The sensitivity of TMT basis functions can be measured by evaluating their contributions to image reconstruction for each moment order. The psychovisual threshold model allows a developer to design several custom TMT quantization tables for a user to choose from according to his or her target output preference. Consequently, these quantization tables produce lower average bit length of Huffman code while still retaining higher image quality than the extended JPEG scaling scheme.

show abstract

“…Research on deep neural network compression has a long tradition [1]. Among many neural network compression techniques, a common method is to directly compress the input data, such as image compression [2][3][4][5] and video compression [6,7]. Another similar method is to directly compress the network parameters.…”

Section: Introductionmentioning

confidence: 99%

Fast CP‐compression layer: Tensor CP‐decomposition to compress layers in deep learning

Wang

2022

IET Image Processing

View full text Add to dashboard Cite

Deep neural network (DNN) shows its powerful performance in terms of image classification and many other applications. However, as the number of network layers increases, it brings huge pressure on devices with limited resources. In this article, a novel network compression algorithm is proposed that compresses the original network by up to about 60 times. In particular, a tensor Canonical Polyadic(CP) decomposition based algorithm is proposed to compress the weight matrix in the fully connected(FC) layer and the convolution kernel in the convolution layer. Traditional tensor decomposition algorithms are usually to first pre‐train the weights, and decompose the weights, finally perform fine‐tuning on the factors in the second training phase. Instead, the decomposed factors are directly updated by performing tensor CP decomposition on weight without fine‐tuning. The proposed algorithm is called Fast CP‐Compression Layer method in this paper. Experiments show that the proposed algorithm cannot only reduce computing time and improve compression factor but also improve accuracy on some datasets.

show abstract

Bi-level image compression technique using neural networks

Cited by 11 publications

References 23 publications

Subject review: Image Compression Techniques

Subject review: Image Compression Techniques

Adaptive Tchebichef Moment Transform Image Compression Using Psychovisual Model

Fast CP‐compression layer: Tensor CP‐decomposition to compress layers in deep learning

Contact Info

Product

Resources

About