Learning a Single Tucker Decomposition Network for Lossy Image Compression With Multiple Bits-per-Pixel Rates


A common problem in Image Processing is lossy image compression (LIC), which seeks to use inexact approximations to reduce the size of an image. An encoder-quantizer-decoder network can be learned using deep convolutional neural networks (CNNs) from a vast amount of data. CNN-based LIC approaches, on the other hand, can only train a network to handle a particular number of pixels per bit-per-pixel (bpp). In practical LIC applications, a "one network per bpp" problem restricts CNNs' generality and flexibility. LIC at several bpp rates can be learned from a single CNN in this work. Decomposing a latent picture representation into a series of projection matrixes and an essential core tensor is accomplished using a novel Tucker Decomposition Layer (TDL). Latent image representation in CNNs can be easily manipulated by modifying the core tensor rank and its quantization. A coarse-to-fine training technique is also introduced to recreate the decompressed pictures, using an iterative non-uniform quantization scheme. TDNet's PSNR and MS-SSIM indices have been extensively tested to demonstrate its state-of-the-art compression capability.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE :Efficient and Accurate Measurement of Absorption Cross Section of a Lossy Object in Reverberation Chamber Using Two One-Antenna MethodsABSTRACT:The averaged absorption cross section of a lossy object can be measured
PROJECT TITLE :On Lossy Source Coding With Side Information Under the Erasure Distortion MeasureABSTRACT:We have a tendency to contemplate the Wyner–Ziv and 2 means source coding issues with the erasure distortion live. We tend
PROJECT TITLE :A Delay-Rational Model of Lossy Multiconductor Transmission Lines With Frequency-Independent Per-Unit-Length ParametersABSTRACT:Cables, printed circuit boards, and VLSI interconnects are commonly modeled as multiconductor
PROJECT TITLE :Antenna Current Optimization for Lossy Media With Near-Field ConstraintsABSTRACT:Optimization of the present distribution is used to analyze how little antennas are plagued by amplitude constraints on the close
PROJECT TITLE :Maximum Aperture Power Transmission in Lossy Homogeneous MattersABSTRACT:We tend to apply array signal processing techniques to the transmitting aperture field modes so as to determine the optimal field distribution

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry