探索基于学习提升的转换结构,以实现完全可扩展和可访问的波形状图像压缩.
概括
这项研究将神经网络集成到波形状的变换中,用于图像压缩. 保持固定的提升步骤,并在熟练操作员中使用更多的道显著提高了性能,与JPEG 2000相比,节省了超过25%的比特率.
科学领域:
- 图像处理 图像处理
- 机器学习是机器学习.
- 信号处理 信号处理
背景情况:
- 传统的波形变换是图像压缩的基础.
- 神经网络为增强基于转换的压缩方法提供了潜力.
- 可扩展和可访问的图像压缩仍然是一个活跃的研究领域.
研究的目的:
- 综合研究神经网络的集成到基于提升的波形状变换.
- 评估各种网络架构和升级步骤配置对图像压缩性能的影响.
- 在图像压缩中为学习过的起重操作员确定最佳策略.
主要方法:
- 为熟练的起重操作员探索不同的起重步骤安排和神经网络架构.
- 分析参数,例如学习的升降步骤数量,道,层和内核支持.
- 研究两种适用于各种起重结构的通用培训方法.
主要成果:
- 从基本波量变换中保留固定升降步骤被证明是非常有利的.
- 增加学习的提升步骤和层并没有显著提高压缩性能.
- 在经验丰富的起重操作员中使用更多道带来了性能优势.
- 与JPEG 2000相比,提出的学习波形变换实现了超过25%的比特率节省.
结论:
- 固定的提升步骤对于有效的学习波形状变换至关重要.
- 对于压缩性能,网络深度 (层) 比通道宽度不那么重要.
- 开发的学习波形变换为图像压缩效率提供了显著的改进.
相关概念视频
Convolution Properties I
140
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
140
Fast Fourier Transform
273
The Fast Fourier Transform (FFT) is a computational algorithm designed to compute the Discrete Fourier Transform (DFT) efficiently. By breaking down the calculations into smaller, manageable sections, the FFT significantly reduces the computational complexity involved. Direct computation of an N-point DFT requires N2 complex multiplications, whereas the FFT algorithm needs only (N/2)log2N multiplications, offering a much faster performance.
The computational efficiency of the FFT becomes...
The computational efficiency of the FFT becomes...
273
Properties of Fourier series II
139
Time scaling of signals is a crucial concept in signal processing that affects the Fourier series representation without altering its coefficients. The process modifies the fundamental frequency, thereby changing how the series represents the signal over time. This principle is essential in various applications, including audio and image processing, where signal manipulation is frequent. Understanding function symmetries is fundamental to simplifying the Fourier series.
A function f(t) is...
A function f(t) is...
139
Convergence of Fourier Series
130
The Fourier series is a powerful mathematical tool for representing periodic signals as an infinite sum of complex exponentials. In practice, this infinite series is truncated to a finite number of terms, yielding a partial sum. This truncation makes the approximation of the signal feasible but introduces certain challenges, particularly near discontinuities, known as the Gibbs phenomenon.
The Gibbs phenomenon refers to the persistent oscillations and overshoots that occur near discontinuities...
The Gibbs phenomenon refers to the persistent oscillations and overshoots that occur near discontinuities...
130
Continuous -time Fourier Transform
299
The Fourier series is instrumental in representing periodic functions, offering a powerful method to decompose such functions into a sum of sinusoids. This technique, however, necessitates modification when applied to nonperiodic functions. Consider a pulse-train waveform consisting of a series of rectangular pulses. When these pulses have a finite period, they can be accurately represented by a Fourier series. Yet, as the period approaches infinity, resulting in a single, isolated pulse, the...
299
Convolution: Math, Graphics, and Discrete Signals
234
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
234


