Design and analysis of efficient reconfigurable wavelet filters

Abstract

Abstract-Real-time image and multimedia processing applications such as video surveillance and telemedicine can have dynamic requirements of system latency, throughput, and power consumption. In this paper we discuss the design of reconfigurable wavelet filters for image processing applications that can meet such dynamic requirements. We generate several efficient hardware designs based on a derived family of bi-orthogonal 9/7 filters. An efficient folded and multiplier-free implementation of a 9/7 filter is obtained with the help of nine adders, which is a significant improvement over other existing approaches. We also propose an architecture that allows for on-the-fly switching between 9/7 and 5/3 filter structures. A performance comparison of these filters and their hardware requirements with other existing approaches demonstrates the suitability of our choice.

An Efficient Hardware Architecture for Multimedia Encryption and Authentication Using the Discrete Wavelet Transform

“…However, a fixed point implementation of the Our Design [7] [8] DWT leads to image reconstruction error and gives no security promise.…”

“…Some other desired features include low hardware cost, low power requirements and high throughput of the system. Recent research [7], [8] addresses these issues by choosing a simple DWT filter design with fewer adders and other hardware, thereby optimizing the hardware architecture for high performance. In [9], we provide a DWT-based architecture to enable real-time video-streaming applications such as those used in tele-medicine [10], remote laboratories [11], educational video streaming [12] and video surveillance.…”

“…In [9], we provide a DWT-based architecture to enable real-time video-streaming applications such as those used in tele-medicine [10], remote laboratories [11], educational video streaming [12] and video surveillance. The DWT filters presented in [7] give a polymorphic hardware support for the real-time requirements of multimedia applications. A summary of state-of-the-art implementations of the DWT on custom hardware is provided in the references [13], [14] and [15].…”

Polymorphic wavelet architectures using reconfigurable hardware

“…Tay [9] increases the number of freedom in original expression for Daubechies bi-orthogonal filter bank derivation and utilizes this to obtain expression for binary rational coefficients for 9/7 filters. A poly-DWT design is built over such rational coefficients filters obtained by a numerical study and analysis to achieve low quantization loss [10]. The filter coefficients are given in Table 1.We use this filter in this paper to illustrate some advantages of our Poly-DWT architecture.…”

“…In [10] we present the mathematics to reach at the coefficients for the Poly-DWT filter. We use those filters to reach the following relation: It is evident that we can develop a perfect reconstruction Poly-DWT filter with binary coefficients.…”