scholarly journals Border Handling for 2D Transpose Filter Structures on an FPGA

2018 ◽  
Vol 4 (12) ◽  
pp. 138 ◽  
Author(s):  
Donald Bailey ◽  
Anoop Ambikumar

It is sometimes desirable to implement filters using a transpose-form filter structure. However, managing image borders is generally considered more complex than it is with the more commonly used direct-form structure. This paper explores border handling for transpose-form filters, and proposes two novel mechanisms: transformation coalescing, and combination chain modification. For linear filters, coefficient coalescing can effectively exploit the digital signal processing blocks, resulting in the smallest resources requirements. Combination chain modification requires similar resources to direct-form border handling. It is demonstrated that the combination chain multiplexing can be split into two stages, consisting of a combination network followed by the transpose-form combination chain. The resulting transpose-form border handling networks are of similar complexity to the direct-form networks, enabling the transpose-form filter structure to be used where required. The transpose form is also significantly faster, being automatically pipelined by the filter structure. Of the border extension methods, zero-extension requires the least resources.

Author(s):  
K. Gugan ◽  
S. V. Saravanan

<p>In the field of Digital signal processing (DSP), the reduction of some logical elements counts is one of the main considerations. To minimize the area, computational delay, and power, the digital form FIR filter is to be implemented. The optimization of the ATP (Area, Time and Power) is achieved by using the efficient multiplication and accumulation unit (MAC). In this work, the direct form FIR filter with the efficient MAC unit is presented. At the initial stage, the half adders and full adders are to be modified by the reduction of the logical gates. The modified half and full adder are implemented in the Wallace tree multiplier for performing the efficient multiplication process. Carry save adder is divided into the two stages to reduce the computational delay of arithmetical operators. The proposed MAC design is implemented in the direct form FIR filter by using the HDL language.</p>


2013 ◽  
Vol 11 (1) ◽  
pp. 2175-2181
Author(s):  
Rajesh Mehra ◽  
Lajwanti Singh

In this paper, a decimator design has been presented for multirate digital signal processing.  The decimator design has been analysed and simulated for cost comparison in terms of multipliers and MPIS. Two structures  namely Transposed Direct form and Symmetric Direct form have been used performance and  resource consumption analysis. The decimators have been designed  & simulated using MATLAB. It can be observed from the simulated results that symmetric structure comsumes almost 50% less multipliers and MPIS compared to transposed structure. So the symmetric structure based decimator is suitable to provide cost effective solution


2019 ◽  
pp. 34-39 ◽  
Author(s):  
E.I. Chernov ◽  
N.E. Sobolev ◽  
A.A. Bondarchuk ◽  
L.E. Aristarhova

The concept of hidden correlation of noise signals is introduced. The existence of a hidden correlation between narrowband noise signals isolated simultaneously from broadband band-limited noise is theoretically proved. A method for estimating the latent correlation of narrowband noise signals has been developed and experimentally investigated. As a result of the experiment, where a time frag ent of band-limited noise, the basis of which is shot noise, is used as the studied signal, it is established: when applying the Pearson criterion, there is practically no correlation between the signal at the Central frequency and the sum of signals at mirror frequencies; when applying the proposed method for the analysis of the same signals, a strong hidden correlation is found. The proposed method is useful for researchers, engineers and metrologists engaged in digital signal processing, as well as developers of measuring instruments using a new technology for isolating a useful signal from noise – the method of mirror noise images.


Sign in / Sign up

Export Citation Format

Share Document