Abstract
Anisotropic-diffusion is a commonly used signal preprocessing technique that allows extracting meaningful local characteristics from a signal, such as edges in an image and can be used to support higher-level processing tasks, such as shape detection. This paper presents a fully scalable CMOS-RRAM architecture of an edge-aware-anisotropic filtering algorithm aimed at computer vision applications. The CMOS circuitry controls the scale-space image data to perform pseudo-parallel in-memory computing and nonlinear processing through RRAM crossbar. The arithmetic operations for in-memory computation of brightness gradients are efficiently accumulated to produce the enhanced image in several iterations. The proposed architecture uses single RRAM as a computing and storage element to perform both arithmetic operations and accumulations. Thanks to the in-memory computation, memory accesses and arithmetic operations are reduced by 64% and 92%, respectively, compared to traditional digital implementations. This, in turn, results in a potential reduction of power and area costs of about 75% and 85%, respectively. The processing time is also reduced by 67%.
Highlights
In image processing and machine learning tasks the images must often be enhanced in a preprocessing phase – for instance to reduce noise and suppress undesired textures, while, at the same time, preserving and highlighting some other structures
The scale-space image is collapsed into a tree description, which is further refined by applying a stability criterion to spot features that persist over large changes in scale
Perona and Malik [3] – based on the observation that Gaussian smoothing can be considered as the result of a diffusion process [4], [5] – proposed an anisotropic diffusion approach: the location-dependent diffusion coefficient of the corresponding formulation is set to promote intra-region smoothing in preference to inter-region smoothing
Summary
In image processing and machine learning tasks the images must often be enhanced in a preprocessing phase – for instance to reduce noise and suppress undesired textures, while, at the same time, preserving and highlighting some other structures. Zayer et al.: RRAM Crossbar-Based In-Memory Computation of Anisotropic Filters output image To address this problem, Perona and Malik [3] – based on the observation that Gaussian smoothing can be considered as the result of a diffusion process [4], [5] – proposed an anisotropic diffusion approach: the location-dependent diffusion coefficient of the corresponding formulation is set to promote intra-region smoothing in preference to inter-region smoothing. The processing element, RRAM, acts as a nonlinear pixel-based resistive state transition that results in averaging and smoothing at the edges This yields to low power and efficient on-chip solution of the AD implementation for image enhancement. Work modules for RRAM-based in-memory computation of the local scale-space gradient changes, HW-friendly, spatial-edge-aware filter and nonlinear averaging for smoothing at the edge are described for image reconstruction and enhancement. 1: procedure Signal processing and pixel intensity data quantization 2: for grey image(N , M ) do
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
