A Novel Hardware Solution for Efficient Approximate Fuzzy Image Edge Detection

In practical fuzzy applications, such as image processing, the utilization of precise models in hardware may not be the most efficient approach due to increased energy consumption and chip resource allocation. In a fuzzy system, an approximate implementation of min-max blocks offers an efficient solution with minimal accuracy compromise. Nevertheless, recent designs predominantly employ noncommercialized technologies for the fundamental fuzzy blocks. This article introduces a novel hardware solution for approximate fuzzy image edge detection using the well-established independent gate Fin field-effect transistor (FinFET) technology. The proposed hardware leverages two inference rules to identify edge pixels effectively. The fuzzy inference engine is implemented at the circuit level using 24 FinFETs, whereas the defuzzifier section incorporates four FinFETs with a configurable thresholding structure for optimal performance. Our circuit-level simulations reveal a remarkable 71% reduction in energy consumption compared with previous designs. The edge detection results are compared at the system level with the MATLAB Sobel edge detector. The proposed approximate hardware consistently matches the Sobel edge detection outcomes, exhibiting a 15% average improvements in data loss rate than other approximate structures. A figure of merit (FoM) is introduced to provide a comprehensive evaluation, considering both circuit and system-level metrics. The proposed FinFET-based hardware outperforms other approximate and even exact fuzzy edge detection hardware designs, boasting a 1.8 times higher FoM. This design paradigm exemplifies a promising direction toward compact and energy-efficient on-chip hardware implementations of real-world fuzzy systems.

I. Introduction

Decision-making is an inseparable cognitive process of human life. When we want to decide on complex problems, our brain thinks fuzzy instead of binary. Fuzzy logic is a powerful concept for solving ambiguous and uncertain problems because it emulates human decision-making [1], [2]. Fuzzy logic and systems have penetrated a diverse range of practical applications, from consumer electronics, and neural networks, to artificial intelligence, image processing, and environmental systems [3], [4], [5].