Usability-based Cross-Layer Reliability Evaluation of Image Processing Applications

Abstract

Image processing applications are today increasingly employed in safety-and mission-critical fields for perception tasks. It is therefore vital to analyse the reliability of the designed system before its deployment and, if necessary, to adopt specific hardening techniques. In this paper we propose a cross-layer reliability evaluation framework specifically meant for image processing applications accelerated onto SRAM-based FPGAs. The framework is based on two key concepts: i) an applicationlevel error simulation based on validated error models to speedup execution times, and ii) an analysis of the usability of the output images based on the working scenario. Such usability analysis allows the designer to study whether the downstream system would be able to take correct decisions even if the image processing outputs are corrupted. We applied the proposed idea on a motion detection application and we compared the achieved accuracy and the required execution times with the ones of a circuit-level fault injector, here considered as a ground truth. This experiment highlighted an accuracy comparable with the one of the fault injection with a dramatic time saving.

Measuring Effectiveness of Metamorphic Relations for Image Processing Using Mutation Testing

“…The effectiveness of MRs is determined through mutation testing. FDR depicted in Equation (1) shows the effectiveness of each MR. We have assessed the effectiveness of existing MRs (edge detection and dilation and erosion) and proposed MRs (dilation and erosion).…”

“…In the domain of computer graphics, the importance of Image Processing Applications (IPAs) is growing fast in our daily lives [1]. IPAs utilize algorithms to analyze the characteristics of an image using various methods and techniques.…”

“…Nowadays, IPAs are widely used in safety and mission-critical systems such as medical radiology, biometric systems, surveillance systems, etc. [1]. In medical radiology, machine learning and deep learning approaches are frequently used for automated diagnostics for patients using medical images such as MRI, CT Scan, ultrasound, etc.…”