Parallelizing Non-Neural ML Algorithm for Edge-based Face Recognition on Parallel Ultra-Low Power (PULP) Cluster

• Published in: Mediterranean Conference on Embedded Computing (New Jersey. Online) pp. 1 - 8
• Main Authors: Nagar, Mitul Sudhirkumar, Kumar, Rahul, Engineer, Pinalkumar
• Format: Conference Proceeding
• Language: English
• Published: IEEE 06.06.2023
• Subjects: Clustering algorithms; Costs; Eigenfaces; Face recognition; Inference algorithms; multi-core cluster; Multicore processing; PCA; Program processors; PULP; RISC-V processor; Training
• ISSN: 2637-9511
• DOI: 10.1109/MECO58584.2023.10154955

The multi-core parallel ultra-low power (PULP) cluster architecture allows the IoT edge node to shift toward near-sensor computing. In this paper, non-neural Eigenfaces-based face recognition (FR) is examined on an octa-core PULP cluster. It is possible to achieve high accuracy in the Eigenfaces-based algorithm without using a large data model. It is observed that the Eigenfaces-based face recognition algorithm achieved 93% accuracy on the PULP platform with a 4.55\times lesser model size compared to the state-of-the-art SqueezeNet1.1-based FR algorithm on GAP8 platform. Parallelization of Eigenfaces-based face recognition is done to achieve maximum speed-up on multi-core, reducing recognition time. Furthermore, DMA-based communication between the fabric controller and multi-core cluster reduces the recognition time by 50\times at the cost of a little degradation in speed-up on the multi-core. By adopting this technique, 165 faces per second are recognized with 93% accuracy on octa-core PULP cluster, which is 7.85\times faster than a single core RISC-V with DMA. Compared to the ARM Cortex-M7 architecture, the multi-core PULP cluster reduces recognition time by 89.89%. These results make the multi-core PULP cluster an efficient choice for Eigenfaces-based face recognition on the edge.