SIMD-Constrained Lookup Table for Accelerating Variable-Weighted Convolution on x86/64 CPUs
Y Naganawa, H Kamei, Y Kanetaka, H Nogami… - IEEE …, 2024 - ieeexplore.ieee.org
Convolution is the inner product of the neighborhood signal and weights and plays a
fundamental role in image processing; thus, acceleration of convolution is essential. Among …
fundamental role in image processing; thus, acceleration of convolution is essential. Among …
Directional Ring Difference Filter for Robust Shape-from-Focus
K Ashfaq, MT Mahmood - Mathematics, 2023 - mdpi.com
In the shape-from-focus (SFF) method, the quality of the 3D shape generated relies heavily
on the focus measure operator (FM) used. Unfortunately, most FMs are sensitive to noise …
on the focus measure operator (FM) used. Unfortunately, most FMs are sensitive to noise …
Neural Network Accelerator Design for System on Chip
S Ammari - 2022 - trepo.tuni.fi
ML is vastly utilized in a variety of applications such as voice recognition, computer vision,
image classification, object detection, and plenty of other use cases. Protecting data privacy …
image classification, object detection, and plenty of other use cases. Protecting data privacy …
Hardware implementation of optimized LeNet-5
J Ju, C Liu - … on Computational Modeling, Simulation and Data …, 2022 - ieeexplore.ieee.org
Convolutional Neural Network (CNN), a feedforward neural network, is widely used in large-
scale machine learning tasks such as image recognition, image classification, and object …
scale machine learning tasks such as image recognition, image classification, and object …