Most neural networks for computer vision are designed to infer using RGB images. However,
these RGB images are commonly encoded in JPEG before saving to disk; decoding them …

The inverse identification of nonhomogeneous material properties from measured
displacement/strain fields, especially when noise exists, is crucial for both engineering and …

Convolutional neural networks (CNNs) learn filters in order to capture local correlation
patterns in feature space. In contrast, in this paper we propose harmonic blocks that produce …

The performance of cloud based image classification depends critically on its allocated
bandwidth. Traditional data compression methods can negatively impact classification …

Offloading tasks to the edge or the Cloud has the potential to improve accuracy of
classification and detection tasks as more powerful hardware and machine learning models …

This paper presents a fractional one-dimensional convolutional neural network (CNN)
autoencoder for denoising the Electroencephalogram (EEG) signals which often get …

Spectral representations have been introduced into deep convolutional neural networks
(CNNs) mainly for accelerating convolutions and mitigating information loss. However …

Convolutional neural networks (CNNs) are very popular nowadays for image processing.
CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context …

JPEG2000 (j2k) is a highly popular format for image and video compression. It plays a major
role in the rapidly growing applications of cloud based image classification. Considering …

A training method and a training apparatus for a neutral network for image recognition are
provided. The method includes: representing a sample image as a point set in a high …