Search

Image classification needs to consider the existence of image degradations in practice. Although degraded images have various levels of degradation, the degradation levels are usually unknown. This paper proposes a convolutional neural network to classify degraded images by using a restoration network and an ensemble learning. The proposed network can automatically infer ensemble weights by using estimated degradation levels of degraded images and features of restored images, where the degradation levels are estimated internally. The proposed network is mainly discussed with JPEG distortion, while degradations of both Gaussian noise and blurring are also examined. We demonstrate that the proposed network can classify degraded images over various levels of degradation. This paper also reveals how the image-quality of training data for a classification network affects the classification performance of degraded images. [ABSTRACT FROM AUTHOR]

This paper reports the effect of DC and pulse wave voltages on space charge characteristics of polyimide material for high-frequency insulation. The pulsed electroacoustic method is used to measure the charge distribution inside the material under the pulse wave voltages with different amplitudes, polarities, frequencies and duty ratios. Comparative results show that positive charge is more likely to accumulate inside the polyimide. The amount of accumulated charge under pulse wave voltages is larger than that under DC voltages. With frequency, more space charge is accumulated under negative pulse wave voltages with a frequency above 50 Hz, while it is not larger than 100 Hz under positive voltages. The maximum distortion of electric field appears under the negative pulse wave voltage with the frequency of 500 Hz, which is 1.19 times the applied field strength. When the duty ratio of the pulse wave voltage exceeds 50%, the distribution of accumulated charge tends to be stable. The research results can provide a reference for the practical application and modification design of polyimide materials in power electronic equipment. [ABSTRACT FROM AUTHOR]