English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Neural networks became the standard technique for image classificationthroughout the last years. They are extracting image features from a largenumber of images in a training phase. In a following test phase, the network isapplied to the problem it was trained for and its performance is measured. Inthis paper, we focus on image classification. The amount of visual data that isinterpreted by neural networks grows with the increasing usage of neuralnetworks. Mostly, the visual data is transmitted from the application side to acentral server where the interpretation is conducted. If the transmission isdisturbed, losses occur in the transmitted images. These losses have to bereconstructed using postprocessing. In this paper, we incorporate the widelyapplied bilinear and bicubic interpolation and the high-quality reconstructionFrequency-Selective Reconstruction (FSR) for the reconstruction of corruptedimages. However, we propose to use Frequency-Selective Mesh-to-Grid Resampling(FSMR) for the joint reconstruction and resizing of corrupted images. Theperformance in terms of classification accuracy of EfficientNetB0, DenseNet121,DenseNet201, ResNet50 and ResNet152 is examined. Results show that thereconstruction with FSMR leads to the highest classification accuracy for mostnetworks. Average improvements of up to 6.7 percentage points are possible forDenseNet121.

Jointly Resampling and Reconstructing Corrupted Images for Image Classification using Frequency-Selective Mesh-to-Grid Resampling