Evaluating the performance of a thresholding filter on handwritten images classification task
Abstract
In this paper we evaluate the effect of a thresholding filter on the accuracy and training times of a deep neural network. The filter increases the brightness of each pixel in the input image and then applies a threshold condition that zeroes out values exceeding a preset value. Although the filter is lossy, we demonstrate improved learning performance under some use cases.
Downloads
Issue
Building bridges and exploring frontiers
6-9 June 2018, Puerto Princesa City
Please visit the activity webpage for SPP2018 for more information on this year's conference.