Research

Speaker: Vivek Sharma, doctoral candidate at Karlsruhe Institute of Technology, Karlsruhe, Germany,

Abstract:

  • Part 1: Image enhancement using visible (RGB) and near-infrared (NIR) image data has been shown to enhance useful details of the image. While the enhanced images are commonly evaluated by observers' perception, in this work, we rather evaluate it by quantitative feature evaluation. The proposed algorithm presents a new method to enhance the visible images using NIR information via edge-preserving filters, and also investigates which method performs best from an image features standpoint.
  • Part 2: Convolutional neural networks rely on image texture and structure to serve as discriminative features to classify the image content. Image enhancement techniques can be used as preprocessing steps to help improve the overall image quality and in turn improve the overall effectiveness of a CNN. Existing image enhancement methods, however, are designed to improve the perceptual quality of an image for a human observer. In this paper, we are interested in learning CNNs that can emulate image enhancement and restoration, but with the overall goal to improve image classification and not necessarily human perception. To this end, we present a unified CNN architecture that uses a range of enhancement filters that can enhance image-specific details via end-to-end dynamic filter learning.