Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks

Abstract

In this paper, we introduce deep learning technology to tackle two traditional low-level image processing problems, companding and inverse halftoning. We make two main contributions. First, to the best knowledge of the authors, this is the first work that has successfully developed deep learning based solutions to these two traditional low-level image processing problems. This not only introduces new methods to tackle well-known image processing problems but also demonstrates the power of deep learning in solving traditional signal processing problems. Second, we have developed an effective deep learning algorithm based on insights into the properties of visual quality of images and the internal representation properties of a deep convolutional neural network (CNN). We train a deep CNN as a nonlinear transformation function to map a low bit depth image to higher bit depth or from a halftone image to a continuous tone image. We also employ another pretrained deep CNN as a feature extractor to derive visually important features to construct the objective function for the training of the mapping CNN. We present experimental results to demonstrate the effectiveness of the new deep learning based solutions.

12 pages

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Understanding Neural Networks Through Deep Visualization
• Learning Deconvolution Network for Semantic Segmentation
• Texture Synthesis Using Convolutional Neural Networks
• Holistically-Nested Edge Detection
• Learning Representations for Automatic Colorization

Cited by in corpus (7)

• A Little Bit More: Bitplane-Wise Bit-Depth Recovery
• Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
• HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization
• Deep Attentive Generative Adversarial Network for Photo-Realistic Image De-Quantization
• Inverse Halftoning Through Structure-Aware Deep Convolutional Neural Networks
• TRLG: Fragile blind quad watermarking for image tamper detection and recovery by providing compact digests with quality optimized using LWT and GA
• Layer Decomposition Learning Based on Gaussian Convolution Model and Residual Deblurring for Inverse Halftoning