Document Resizing Using a Multi-Layer Neural Network
Abstract:In this paper we present a resizing neural network for edge and detail preserving image interpolation. The multilayer neural network is trained by using pairs of high resolution and low resolution imagery. The high resolution is an 8-bit image scanned at 600 dpi. The low resolution image (300 dpi) is either a processed version of the high resolution image, or it is scanned independently. pixels are extracted from the low (high) resolution image and are used as inputs to the neural networks. The interpolated pixels obtained as output are compared with the high (low) resolution pixels after enhancement and the error is used to train the neural network.
Document Type: Research Article
Publication date: 2001-01-01
For more than 25 years, NIP has been the leading forum for discussion of advances and new directions in non-impact and digital printing technologies. A comprehensive, industry-wide conference, this meeting includes all aspects of the hardware, materials, software, images, and applications associated with digital printing systems, including drop-on-demand ink jet, wide format ink jet, desktop and continuous ink jet, toner-based electrophotographic printers, production digital printing systems, and thermal printing systems, as well as the engineering capability, optimization, and science involved in these fields.
Since 2005, NIP has been held in conjunction with the Digital Fabrication Conference.
- Information for Authors
- Submit a Paper
- Subscribe to this Title
- Membership Information
- Terms & Conditions
- Ingenta Connect is not responsible for the content or availability of external websites