This thesis proposes an algorithm for automatically classifying a specific set of image quality (IQ) defects on noisy and mottled printed documents. A rough initial estimate of the defects' location i.e. defect detection is manually provided with a scanned image. The approach then proceeds to derive a more accurate segmentation by performing several image processing routines on the digital image. This reveals regions of interest from which discriminatory features are extracted. A classification of four defects is achieved via a customized tree classifier which employs a combination of size, shape and region attributes at corresponding nodes to yield appropriate binary decisions. Applications of this process include automated/assisted diagnosis and repair of printers or copiers in the field in a timely fashion. The proposed algorithm is tested on a database of 261 scanned images provided by Xerox Corporation and several synthetic defects yielding a 96.6% classification rate.
Library of Congress Subject Headings
Image processing; Imaging systems--Image quality; Printing--Data processing; Algorithms
Electrical Engineering (MS)
Department, Program, or Center
Electrical Engineering (KGCOE)
Ugbeme, Onome Augustine, "An Automated algorithm for the identification of artifacts in mottled and noisy images" (2006). Thesis. Rochester Institute of Technology. Accessed from
RIT – Main Campus