Use this URL to cite or link to this record in EThOS:
Title: Automatic texture classification in manufactured paper
Author: Gatsheni, Barnabas Ndlovu
Awarding Body: University of Edinburgh
Current Institution: University of Edinburgh
Date of Award: 2001
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
The automatic classification of manufactured paper will form an important part of the paper making industry. Currently the human element plays a pivotal role in the quality assessment of manufactured paper. However, the inspection results can be unreliable as the performance of the human element can be affected by social pressures and fatigue among others. The system presented in this thesis replicates the actions of the human element in the quality assessment of manufactured paper and also expresses the subjective judgement for an objective figure of merit. This is achieved through the application of texture analysis in the characterisation of the surface appearance of paper for quality. However, texture analysis techniques individually can give unsatisfactory classification performance. This thesis has shown that the use of multiple features from different techniques in combination leads to enhanced classification performance over the use of features from any single method alone. Techniques from computer image analysis that were found useful for characterising the surface appearance quality for paper included the co-occurrence matrices, the grey level run length method, the specific perimeter method and first order statistics. A supervised neural network classifier was used for classification. The use of confusion matrices and the loss matrices to interpret the paper classification results is new. The results presented from paper appear promising and further work on other strategies that fuse information (extracted from samples of paper) together must improve the classification performance of this scheme.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available