Title | ||
---|---|---|
An investigation into applying support vector machines to pixel classification in image processing |
Abstract | ||
---|---|---|
Support Vector Machines (SVMs) have been used successfully for many classification tasks In this paper, we investigate applying SVMs to classification in the context of image processing We chose to look at classifying whether pixels have been corrupted by impulsive noise, as this is one of the simpler classification tasks in image processing We found that the straightforward application of SVMs to this problem led to a number of difficulties, such as long training times, performance that was sensitive to the balance of classes in the training data, and poor classification performance overall We suggest remedies for some of these problems, including the use of image filters to suppress variation in the training data This led us to develop a two-stage classification process which used SVMs in the second stage This two-stage process was able to achieve substantially better results than those resulting from the straightforward application of SVMs. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1007/978-3-540-30549-1_13 | Australian Conference on Artificial Intelligence |
Keywords | Field | DocType |
support vector machine,support vector machines,image filter,training data,simpler classification task,straightforward application,classification task,image processing,two-stage process,long training time,poor classification performance,two-stage classification process,impulse noise | Training set,Pattern recognition,Computer science,Pixel classification,Support vector machine,Image processing,Artificial intelligence,Pixel,Contextual image classification,Image structure,Machine learning,Statistical analysis | Conference |
Volume | ISSN | ISBN |
3339 | 0302-9743 | 3-540-24059-4 |
Citations | PageRank | References |
0 | 0.34 | 7 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Douglas Clarke | 1 | 0 | 0.34 |
David Albrecht | 2 | 356 | 36.66 |
Peter Tischer | 3 | 0 | 0.34 |