2015
DOI: 10.1109/tcyb.2014.2360074
|View full text |Cite
|
Sign up to set email alerts
|

Evolutionary Multiobjective Image Feature Extraction in the Presence of Noise

Abstract: Abstract-A Pareto-based evolutionary multi-objective approach is adopted to optimize the functionals in the Trace Transform for extracting image features that are robust to noise and invariant to geometric deformations such as rotation, scale and translation (RST). To this end, sample images with noise and with RST distortion are employed in the evolutionary optimization of the Trace Transform, which is termed evolutionary Trace Transform with noise (ETTN). Experimental studies on a fish image database and the… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
39
0

Year Published

2015
2015
2024
2024

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 67 publications
(39 citation statements)
references
References 49 publications
0
39
0
Order By: Relevance
“…Albukhanajer et al [31] proposed a multi-objective approach to extracting image features that are robust to noise and invariant to geometric deformations, e.g., illumination, rotation, and scale, by optimizing the functionals in the trace transform 1 . In this method, the system automatically combines different trace, diametric, and "circus functionals" in order to minimise the within-class variance and maximise the betweenclass variance.…”
Section: B Related Workmentioning
confidence: 99%
“…Albukhanajer et al [31] proposed a multi-objective approach to extracting image features that are robust to noise and invariant to geometric deformations, e.g., illumination, rotation, and scale, by optimizing the functionals in the trace transform 1 . In this method, the system automatically combines different trace, diametric, and "circus functionals" in order to minimise the within-class variance and maximise the betweenclass variance.…”
Section: B Related Workmentioning
confidence: 99%
“…By removing irrelevant and redundant features, feature selection can reduce the dimensionality of the data, speed up the learning process, simplify the learned model, and/or increase the performance [1], [2]. Feature construction (or feature extraction) [3]- [5], which can also reduce the dimensionality, is closely related to feature selection. The major difference is that feature selection selects a subset of original features while feature construction creates novel features from the original features.…”
Section: Introductionmentioning
confidence: 99%
“…Over the past few decades, utilising GP for image related problems has attracted increasing interest [19,1]. Two GP methods have been developed by Song et al [21] for multiclass texture classification by utilising the Static Range Selection (SRS) [22,30] and Dynamic Range Selection (DRS) [13] techniques.…”
Section: Introductionmentioning
confidence: 99%
“…On the contrary, Hindmarsh et al [7] used GP as a postprocessing step to select a subset of the features detected by SIFT for object recognition. Recently, Albukhanajer et al [1] adopted a multiobjective approach in conjunction with the trace transform to extract image features that are robust to noise and invariant to different geometric deformations.…”
Section: Introductionmentioning
confidence: 99%