Pit Pattern Classification of Zoom-Endoscopic Colon Images using Histogram Techniques

Häfner, Michael; Kendlbacher, Ch.; Mann, William A.; Taferl, W.; Wrba, Friedrich; Gangl, Alfred; Vécsei, Andreas; Uhl, Andreas

doi:10.1109/norsig.2006.275276

Cited by 15 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, color channel information leads to even better results and is superior to luminance-channel based image processing, at least for our two classification problems. This is consistent with the results in [2], where information from three-dimensional color histograms led to the top classification results. Regarding the choice, which transform to choose, we favour the DT-CWT, since it is less computationally expansive than the Gabor Wavelet transform and leads to slightly better classification results.…”

Section: Resultssupporting

confidence: 91%

See 1 more Smart Citation

Multi-directional Multi-resolution Transforms for Zoom-Endoscopy Image Classification

Kwitt¹,

Uhl²

2007

Advances in Soft Computing

View full text Add to dashboard Cite

Summary. In this paper, we evaluate the discriminative power of image features, extracted from subbands of the Gabor Wavelet Transform and the Dual-Tree Complex Wavelet Transform for the classification of zoom-endoscopy images. Further, we incorporate color channel information into the classification process and show, that this leads to superior classification results, compared to luminance-channel based image processing.

show abstract

Section: Resultssupporting

confidence: 91%

“…Existing approaches in this research area include histogram-and 2-D DWT-based methods for pit-pattern classification [2,3] or classic video-endoscopy image classification by statistical second-order measures [10,5].…”

Section: Introductionmentioning

confidence: 99%

Multi-directional Multi-resolution Transforms for Zoom-Endoscopy Image Classification

Kwitt¹,

Uhl²

2007

Advances in Soft Computing

View full text Add to dashboard Cite

show abstract

“…In (Häfner et al, 2006a) several histogram-based techniques (e.g. : luminance histogram, color-channel histogram) are used to capture the characteristics of the pit-pattern types.…”

Section: Pit-pattern Classification -The Medical Perspectivementioning

confidence: 99%

Computer-assisted pit-pattern classification in different wavelet domains for supporting dignity assessment of colonic polyps

Häfner

Kwitt

Uhl

et al. 2009

Pattern Recognition

View full text Add to dashboard Cite

In this paper, we show that zoom-endoscopy images can be well classified according to the pit-pattern classification scheme by using texture-analysis methods in different wavelet domains. We base our approach on three different variants of the wavelet transform and propose that the color-channels of the RGB and LAB color model are an important source for computing image features with high discriminative power. Color-channel information is incorporated by either using simple feature vector concatenation and cross-cooccurrence matrices in the wavelet domain. Our experimental results based on k-Nearest Neighbor classification and forward feature selection exemplify the advantages of the different wavelet transforms and show that color-image analysis is superior to grayscale image analysis regarding our medical image classification problem.

show abstract

“…In recent work [4] we have found histogram-based techniques to be surprisingly well suited for our classification problem. This is quite surprising, since pit patterns seem to be more localized phenomena characterized by their respective shapes -however, the corresponding results still leave room for improvements.…”

Section: Feature Extraction: Co-occurrence Histogramsmentioning

confidence: 99%

“…Therefore, histogram intersection may be immediately used for k-NN classification and has turned out to give good results on simple histograms and wavelet-based features derived from zoom-endoscopic images in earlier work [5,4].…”

Section: Classificationmentioning

confidence: 99%

Comparison of k-NN, SVM, and NN in Pit Pattern Classification of Zoom-Endoscopic Colon Images using Co-Occurrence Histograms

Häfner¹,

Gangl²,

Wrba³

et al. 2007

2007 5th International Symposium on Image and Signal Processing and Analysis

Self Cite

View full text Add to dashboard Cite

show abstract

Pit Pattern Classification of Zoom-Endoscopic Colon Images using Histogram Techniques

Cited by 15 publications

References 9 publications

Multi-directional Multi-resolution Transforms for Zoom-Endoscopy Image Classification

Multi-directional Multi-resolution Transforms for Zoom-Endoscopy Image Classification

Computer-assisted pit-pattern classification in different wavelet domains for supporting dignity assessment of colonic polyps

Comparison of k-NN, SVM, and NN in Pit Pattern Classification of Zoom-Endoscopic Colon Images using Co-Occurrence Histograms

Contact Info

Product

Resources

About