1 / 16

Visual Features for Content-based Medical Image Retrieval

Visual Features for Content-based Medical Image Retrieval. Peter Howarth, Alexei Yavlinsky, Daniel Heesch, Stefan Rüger. http://km.doc.ic.ac.uk. Outline of presentation. CBIR Feature selection Texture Results and implications Conclusion. Relevance. 4521785. 3. feedback. Query.

deron
Télécharger la présentation

Visual Features for Content-based Medical Image Retrieval

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Visual Features for Content-based Medical Image Retrieval Peter Howarth, Alexei Yavlinsky, Daniel Heesch, Stefan Rüger http://km.doc.ic.ac.uk

  2. Outline of presentation • CBIR • Feature selection • Texture • Results and implications • Conclusion

  3. Relevance 4521785 3 . feedback . . Query 4521785 3 k - nn Feature (boost, VSM) Σ wD generation Retrieved Weighted Distances Test 4521785 3 results sum of . . data . distances 4521785 3 Feature vectors A CBIR system

  4. The task • Medical image collection, 8725 images, 25 single image queries • No training data • 1st stage, automatic visual query

  5. Feature choice • Dataset • High proportion monochrome • Precisely composed • Textures and structural elements • Layout • Thumbnail • Structural features • Convolution • Colour structure descriptor • Texture features • Co-occurrence • Gabor • Tiling

  6. What is texture? • Can it be defined? • Contrast, coarseness, fineness, direction, line-likeness, polarization, scale… • Regional property • How can these visual characteristics be captured in a feature?

  7. Grey Level Co-occurrence Matrices • Haralick 1979 • GLCM is a matrix of frequencies at which 2 pixels separated by a vector occur in the image • Generate the GLCM and then extract features • Energy • Contrast • Entropy • Homogeneity

  8. Co-occurrence Horizontal vector Vertical vector Query

  9. Gabor Features • Turner 1986, Manjunath 1996 2000 • Gabor filters are defined by harmonic functions modulated by a Gaussian distribution • By varying the orientation and scale can detect edge and line features that characterize texture

  10. Gabor Query Scale Orientation

  11. Results

  12. Fusing features • Convex combination • W is the plasticity of the retrieval system

  13. Approaches to feature weighting • Relevance feedback • SVM metaclassifier • Find optimum weights for retrieving an image class • [Yavlinsky et al ICASSP 04] • NNk • Find the nearest neighbour for for a given weight set • [Heesch et al ECIR 04]

  14. NNk Browsing

  15. Conclusions • Gabor wavelet feature gave best retrieval performance for this test collection • Browsing approach is useful for image search • Next year… • Training data?

  16. Visual Features for Content-based Medical Image Retrieval Peter Howarth, Alexei Yavlinsky, Daniel Heesch, Stefan Rüger http://km.doc.ic.ac.uk

More Related