Research Research Tools in Image Analysis and Processing

Search

Unsupervised Analysis and Restoration of Map Images
Dr. Eugene Ageenko, Dr. Alexey Podlasov

The problem

It has been shown that the best compression results for color line-art images can be achieved if the images are decomposed into binary semantic layers, which are consequently compressed. Semantic decomposition of the image is a challenging task. Semantic layers can be obtained from corresponding color layers, which however lead to appearance of severe artefacts in place when information in one layer overlay another. A proper image restoration technique shall be therefore applied.

Illustrations

Color Raster Map Image:

Semantic Layers (as it should be):

Color layers showing artifacts (as result of the color separation process):

Semantic Layer Reconstruction

We have developed the technique to reconstruct the semantic layers from the color layers resulting from the image separation process. The proposed technique provides good visual quality of the reconstructed image layers, and can therefore be applied for selective layer removal/extraction, which is often necessary in map processing and analyzing applications. It improves the accuracy of the data analysis and measurement tasks. The technique requires few computation resources and can be successfully used in mobile computers and terminals.

Further reading

On the restoration of semantic features in raster topographic images (article in PDF)

Other articles on the topic can be found in Publications section.