Elisa Drelie Gelasca
Vision Research Lab.
Calendar
Categories
- Back <<
- Research
- Publications EPFL
- Publications UCSB
- Students
- Private
-
Highligths
Die Slowly
[..] He who becomes the slave of habit,
who follows the same routes every day,
who never changes pace,
who does not risk and change the color of his clothes,
who does not speak and does not experience,
dies slowly. [..]
Contact
Research
| BioImage Analysis |
| Biological images are critical components for a detailed understanding of the structure and functioning of cells and proteins. Image processing and analysis tools increasingly play a significant role in better harvesting this vast amount of data, most of which is currently analyzed manually and qualitatively. A number of image analysis tools have been proposed to automatically extract the image information. As the studies relying on image analysis tools have become widespread, the validation of these methods, in particular, segmentation methods, has become more critical. There have been very few efforts at creating benchmark datasets in the context of subcellular, cell and tissue imaging [read more] |
Related Papers: You can find all details concerning the method in the following papers:
|
| CBIR (Cortina) |
| Recent advances in processing and networking capabilities of computers have led to an accumulation of immense amounts of multimedia data such as images. One of the largest repositories for such data is the World Wide Web (WWW). We present Cortina, a large-scale image retrieval system for the WWW. Cortina v.3 indexes still over 10 Million images using image content, text and annotations At the systems level, the components of Cortina include building image collections using a Web crawler, collecting category information and keywords, and processing images to compute content descriptors. In this last version of Cortina the user has 4 options to start a search as shown in the Screen Shot on the right. Keyword query, to do a keyword or text search within the existing images, upload an image or insert the URL, browse images in the database randomly, or cluster to visualize images in its semantic clusters.[read more] |
Related Papers: You can find all details concerning the method in the following papers:
|
| 3D Watermarking Quality Assessemt |
One of the most important requirement of digital watermarking algorithms is imperceptibility. This requirement is particularly severe for watermarking of 3D objects where the visual quality of the original model has to be preserved, i.e. the visual aspect of the watermarked object should be the same of the original one. Several watermarking methods for still images and video exploit the knowledge of the Human Visual System (HVS) to obtain imperceptibility maximizing robustness. Since now, no similar techniques for watermarking of 3D objects exist. Here, we present a new experimental methodology for subjective evaluations of 3D objects and two perceptual metrics for quality assessment of watermarked 3D objects. Such metrics have been developed combining roughness estimation of model surface with psychophysical data collected by subjective experiments based on the proposed methodology. Such metrics can be useful for the evaluation and comparison of the perceptual artifacts introduced by 3D watermarking algorithms. The final aim of the evaluation is to minimize extraneous detail introduced by the watermarking by modulating the watermarking insertion in order to improve the visual quality of the watermarked model. Concerning comparison the performance of different 3D watermarking algorithms can be measured on the basis of the artifacts perceived on the 3D model.
|
Related Papers: You can find all details concerning the method in the following papers:
3DWPM is a tool to predict the human perception of geometric defects introduced by 3D watermarking algorithms on the model surface.
|
Video Object Segmentation Quality Assessemt
Segmentation of moving objects in image sequences plays an important role in video processing and analysis. Evaluating the quality of segmentation results is necessary
|
Experimental Results :
The expected segmentation quality for a given application can often be translated into requirements related to the shape precision and the temporal coherence of the objects to be produced by the segmentation algorithm. The setting up of a subjective experiment differs for each application.
Related Publications:
A graphical user interface is available to run the subjective tests. The inputs are the test video sequences in .avi format and a list (in txt. format) of the name of the test video sequences in the desired order in which they should be played. The outputs are .txt files with the corresponding annoyance value (a .txt file for each video sequence with as many annoyance values as the number of subjects who attended to the experiment). The software has been implemented in Microsoft Visual Basic 6.0. It has been tested under Windows XP.
|
