My main research fields are: mathematical morphology, color and multi- & hyper-spectral image processing as well as pattern recognition. The topics I am currently working on include:

8) Content based retrieval of remote sensing images
The proliferation of remote sensing images, in parallel with the advent of hyperspectral sensors, has rendered the development of content based indexing and retrieval solutions mandatory for this context. To achieve this goal, I work on the combination of deep learning and morphological content features. My work on this topic is supported by a Tubitak grant (1001).


Samples from Merced Dataset

7) Melt pond detection from sea-ice SAR and optical data
Global warming is taking its toll on the Arctic, with progressively less ice coverage every passing year. In order to better study this issue, marine scientists are interested in obtaining accurate sea ice size distributions. The melt ponds located on top of ice floes however constitute a serious obstacle with respect to this goal. In this context, I investigate and design methods of detecting melt ponds from SAR and optical sea-ice images. This work is being carried out in collaboration with the Scottish Association for Marine Science.


Optical sea-ice image

6) Hyper-spectral remote sensing image classification
With the widespread availability of both high spectral and high spatial resolution remote sensing images, several new application areas have emerged, such as sophisticated compound object detection and retrieval. Mathematical morphology being shape oriented per se, is highly suitable for processing images of high spatial resolution. Then again, the high number of bands (tens and often hundreds) constitutes a serious problem, since many of the existing image analysis methods do not lend themselves to multivariate data. In this context, we investigate methods for best applying morphological operators to hyperspectral images and focus specifically on tree representations (max-tree, alpha-tree, etc.). My work on this topic is supported by a career grant from Tubitak (3501).


False color version of the Pavia University dataset


Classification Map

5) Mitosis detection
We participated with colleagues from the South Brittany University (France) in the mitosis detection contest organized during the ICPR 2012 (Contest Website). The objective was to detect and recognize cells in mitosis in an effort to aid the automated prognosis of breast cancer. We worked both on color images (as seen below) as well as multispectral data. Out of the 129 participants only 17 submitted their results. Out of which we achieved the best 10th score using a purely automated solution; please note that most of the contestants relied on human assisted approaches.


Color microscopy image


Detection results


Actual mitosis cells

4) Texture classification
Texture classification or categorization is an important sub-topic of texture analysis with hundreds of solutions being available to this end. The main challenge is designing scale, rotation and illumination invariant features. With this purpose, besides several other experimentations, I have extended the classical definition of morphological covariance, so that it can outperform other widely used texture features such as LBP and MR8 with several publicly available texture collections. For more information:

3) Plant Identification
ImageCLEF has been organizing a plant identification track since 2011, where plant species are to be identified from various plant images: leaves, fruits, stems, branches, etc. During our collaboration with Sabanci University, I developed several morphology based content features and we participated in all occasions. We have achieved twice the 1st place (2012-13) and once the 2nd place (2016). For more information: PlantCLEF. Our work on this topic has been supported by a Tubitak grant (1001).


Examples from the 2016 dataset

2) Content-based Image Retrieval (CBIR)
The objective of CBIR, which constitutes the main application of my PhD, is to exploit images and more generally visual data using their visual content. Although some visual search engines have already reached the general public (e.g., their majority still index image files based on their filenames and textual meta data. Our ultimate aim is to carry out successfully the unsupervised annotation of a heterogeneous visual collection. Our work so far, has resulted in an engine called MIMAR (Morphological IMage Annotation and Retrieval), which using purely morphological features, is based on an architecture of keywords in order to implement content-based retrieval of still images. The system has led so far only to limited success using medium-sized image collections. Nonetheless, we have only begun to explore the potential of morphology for color indexation purposes.




Images to annotate


Keyword adding steps


Keyword adding interface




Retrieval results for "beach"

1) Color and multivariate mathematical morphology
Even though mathematical morphology provides a rich variety of tools and operators specializing particularly in the extraction of spatial structures, its application to color and more generally to multivariate images (e.g. multispectral, hyperspectral, etc) is highly problematic and still limited. Overcoming these limitations and extending morphology to color images has been the main topic of my PhD, and although we have introduced several novel approaches in this regard, our efforts will continue until we have obtained the ultimate color morphological solution.




Dilation of Lenna in the LSH space


Erosion of Lenna in the LSH space