My research focuses on the intersection of Artificial Intelligence, Computer Vision, and Robotics. My scientific interests lie in the following fields: visual feature extraction, image analysis, matching, indexing and retrieval, SLAM, control, and educational robotics.
Compact Composite Descriptors
The family of compact composite descriptors includes descriptors for 3 types of images. A group of 3 descriptors combines color and texture information to describe natural color images. You can read more details about CCDs and download the related libraries on this page. Read more…
SIMPLE Descriptors
SIMPLE utilizes global descriptors as local ones. They employ ROI detectors to define salient image patches of blob-like textures and use the MPEG-7 and CCDs descriptors to produce the final local features’ vectors. SIMPLE descriptors emphasize and incorporate the characteristics that allow a more abstract but retrieval-friendly description of the image’s salient patches. Read more…
img(Rummager)
img(Rummager) brings into effect several new and state-of-the-art descriptors. The application can execute an image search based on a query image, either from XML-based index files or directly from a folder containing image files, extracting the comparison features in real time. Read more…
Micro Flying Robots
sFly – Swarm of Micro-Flying Robots (FP7-ICT Robotics). Role in the project: Senior Researcher.
Precision Agriculture
Olive oil is one of the major agricultural products of the countries of the Mediterranean Basin. More than 70% of the world’s production is produced in Spain, Italy, and Greece. One of the main threats to olive production is pest infestation, which distracts the fruit of the olive tree. We have developed a holistic approach using embedded systems, GIS, and web-based applications to tackle the problem of successfully implementing bait sprays. Read More…
MMRetrieval.net
This web application presents a multimodal search engine, which allows multimedia and multi-language queries, and uses the total available information in a multimodal collection. Read more…
Image Retrieval Tools
You can find details regarding several open-source and freeware applications/libraries for Content-Based Image Retrieval on this page. Read more…
Enorasis Robot
Enorasis robot implements the first high-speed computer-vision-based line-tracking and following-control autonomous robot. Read More
Gradient Free Training of Artificial Neural Networks
This work presents a numerical scheme for the computation of Artificial Neural Networks’ weights without a laborious iterative procedure. The proposed algorithm adheres to the underlying theory, is highly fast, and results in remarkably low errors when applied for regression and classification of complex data sets, such as the Griewank function of multiple variables x∈R^100 with random noise addition and the MNIST database for handwritten digits recognition, with 7×10^4 images. Read More
Autonomous Underwater Systems
NOPTILUS – autoNomous, self-learning, OPTImal, and compLete Underwater Systems (FP7-ICT Robotics). Role in the project: Technical Scientific Manager
MPEG-7 Visual Descriptors
From this page, one can download an open-source implementation (in C#) of the Scalable Color Descriptor, Color Layout Descriptor, Dominant Colors Descriptor, and Edge Histogram Descriptor.
Read more…
STEM Education – Educational Robotics
Science, Technology, Engineering, and Mathematics (STEM) tools have been proven useful for teachers and students in many learning contexts. They have been widely used in closely related fields to programming, automation, and robotics. Read more…
Surveillance Coverage Using Multiple Robots
Autonomous robots (aerial, ground, surface, or underwater) can perform a variety of missions with different levels of autonomy. The problem of deploying a team of robots to perform surveillance coverage missions over an unknown terrain of complex and non-convex morphology is crucial in real missions involving autonomous devices. Read more…
img(Anaktisi)
This website presents a new set of feature descriptors in a retrieval system. These descriptors have been designed with particular attention to their size and storage requirements, keeping them as small as possible without compromising their discriminating ability. These descriptors incorporate color and texture information into one histogram while keeping their sizes between 23 and 74 bytes per image. Read more…
Research on Blockchain
My research on Blockchain focuses on studying the innovative concepts leveraged by this newly emerged technology and its new application-driven directions. My main research activity focuses on designing and developing special-purpose decentralized applications (dApps). My work includes the Parkchain project, the RandomBlocks generator, and Sensitive Information Exchange Mechanisms. Read more…