Content-based image retrieval is an important research area in the domain of multimedia information processing, while shape-based image retrieval is one of the main aspects of the content-based image retrieval. Image and video are the most intuitive and visual content in the multimedia. Due to the dramatic increasing of the information in today’s era, the efficient management and rapid indexing of the rapidly expanding multimedia information became an urgent problem. In this thesis, the fundamental theory of the content-based image retrieval and the developing process of the application research are firstly introduced. Then, the content-based image retrieval techniques especially the shape retrieval techniques and its current status are reviewed along with some discussions of the key techniques of image retrieval. Owing to the fact that the shape features are one of the most important features of the image that can describe the object reliably, shape-based image retrieval has been an active research area in image retrieval. The main contributions of this thesis are as follows:Firstly, a new image retrieval algorithm based on the distance-histogram derived from shape contour is proposed. In this algorithm, the one-dimensional Gaussian functions of two different scales are firstly employed respectively for the concave and convex part of the contour to generate a simpler and smoother evolved curve that can capture the main information of the original contour, after which, the skeleton of the contour is extracted with a skeletonization algorithm. Finally, the histogram of the distances between the evolved contour and skeleton is used to describe the shape for the retrieval purpose. The algorithm proposed uses not only the contour that represents the shape of an object from its outer part but also the skeleton that preserves the original object’s topology from its inner part. Experimental results show that this algorithm performs well in robustness to both contour transformations of scaling and rotation and to the noise corruptions of the contour.Secondly, a new image retrieval algorithm based on the Hidden Markov Models (HMM) is also proposed in this thesis. In this algorithm, the object contour is firstly partitioned at points with zero curvature value. Then, four structural features of the symmetry, the orientation, the length, and the linearity are extracted for the partitioned contour segments. For the extracted four structural features, the K-means algorithm is used for clustering purpose so that they can be organized into the observation sequences considered as the input for the HMM. Finally, the HMM is used for the classification and retrieval of the objects. Experimental results show that the proposed algorithm is an efficient method for shape retrieval.
Tuesday, June 30, 2009
Friday, June 26, 2009
Thursday, June 25, 2009
Την αντίδρασή του για την περικοπή της χρηματοδότησης του Δημοκριτείου Πανεπιστημίου Θράκης κατά 43% εξέφρασε το πρυτανικό συμβούλιο του πανεπιστημίου, το οποίο μετά από έκτακτη συνεδρίαση στις 22 Ιουνίου, εξέδωσε την εξής ανακοίνωση:
"Σε συνάντηση των πρυτανικών αρχών στις 18 Ιουνίου με τον υφυπουργό Παιδείας Σπύρο Ταλιαδούρο και την γενική γραμματεία του ΥΠΕΠΘ Νίκη Γκοτσοπούλου, μας ανακοινώθηκε ότι μειώθηκε κατά 43% η χρηματοδότηση των υποδομών του ΔΠΘ από το ΠΕΠ Ανατολικής Μακεδονίας και Θράκης του ΕΣΠΑ, δηλαδή από 62 εκ. ευρώ σε 35 εκ. ευρώ.
Το ύψος της χρηματοδότησης είχε συμφωνηθεί με τον προηγούμενο γενικό γραμματέα της Περιφέρειας Ανατολικής Μακεδονίας – Θράκης Μιχάλη Αγγελόπουλο και είχε επιβεβαιωθεί από το νυν γραμματέα Δημήτρη Σταμάτη, όπως επίσης και με τον προηγούμενο υπουργό Παιδείας Ευριπίδη Στυλιανίδη, οι οποίοι είχαν προεγκρίνει την συμφωνία.
Δεν θέλουμε να χαρακτηρίσουμε την ενέργεια περικοπής, η οποία μάλιστα έγινε σε σύσκεψη χωρίς την συμμετοχή του ΔΠΘ, τονίζει το πρυτανικό συμβούλιο και προσθέτει ότι, η μείωση αυτή θα πρέπει να συνδυαστεί με τον μειωμένο κατά 30% περίπου αριθμό των φοιτητών που το Υπουργείο Εθνικής Παιδείας και Θρησκευμάτων λαμβάνει υπόψη του για την χρηματοδότηση του τακτικού προϋπολογισμού, του προγράμματος δημοσίων επενδύσεων, καθώς και του τετραετή προγραμματισμού του Δημοκριτείου Πανεπιστημίου Θράκης.
Όλοι θα πρέπει να θυμηθούν την σημασία και την αποστολή του ακριτικού πανεπιστημίου στο οποίο στηρίζεται η ανάπτυξη της Θράκης σε μεγάλο βαθμό.
Το πρυτανικό συμβούλιο του Δημοκριτείου Πανεπιστημίου καλεί σε πρώτη φάση τον υπουργό Εθνικής Παιδείας και Θρησκευμάτων Άρη Σπηλιωτόπουλο να ασχοληθεί προσωπικά με το θέμα και να αποκαταστήσει τις όποιες λανθασμένες αποφάσεις έχουν ληφθεί σχετικά με την χρηματοδότηση του πανεπιστημίου και δηλώνει ότι, το Δημοκρίτειο Πανεπιστήμιο Θράκης σύσσωμο θα παρακολουθήσει στενά την εξέλιξη της υπόθεσης και θα αποφασίσει στη σύγκλητο τις περαιτέρω ενέργειες."
Daniel Sonntag, Manuel Möller: “Unifying Semantic Annotation and Querying in Biomedical Iimage Repositories”, to appear in Proc. of the International Conference on Knowledge Management and Information Sharing (KMIS), Madeira, 6 - 8 October, 2009, Portugal, [PDF]
Abstract: In the medical domain, semantic image retrieval can provide the basis for a new generation of sophisticated decision support and computer aided diagnosis systems. However, the acquisition of the necessary medical knowledge about the image contents poses new problems. We present a set of techniques for annotating images and querying image data sets, based on image semantics. The unification of semantic annotation (using a GUI) and querying (using natural dialogue) in biomedical image repositories is based on a unified view on the knowledge acquisition process. At the core, this system uses central RDF repository to capture both medical domain knowledge as well as image annotations. We understand medical knowledge engineering as an interactive process between the knowledge engineer and the clinician. Our system supports the knowledge engineering in an interactive process between the dialogue engineer and the clinician.
Sunday, June 21, 2009
Grounded Situation Models for Ripley the Robot ( by Nikolaos Mavridis ): Ripley the robot answers questions, remembers, and imagines!
Thursday, June 18, 2009
Journal of Visual Communication and Image Representation (JVCI)
Special Issue on “Large-Scale Image and Video Search: Challenges,
Technologies, and Trends”
The past recent years have witnessed the explosive growth of image and video data on the Internet, which brings significant challenges and profound impacts to search and related technologies. It is challenging for many existing algorithms to effectively and efficiently handle very large collections of image and video contents, especially when the scale rises from tens of thousands to tens of millions or even billions. Fortunately, along with the growth of imagery contents, more and more resources on the Internet become available, such as the associated metadata, context and social information. In addition, the power of grassroots has been fully demonstrated in the Web 2.0 era. For example, they can easily tag and comment on millions of images and videos, as well as label millions of images via a simple game. These facts have both raised challenges of large-scale search and provided opportunities for inventing new methodologies and pushing forward the frontiers of information technology. Recently, many research efforts are dedicated to developing new search technologies to overcome the scalability issue. This trend of rapidly increasing data scales is anticipated to spread across a still wider range of research communities. This special issue is intended to bring together the latest research results in this direction.
The scope of this special issue is to cover all aspects that relate to large-
scale image and video search. Topics of interest include, but are not
- Large-scale image and video indexing, including high-dimensional indexing, semantic-based indexing, etc.
- Large-scale image and video annotation/tagging, including new annotation and tagging interface, concept detection, categorization, tag recommendation, game-based tagging, tag filtering, etc.
- Large-scale image and video ranking, including ranking models, reranking, learning to rank, ranking performance evaluation, etc.
- Interactive image and video search, including relevance feedback, query suggestion, recommendation, etc.
- Image and video search presentation, such as search results clustering, browsing, and summarization.
- Large-scale image and video copy detection and near-duplication detection.
- Large-scale social-network analysis for image and video
Tuesday, June 16, 2009
10th International Workshop of the Multimedia Metadata Community
September 7, 2009-Deadline for Workshop Papers
September 28, 2009-Notification of Acceptance for Workshop Papers
October 19, 2009-Camera-ready Workshop Papers due
Ontology-based systems have been developed to structure content and support knowledge retrieval and management. Semantic multimedia data processing and indexing in ontology- based systems is usually done in several steps, one starts by enriching multimedia metadata with additional semantic information (possibly obtained by methods for bridging the semantic gap). Then, in order to structure data, a localized and domain specific ontology becomes necessary since the data has to be interpreted domain-specific. The annotations are stored in an ontology management system where they are kept for further processing. In this scope, Semantic Database Technologies are now applied to ensure reliable and secure access, efficient search, and effective storage and distribution for both multimedia metadata and data. Their services can be used to adapt multimedia to a given context based on multimedia metadata or even ontology information. Services automate cumbersome multimedia processing steps and enable ubiquitous intelligent adaptation. Both, database and automation support facilitate to ubiquitous use of multimedia in advanced applications.
We are searching for research contributions on the mapping and integration of multimedia metadata and ontologies into databases, on multimedia query languages, on the optimization and processing of semantic queries. Moreover, we are interested how multimedia data services are conceived to ensure interoperability, how to improve security and reliability of access and storage of multimedia data and metadata.
In addition, application papers showing concrete semantic multimedia database services (like, adaptation of multimedia, semantic enrichment of multimedia, and bridging of media breaks), as well as demonstrations on database technologies (like, mobile online image analysis and retrieval) are expected.
Topics of interest:
- Multimedia metadata models and mappings to databases
- Multimedia ontology and interoperability
- Multimedia ontology to database mapping and processing
- Multimedia query optimization and processing
- Ontology query languages and multimedia
- Semantic retrieval in multimedia databases
- Database management: security, indexing, reliability, distribution, transactions
- Indexing strategies for multimedia databases
- Semantic enrichment and annotation of multimedia
- Semantic metadata management
- Uncertainty in multimedia databases
- Human-computer interfaces for multimedia database access
- Mobile multimedia database services
- Context-aware multimedia
- Semantic adaptation of multimedia
- Proactive semantic multimedia delivery & distribution services
- Self-organization in service oriented multimedia architectures
- Semantic multimedia demonstrations and applications
Thursday, June 11, 2009
Recent years have witnessed the proliferation of social media and the success of many social websites, including Flickr, Youtube, MySpace, Facebook, Zooomr, etc. These websites allow users not only to create and share media data but also to rate and annotate them. On the one hand, the rapid increase of social media data makes many related applications challenging, such as categorization,
recommendation and search. On the other hand, the rich information clues associated with the data also offer us opportunities to attack many well-recognized difficulties encountered in multimedia analysis and understanding, e.g., insufficiency of labeled data for semantic learning.
Recently, more and more research efforts have been dedicated to the aforementioned challenges and opportunities. This special issue aims to introduce novel techniques, algorithms and systems regarding social media mining and search. Topics of interest include but not limited to:
· Social media creation, including editing, authoring, sharing, etc.
· Social media analysis and organization, including grouping, classification, indexing, navigation, etc.
· Social media search, including new search interface, query suggestion and expansion, ranking, search results presentation and browsing, etc.
· Social media tagging, including new tagging interface, tag recommendation, tag classification, tag filtering, automatic tagging, etc.
· Social media-based advertisement.
· Social media-based knowledge mining, such as learning models from tagged data, building lexicon/ontology from tags, and user interests/trends/relationships mining.
· Social context-based applications, such as media recommendation and collaborative filtering
· Social media benchmark dataset construction for research.
Multimedia Tools and Applications (MTAP) An International Journal Special Issue on “Data Hiding for Multimedia Security”
The digital information revolution has brought profound changes in our daily lives and the advantages of digital information have also generated new challenges and opportunities for their protection. Due to the tremendous advances in signal processing and transmission techniques, it is easy to acquire, tamper and duplicate multimedia data. For the last two decades, digital data hiding has received a great deal of attention from the scientific community to overcome the aforementioned problems. Remarkable research efforts have been invested in recent years, trying
to export novel and applied real world engineering applications. This special issue intents to bring together diversity of international researchers, experts and practitioners who are currently working in the area of digital data hiding systems. It is envisaged that this special issue will explore the advances of methods, techniques, and tools in solving the unsolved questions in digital data hiding. Prominent researchers both from academia and industry are invited to contribute their work for extending the existing knowledge in the field.
Research areas of relevance to this special issue would therefore include, but not only limited to:
• Digital watermarking
• Steganology (steganography and steganalysis)
• Information theoretic analysis of data hiding systems
• Data hiding in law enforcement, medicine, military, E-commerce, and M-commerce
• Fingerprinting in multimedia signals
• Data hiding for forensic applications
• Integrity verification and authentication
• Digital content protection
• Tampering and attacks on original information
• Data hiding system design and implementation
• Digital rights management
• Content identification and secure content delivery