Eugen Ganea

A New Method for Segmentation of Images Represented in a HSV Color Space

This paper presents an original low-level system for color image segmentation considering the Hue-Saturation-Value (HSV) color space. Many difficulties of color image segmentation may be resolved using the correct color space in order to increase the effectiveness of color components to discriminate color data. The technique proposed in the article uses new data structures that lead to simpler and more efficient segmentation algorithms. We introduce a flexible hexagonal network structure on the pixels image and we extract for each segmented region the syntactic features that can be used in the shape recognition process. Our technique has a time complexity lower than the methods studied from specialized literature and the experimental results on Berkeley Segmentation Dataset color image database show that the performance of method is robust.

An Adaptive Method for Efficient Detection of Salient Visual Object from Color Images

This paper presents an efficient graph-based method to detect salient objects from color images and to extract their color and geometric features. Despite of the majority of the segmentation methods our method is totally adaptive and it do not require any parameter to be chosen in order to produce a better segmentation. The proposed segmentation method uses a hexagonal structure defined on the set of the image pixels ant it performs two different steps: a pre-segmentation step that will produce a maximum spanning tree of the connected components of the visual graph constructed on the hexagonal structure of an image, and the final segmentation step that will produce a minimum spanning tree of the connected components, representing the visual objects, by using dynamic weights based on the geometric features of the regions. Experimental results are presented indicating a good performance of our method.

Evaluation of image segmentation algorithms from the perspective of salient region detection

The present paper addresses the problem of image segmentation evaluation by comparing seven different approaches. We are presenting a new method of salient object detection with very good results relative to other already known object detection methods. We developed a simple evaluation framework in order to compare the results of our method with other segmentation methods. The results of our experimental work offer good perspectives for our algorithm, in terms of efficiency and precision.

New Method to Detect Salient Objects in Image Segmentation using Hypergraph Structure

This paper presents a method for detection of salient objects from images. The proposed algorithms for image segmentation and objects detection use a hexagonal representation of the im ...

New algorithm for segmentation of images represented as hypergraph hexagonal-grid

This paper presents a new method for segmentation of images into regions and for boundary extraction that reflect objects present in the image scene. The unified framework for image processing uses a grid structure defined on the set of pixels from an image. We propose a segmentation algorithm based on hypergraph structure which produces a maximum spanning tree of a visual hypergraph constructed on the grid structure, and we consider the HCL (Hue-Chroma-Luminance) color space representation. Our technique has a time complexity lower than the methods from the specialized literature, and the experimental results on the Berkeley color image database show that the performance of the method is robust.

An hypergraph object oriented model for image segmentation and annotation

This paper presents a system for segmentation of images into regions and annotation of these regions for semantic identification of the objects present in the image. The unified method for image segmentation and image annotation uses an hypergraph model constructed on the hexagonal structure. The hypergraph structure is used for representing the initial image, the results of segmentation processus and the annotation information together with the RDF ontology format. Our technique has a time complexity much lower than the methods studied in the specialized literature, and the experimental results on the Berkeley Dataset show that the performance of the method is robust.

Region-based measures for evaluation of color image segmentation

The present paper is aimed to compare the efficiency of a new segmentation method with several existing approaches. The paper addresses the problem of image segmentation evaluation from the error measurement point of view.We are introducing a new method of salient object recognition with very good results relative to other already known object detection methods. We developed a simple evaluation framework in order to compare the results of our method with other segmentation methods. The experimental results offer a complete basis for parallel analysis with respect to the precision of our algorithm, rather than the individual efficiency.

High-Level Petri Nets with Object-Orientation – A High-Level Petri Net Model Allowing Multiple Inheritance and Multiple Polymorphism

This paper presents a high-level Petri net model called High-Level Petri Nets with Object-Orientation (HLPNOO), a new approach for introducing object-oriented concepts into the framework of Petri nets. An important feature of the HLPNOO formalism is the fact that it allows distinct hierarchies for subtyping and subclassing. We use order-sorted algebras in order to specify the notion of subtyping for object type hierarchies. Moreover we use the notions from category theory and institutions in order to allow composable Petri nets and multiple inheritance. We use encapsulated multi-methods and a multi-dispatching mechanism for messages in order to safety integrate the concepts of covariant and contravariant specialization of inherited methods and to allow the multiple polymorphism.

From GMoDS models to object-oriented specifications in Event-B

This paper represents a first attempt to express in Event-B the models of the GMoDS (The Goal Model for Dynamic Systems) methodology. GMoDS is a major result of the research related to Organization-Based Multiagent System Engineering methodology (O-MaSE), allowing to specify goals during requirements engineering process and then to use them throughout the system development and at runtime. We choose Event-B as a modelling language for specifying the GMoDS models for two reasons: (a) Event-B has the concept of proving correctness, which supports the accuracy of software development, and (b) its supporting tool, RODIN, is open-source, and it is used in many software industrial applications. Because Event-B is not object-oriented, and because several concepts used in GMoDS are related to object-orientation, we have included in the corresponding Event-B specifications the object-oriented concepts used in the GMoDS models, without changing the syntax and semantics of Event-B, and without using the UML-B tool.

Annotation System for Medical Domain

Automatic image annotation is the process of assigning meaningful words to an image taking into account its content. This process is of great interest as it allows indexing, retrieving, and understanding of large collections of image data. This paper presents an original image annotation system used in the medical domain. The annotation model used was inspired from the principles defined for Cross Media Relevance Model. The ontology used by the annotation process was created in an original manner starting from the information content provided by the Medical Subject Headings (MeSH).