Liana Stanescu

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.

Automatic image annotation and semantic based image retrieval 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 a system used in the medical domain for three distinct tasks: image annotation, semantic based image retrieval and content based image retrieval. An original image segmentation algorithm based on a hexagonal structure was used to perform the segmentation of medical images. Images regions are described using a vocabulary of blobs generated from image features using the K-means clustering algorithm. The annotation and semantic based retrieval task is evaluated for two annotation models: Cross Media Relevance Model and Continuous-space Relevance Model. Semantic based image retrieval is performed using the methods provided by the annotation models. 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). The experiments were made using a database containing color images retrieved from medical domain using an endoscope and related to digestive diseases.

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.

Question generation for learning evaluation

In the last decade the electronic learning became a very useful tool in the studentspsilas education from different activity domains. The accomplished studies indicated that the students substantially appreciate the e-learning method, due to the facilities: the facile information access, a better storage of the didactic material, the curricula harmonization between universities, personalized instruction. The paper presents a software tool that can be used in the e-learning process in order to automatically generate questions from course materials, based on a series of tags defined by the professor. The test creator tool permits generation of questions based on electronic materials that students have. The solution implies teachers to have a series of tags and templates that they manage. These tags are used to generate question automatically.

Medical image segmentation - a comparison of two algorithms

Image segmentation plays an important role in image analysis as a frequent pre-processing step in many image understanding algorithms and practical vision systems. According to several authors, segmentation terminates when the observers goal is satisfied and for this reason, a unique method that can be applied to all possible cases does not yet exist. The purpose of this paper is to find which segmentation method is more appropriate for recognition and diagnosis of medical images. The algorithms used for comparison are: the color set back-projection algorithm that can be found in many related studies, and an original segmentation method using a hexagonal structure defined on the set of image pixels. Error measuring algorithms, which quantify the consistency between these two segmentations, were used in order to evaluate these segmentation methods. These measures allow a principled comparison between segmentation results on different images, with differing numbers of regions and which is generated by different algorithms with different parameters.

An improved platform for medical E-Learning

The paper presents an improved E-Learning platform that is especially designed for medical education. There are presented users tasks, having the following roles: administrator, secretary and teacher. The facilities of the students are also presented: students have the possibility to download course materials, take tests or sustain final examinations and communicate with all parties involved. An element of originality for this platform is the image database that is permanently updated by the teachers. The students can use this database for simple text based queries, or content-based visual queries. The content-based visual query represents a modern possibility to query the image databases using characteristics that were automatically extracted from images: colour, texture or regions. Combining content-based visual query with other access methods (text-based, hierarchical methods) for a teaching image database, helps students to view images in the database in a simple and direct manner, stimulating learning by comparing the similar cases and their particularities, or comparing similar images that have different diagnostics.

Computational Complexity Analysis of the Graph Extraction Algorithm for 3D Segmentation

The problem of partitioning images into homogenous regions or semantic entities is a basic problem for identifying relevant objects. Visual segmentation is related to some semantic concepts because certain parts of a scene are pre-attentively distinctive and have a greater significance than other parts. Unfortunately there are huge of papers for 2D images and segmentation methods and most graph-based for 2D images and few papers for spatial segmentation methods. We attempt to search a certain structures in the associated edge weighted spatial graph constructed on the image voxels, such as minimum spanning tree. The major concept used in graph-based 3D clustering algorithms is the concept of homogeneity of regions. For color 3D segmentation algorithms the homogeneity of regions is color-based, and thus the edge weights are based on color distance. Early graph-based methods use fixed thresholds and local measures in finding a 3D segmentation. Complex grouping phenomena can emerge from simple computation on these local cues. A number of approaches to segmentation are based on finding compact clusters in some feature space. A recent technique using feature space clustering first transforms the data by smoothing it in a way that preserves boundaries between regions. Our previous works are related to other works in the sense of pair-wise comparison of region similarity. In this paper we extend our previous work by adding a new step in the spatial segmentation algorithm that allows us to determine regions closer to it. We use different measures for internal contrast of a connected component and for external contrast between two connected components than the measures. The key to the whole algorithm of spatial segmentation is the honeycomb. The preprocessing module is used mainly to blur the initial RGB spatial image in order to reduce the image noise by applying a 3D Gaussian kernel. Then the segmentation module creates virtual cells of prisms with tree-hexagonal structure defined on the set of the image voxels of the input spatial image and a spatial triangular grid graph having tree-hexagons as cells of vertices.

A comparative study of some methods for color medical images segmentation

The aim of this article is to study the problem of color medical images segmentation. The images represent pathologies of the digestive tract such as ulcer, polyps, esophagites, colitis, or ulcerous tumors, gathered with the help of an endoscope. This article presents the results of an objective and quantitative study of three segmentation algorithms. Two of them are well known: the color set back-projection algorithm and the local variation algorithm. The third method chosen is our original visual feature-based algorithm. It uses a graph constructed on a hexagonal structure containing half of the image pixels in order to determine a forest of maximum spanning trees for connected component representing visual objects. This third method is a superior one taking into consideration the obtained results and temporal complexity. These three methods were successfully used in generic color images segmentation. In order to evaluate these segmentation algorithms, we used error measuring methods that quantify the consistency between them. These measures allow a principled comparison between segmentation results on different images, with differing numbers of regions generated by different algorithms with different parameters.

Semantic Based Image Retrieval Using Relevance Feedback

In this paper, we propose a method for image categorization and retrieval, by integrating knowledge from low-level and semantic features extracted from images. The low -level descriptors, like color, position, dimension and texture are extracted from each image region. These mathematical descriptors are automatically associated with intermediate semantic descriptors. The intermediate descriptors are used also for image categorization and for qualitative definition of semantic keywords in the user queries. For improving the initial query results, we apply a relevance feedback mechanism that uses the low -level descriptors of the images selected as relevant by user for producing the final query results. A support vector machine classifier can be learned from training data of relevance images and irrelevance images marked by users. Using the classifier and the semantic indexing, we implement a software system that can retrieve more images relevant to the query in the database efficiently.

A Spatial Watermarking Algorithm for Video Images

The lack of control inherent to digital content has been put on the spotlight by copyright infringement coupled with massive content online distribution (e.g., Peer-to-Peer). Digital Rights Management seems to be the solution to counter this problem advocating the use of cryptography and other related security mechanisms to protect digital content and to associate rights with it which determine how, when and by whom it can be consumed. The rapid growth of digital multimedia technologies brings tremendous attention to the field of digital watermarking. Watermarking embeds a secret message into a cover multimedia data. In media watermarking the secret is usually a copyright notice and the cover a digital image. In digital watermarking, robustness is still a challenging problem if different sets of attacks needed to be tolerated simultaneously. In this paper we present an original spatial watermarking technique for video and images. Our approach modifies blocks of the image or frames by a spatial watermark insertion. Spatial mask of suitable size is used to hide data with less visual impairments. Watermark insertion process exploits average color of the homogeneity regions of the cover image. We took a frame-based approach to video watermarking. From video we extract a certain number of key-frames: the first, the middle, and last key-frame. The first step is decoding: transformation of mpeg to jpeg sequences, after that we select three frames that will be process by applying the watermark mask. In the reverse process of encoding we take the marked frames.