Dimitrios Besiris

Dictionary based color image retrieval

In this work the normalized dictionary distance (NDD) is presented and investigated. NDD is a similarity metric based on the dictionary of a sequence acquired from a data compressor. A dictionary gives significant information about the structure of the sequence it has been extracted from. We examine the performance of this new distance measure for color image retrieval tasks, by focusing on three parameters: the transformation of the 2D image to a 1D string, the color to character correspondence, and the image size. We demonstrate that NDD can outperform standard (dis)similarity measures based on color histograms or color distributions.

Combining graph connectivity & dominant set clustering for video summarization

The paper presents an automatic video summarization technique based on graph theory methodology and the dominant sets clustering algorithm. The large size of the video data set is handled by exploiting the connectivity information of prototype frames that are extracted from a down-sampled version of the original video sequence. The connectivity information for the prototypes which is obtained from the whole set of data improves video representation and reveals its structure. Automatic selection of the optimal number of clusters and hereafter keyframes is accomplished at a next step through the dominant set clustering algorithm. The method is free of user-specified modeling parameters and is evaluated in terms of several metrics that quantify its content representational ability. Comparison of the proposed summarization technique to the Open Video storyboard, the Adaptive clustering algorithm and the Delaunay clustering approach, is provided.

Key frame extraction in video sequences: a vantage points approach

In this work, the idea of key frames extraction from single shots in video sequences is presented. The method is implemented by an efficient two-step algorithm, which is classified neither to clustering nor to temporal variations based techniques. In the first step, an MST (minimal spanning tree) graph is constructed, where each node is associated to a single frame of the shot. In the second step, extracts key frames based on the principle of their maximum spread, are extracted. The number of the selected key frames is controlled by an adaptively defined threshold, while the validity of the results is evaluated by the fidelity measure.

An FPGA-Based Hardware Implementation of Configurable Pixel-Level Color Image Fusion

Image fusion has attracted a lot of interest in recent years. As a result, different fusion methods have been proposed mainly in the fields of remote sensing and computer (e.g., night) vision, while hardware implementations have been also presented to tackle real-time processing in different application domains. In this paper, a linear pixel-level fusion method is employed and implemented on a field-programmable-gate-array-based hardware system that is suitable for remotely sensed data. Our work incorporates a fusion technique (called VTVA) that is a linear transformation based on the Cholesky decomposition of the covariance matrix of the source data. The circuit is composed of different modules, including covariance estimation, Cholesky decomposition, and transformation ones. The resulted compact hardware design can be characterized as a linear configurable implementation since the color properties of the final fused color can be selected by the user in a way of controlling the resulting correlation between color components.

Dictionary-based color image retrieval using multiset theory

Dictionaries have recently attracted a great deal of interest as a new powerful representation scheme that can describe the visual content of an image. Most existing approaches nevertheless, neglect dictionary statistics. In this work, we explore the linguistic and statistical properties of dictionaries in an image retrieval task, representing the dictionary as a multiset. This is extracted by means of the LZW data compressor which encodes the visual patterns of an image. For this reason the image is first quantized and then transformed into a 1D string of characters. Based on the multiset notion we also introduce the Normalized Multiset Distance (NMD), as a new dictionary-based dissimilarity measure which enables the user to retrieve images with similar content to a given query. Experimental results demonstrate a significant improvement in retrieval performance compared to related dictionary-based techniques or to several other image indexing methods that utilize classical low-level image features.

Video summarization by a graph-theoretic FCM based algorithm

In this work, we propose a unified approach for video summarization based on the analysis of the video structure. The method originates from a data learning technique that uses the membership values produced by an over-partitioning mode of the FCM algorithm to find the connection strength between the resulting set of prototype centers. The final clustering stage is implemented by using the minimal spanning tree produced by the connectivity matrix. Based on the MST edge weights value, the clusters are derived straightforwardly and without supervision. The algorithm is finalized by the detection of video shots and the selection of key frames from each one. The method is evaluated by using objective and subjective criteria and its applicability to elongated video data set structures is very satisfactory.

Image database organization based on membership values and connectivity graph

A fast, simple and low complexity technique for image database organization is presented. The basic idea is to reveal the connectivity relations of the database obtain information of the database structure and facilitate the clustering process. This is achieved by randomly selecting a certain number of prototype data and using appropriately the membership values of the rest data points to the selected prototypes. The clustering is easily performed in the final step by using graph theory methodology.