Evangelos Zigouris

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.

An FPGA-based Digital Camera System controlled from an LCD Touch Panel

Field Programmable Gate Arrays (FPGAs) are in use to build high performance image processing systems. This paper presents the design and implementation of such an open FPGA-based Digital Camera System for image capturing and real-time image processing. Images captured with a CMOS sensor are initially stored in the systems memory and then they are displayed on an LCD Touch Panel. The main goal of this proposed architecture is to be used as a platform to implement and test advance image processing algorithms. Apart of this, the system supports the control of the image sensor, through the LCD Touch Panel. In addition, has the ability to communicate with a PC through a JTAG interface for storing the images on it. The structural element for this proposed architecture was chosen to be the low cost and widely used at universities, Alteras DE2 development board.

LabVIEW to CCS Link for Automating Digital Signal & Image Processing Applications

The purpose of this paper is to present the Lab VIEW to CCS Link which is a developed from scratch toolkit. It provides the user with the opportunity to design and implement in a fast and easy way, interfaces with Lab VIEW 7.1 or later, for digital signal and image processing applications on DSPs. The interfaces (Vis) created with Lab VIEW to CCS Link can setup and control Code Composer Studio v3.1 or later and exchange data with more than one DSPs. In order to demonstrate the LabVIEW to CCS Link capabilities, the implementation of two typical applications on signal and image processing are also presented. Due to the great convenience this toolkit offers, it can be used for educational purposes as well.

The use of entropy for colour edge detection

The edge detection of images is a widely discussed topic and several methods have been presented. In this work the vector nature of the color image is retained assuming the RGB space as the standard processing space. The proposed statistical approach is based on entropy and relative entropy operator using the Parzen kernels to estimate the local density distribution. Experimental results indicate that these methods, if not better, are comparable to other standard colour edge detection techniques.

A Remote Laboratory for Real-Time Digital Image Processing on Embedded Systems

The purpose of this paper is to present a Remote Laboratory on embedded systems focused in real-time digital image processing. This laboratory consists of a Main Web Server and several Workstations which are designed for digital image retrieval from a CMOS Image Sensor and real-time image processing on a Digital Signal Processor development platform. The Main Web Server redirects the authorised remote users to available Workstations in order to execute and verify their image processing algorithms or test their system designs using a developed Application Programming Interface. Through user-friendly web pages users can interfere with the hardware parameters and observe the results of their solutions.

Real-time DSP applications remotely controlled through customized GUIs

This paper proposes an extended version of the R-DSP (Remote Digital Signal Processor) Server which supports the remote control of real-time DSP applications through customized GUIs (Graphical User Interfaces) developed by the users. This server allows users to validate their realtime DSP applications without time and place barriers. The interaction between the customized GUIs and the DSP development platforms through the R-DSP Server is achieved using TCP/IP messages formatted according to the R-DSP Protocol. The users are able to design and develop their own GUIs using any programming language. In order to decrease the complexity and the development time of customized GUIs based on Matlab and LabVIEW, two sets of functions are also proposed. Two examples of real-time DSP applications remotely controlled by customized GUIs are also presented.

Remotely Controlled Real-Time DSP Applications through Customized GUIs based on LabVIEW

The purpose of this paper is to present an approach which could expand the features of Remote Laboratories focused on embedded Digital Signal Processing (DSP) systems. The proposed approach is based on a system which is designed and developed with LabVIEW and is called R-DSP Server. Exploiting this system, users are able to develop their own Graphical User Interfaces (GUIs), named Customized GUIs, for the remote control and validation of real-time DSP applications. These GUIs are tailored to the needs of each DSP application and can be implemented in any programming language. The rapid design of Customized GUIs using LabVIEW for the communication with the R-DSP Server is achieved utilizing an implemented set of functions, called R-DSP LabVIEW Toolkit.