Image Processing and Communications 

About: Image Processing and Communications is an academic journal. The journal publishes majorly in the area(s): Image segmentation & Image processing. It has an ISSN identifier of 1425-140X. It is also open access. Over the lifetime, 311 publications have been published receiving 952 citations.

The put face database

Abstract: In this paper we present a new database of color, high resolution face images. The database contains almost 10000 images of 100 people acquired in partially controlled conditions and stored in 2048 × 1536 pixels images. The base is publicly available for research purposes and can be used as a training and testing material in developing various algorithms related to the face detection, recognition and analysis.

A novel LBP based methods for pavement crack detection

Abstract: Two optimized architectures of Context-based Adaptive Binary Arithmetic Coding (CABAC) are presented in the paper. These are: the software version of CABAC (dedicated to IA-32 and DSP platforms) and the hardware version of CABAC (dedicated to FPGA and ASIC platforms). The paper presents analysis of implementations for both versions of CABAC. The optimized software as well as the hardware version of CABAC was tested in terms of codec throughput.

Shortest Path Problem Solving Based on Ant Colony Optimization Metaheuristic

Abstract: Abstract The Ant Colony Optimization (ACO) metaheuristic is a versatile algorithmic optimization approach based on the observation of the behaviour of ants. As a result of numerous analyses, ACO has been applied to solving various combinatorial problems. The ant colony metaheuristic proves itself to be efficient in solving NP-hard problems, often generating the best solution in the shortest amount of time. However, not enough attention has been paid to ACO as a means of solving problems that have optimal solutions which can be found using other methods. The shortest path problem is undoubtedly one of the aspects of great significance to navigation and telecommunications. It is used, amongst others, for determining the shortest route between two geographical locations, for routing in packet networks, and to balance and optimize network utilization. Thus, this article introduces ShortestPathACO, an Ant Colony Optimization based algorithm designed to find the shortest path in a graph. The algorithm consists of several subproblems that are presented successively. Each subproblem is discussed from many points of view to enable researchers to find the most suitable solutions to the problems they investigate.

FPGA Implementation of Decision Trees and Tree Ensembles for Character Recognition in Vivado Hls

Abstract: Abstract Decision trees and decision tree ensembles are popular machine learning methods, used for classification and regression. In this paper, an FPGA implementation of decision trees and tree ensembles for letter and digit recognition in Vivado High-Level Synthesis is presented. Two publicly available datasets were used at both training and testing stages. Different optimizations for tree code and tree node layout in memory are considered. Classification accuracy, throughput and resource usage for different training algorithms, tree depths and ensemble sizes are discussed. The correctness of the module’s operation was verified using C/RTL cosimulation and on a Zynq-7000 SoC device, using Xillybus IP core for data transfer between the processing system and the programmable logic.

Filters for RSSI-based measurements in a device-free passive localisation scenario

Abstract: There are a number of techniques used in modernLocation aware systems such as Received Signal Strength Indicator(RSSI), Time of Arrival (TOA), Time Difference of Arrival(TDOA) and Angle of Arrival (AOA). However the benefit ofRSSI-based location positioning technologies, is the possibilityto develop location estimation systems without the need forspecialised hardware.The human body contains more than 70% water which iscausing changes in the RSSI measurements. It is known thatthe resonance frequency of the water is 2.4 GHz. Thus a humanpresence in an indoor environment attenuates the wireless signal.Device-free Passive (DfP) localisation is a technique to detect aperson without the need for any physical devices i.e. tags orsensors. A DfP Localisation system uses the Received SignalStrength Indicator (RSSI) for monitoring and tracking changesin a Wireless Network infrastructure. The changes in the signalalong with prior fingerprinting of a physical location allowidentification of a person’s location.This research is focused on implementing DfP Localisationbuilt using a Wireless Sensor Network (WSN). The aim of thispaper is the evaluation of various smoothing algorithms forthe RSSI recorded in a Device-free Passive (DfP) Localisationscenario in order to find an algorithm that generates the bestoutput. The best output is referred to here as results that canhelp us decide if a person entered the monitored environment.The DfP scenario considered in this paper is based on monitoringthe changes in the wireless communications due to the presenceof a human body in the environment. Thus to have a clear imageof the changes caused by human presence indoors, the wirelessrecordings need to be smoothed. The following algorithms aredemonstrated with results: five-point Triangular Smoothing Algorithm,Moving Average filter, Lowess filter, Loess filter, Rlowessfilter, Rloess filter, 1-D median filter, Savittzky-Golay filter, andKalman filter.