Sonja Grgic

Performance analysis of image compression using wavelets

The aim of this paper is to examine a set of wavelet functions (wavelets) for implementation in a still image compression system and to highlight the benefit of this transform relating to todays methods. The paper discusses important features of wavelet transform in compression of still images, including the extent to which the quality of image is degraded by the process of wavelet compression and decompression. Image quality is measured objectively, using peak signal-to-noise ratio or picture quality scale, and subjectively, using perceived image quality. The effects of different wavelet functions, image contents and compression ratios are assessed. A comparison with a discrete-cosine-transform-based compression system is given. Our results provide a good reference for application developers to choose a good wavelet compression system for their application.

SCface --- surveillance cameras face database

In this paper we describe a database of static images of human faces. Images were taken in uncontrolled indoor environment using five video surveillance cameras of various qualities. Database contains 4,160 static images (in visible and infrared spectrum) of 130 subjects. Images from different quality cameras should mimic real-world conditions and enable robust face recognition algorithms testing, emphasizing different law enforcement and surveillance use case scenarios. In addition to database description, this paper also elaborates on possible uses of the database and proposes a testing protocol. A baseline Principal Component Analysis (PCA) face recognition algorithm was tested following the proposed protocol. Other researchers can use these test results as a control algorithm performance score when testing their own algorithms on this dataset. Database is available to research community through the procedure described at www.scface.org.

Independent Comparative Study of PCA, ICA, and LDA on the FERET Data Set

Face recognition is one of the most successful applications of image analysis and understanding and has gained much attention in recent years. Various algorithms were proposed and research groups across the world reported different and often contradictory results when comparing them. The aim of this paper is to present an independent, comparative study of three most popular appearance‐based face recognition projection methods (PCA, ICA, and LDA) in completely equal working conditions regarding preprocessing and algorithm implementation. We are motivated by the lack of direct and detailed independent comparisons of all possible algorithm implementations (e.g., all projection–metric combinations) in available literature. For consistency with other studies, FERET data set is used with its standard tests (gallery and probe sets). Our results show that no particular projection–metric combination is the best across all standard FERET tests and the choice of appropriate projection–metric combination can only be made for a specific task. Our results are compared to other available studies and some discrepancies are pointed out. As an additional contribution, we also introduce our new idea of hypothesis testing across all ranks when comparing performance results.

Image compression using wavelets

The discrete wavelet transform (DWT) represents images as a sum of wavelet functions (wavelets) on different resolution levels. The basis for the wavelet transform can be composed of any function that satisfies requirements of multiresolution analysis. It means that there exists a large selection of wavelet families depending on the choice of wavelet function. The choice of wavelet family depends on the application. In image compression application this choice depends on image content. This paper provides fundamentals of wavelet based image compression. The options for wavelet image representations are tested. The results of image quality measurements for different wavelet functions, image contents, compression ratios and resolutions are given.

Picture quality measures in image compression systems

A major problem in evaluating picture quality in image compression systems is the extreme difficulty in describing the type and amount of degradation in reconstructed image. Because of the inherent drawbacks associated with the subjective measures of picture quality, there has been a great deal of interest in developing an objective measure that can be used as a substitute. The aim of this paper is to examine a set of objective picture quality measures for application in still image compression systems and to highlight the correlation of these measures with subjective picture quality measures. Picture quality is measured using nine different objective picture quality measures and subjectively using mean opinion score (MOS) as a measure of perceived picture quality. The correlation between each objective measure and MOS is found. The effects of different image compression ratios are assessed and the best objective measures are proposed. Our results show that some objective measures correlate well with the perceived picture quality for a given compression algorithm but they are not reliable for an evaluation across different algorithms. So, we compared objective picture quality measures across different algorithms and we found measures, which serve well in all tested image compression systems.

Modified SPIHT algorithm for wavelet packet image coding

This paper introduces a new implementation of wavelet packet decomposition which is combined with SPIHT (Set Partitioning in Hierarchical Trees) compression scheme. We provide the analysis of the problems arising from the application of zerotree quantisation based algorithms (such as SPIHT) to wavelet packet transform coefficients. We established the generalized parent-child relationships for wavelet packets, providing complete tree structures for SPIHT. The proposed algorithm can be used for both wavelet dyadic and Wavelet Packet decomposition (WP-SPIHT). An extensive evaluation of the algorithm was performed and it has been shown that WP-SPIHT significantly outperforms base-line SPIHT coder for texture images. For these images the suboptimal WP cost-function enables good enough energy compaction that is efficiently exploited by the WP-SPIHT.

Face recognition in JPEG and JPEG2000 compressed domain

In this paper we investigate the potential of performing face recognition in JPEG and JPEG2000 compressed domain. This is achieved by avoiding full decompression and using transform coefficients as input to face recognition algorithms. We propose a new comparison methodology and by employing it show that face recognition can efficiently be implemented directly into compressed domain. In the first part of our experiment we use all the available transform coefficients and show that recognition rates are comparable and in some cases even higher than recognition rates obtained by using pixels from uncompressed images (standard face recognition approach). In the second part, we propose an effective coefficient preselection method (applicable both in JPEG and JPEG2000 compressed domain). Our results show that by using the proposed method, recognition rates can be significantly improved while additionally reducing computational time. Finally, we propose what a hypothetical compressed domain face recognition system should look like.

New image-quality measure based on wavelets

We present an innovative approach to the objective quality evaluation that could be computed using the mean difference between the original and tested images in different wavelet subbands. Discrete wavelet transform (DWT) subband decomposition properties are similar to human visual system characteristics facilitating integration of DWT into image-quality evaluation. DWT decomposition is done with multiresolution analysis of a signal that allows us to decompose a signal into approximation and detail subbands. DWT coefficients were computed using reverse biorthogonal spline wavelet filter banks. Wavelet coefficients are used to compute new image-quality measure (IQM). IQM is defined as perceptual weighted difference between coefficients of original and degraded image.

VCL@FER Image Quality Assessment Database

In this paper we present new image quality database which consists of four degradation types: JPEG, JPEG2000, White noise and Gaussian blur. Results for five commonly used objective quality measures are compared using newly developed image database, as well as LIVE image database.

Fuzzy Logic Power Control in Cognitive Radio

Opportunistic radio spectrum access has the possibility to improve spectrum utilization needed for next generation mobile networks. The main challenge to opportunistic radio spectrum access lies in finding balance in conflicting goals of satisfying performance requirements while minimizing interference. In this paper we propose new strategy for fuzzy logic transmit power control which enables cognitive secondary user to achieve its required transmission rate and quality, while minimizing interference to the primary users and other concurrent secondary users.