Visualisation and browsing of image databases

In this chapter we provide a comprehensive overview of the emerging field of visualising and browsing image databases. We start with a brief introduction to content-based image retrieval and the traditional query-by-example search paradigm that many retrieval systems employ. We specify the problems associated with this type of interface, such as users not being able to formulate a query due to not having a target image or concept in mind. The idea of browsing systems is then introduced as a means to combat these issues, harnessing the cognitive power of the human mind in order to speed up image retrieval.We detail common methods in which the often high-dimensional feature data extracted from images can be used to visualise image databases in an intuitive way. Systems using dimensionality reduction techniques, such as multi-dimensional scaling, are reviewed along with those that cluster images using either divisive or agglomerative techniques as well as graph-based visualisations. While visualisation of an image collection is useful for providing an overview of the contained images, it forms only part of an image database navigation system. We therefore also present various methods provided by these systems to allow for interactive browsing of these datasets. A further area we explore are user studies of systems and visualisations where we look at the different evaluations undertaken in order to test usability and compare systems, and highlight the key findings from these studies. We conclude the chapter with several recommendations for future work in this area. © 2011 Springer-Verlag Berlin Heidelberg.

(Table 1, page 400) Metal content of different manganese nodules from cruise VA-04 (R/V Valdivia) in the Pacific Ocean

Deep sea manganese nodules are considered as important natural resources for the future because of their Ni, Cu and Co contents. Their different shapes cannot be correlated clearly with their chemical composition. Surface constitution, however, can be associated with the metal contents. A classification of the nodules is suggested on the basis of these results. The iron content of the nodules strikingly shows relations to the physical properties (e.g. density and porosity). The method of density-measurement is the reason for this covariance. The investigation of freeze-dried nodular substance does not give this result. The Fe-rich nodules lose more hydration water than the Fe-poor ones during heat drying. The reason for this effect is the different crystallinity, respectively the particle size. The mean particle size is calculated on the basis of geometrical models. The X-ray-diffraction analysis proves the variation of crystallinity in connection with the Fe-content, too. The internal nodular textures also show characteristic distinctions.

Demonstration of image compression in a low-bandwidth wireless camera network

This paper presents an overview of our demonstration of a low-bandwidth, wireless camera network where image compression is undertaken at each node. We briefly introduce the Fleck hardware platform we have developed as well as describe the image compression algorithm which runs on individual nodes. The demo will show real-time image data coming back to base as individual camera nodes are added to the network. Copyright 2007 ACM.

Choice of image features for depth-axis control in image based visual servo control

This paper is concerned with choosing image features for image based visual servo control and how this choice influences the closed-loop dynamics of the system. In prior work, image features tend to be chosen on the basis of image processing simplicity and noise sensitivity. In this paper we show that the choice of feature directly influences the closed-loop dynamics in task-space. We focus on the depth axis control of a visual servo system and compare analytically various approaches that have been reported recently in the literature. The theoretical predictions are verified by experiment.

Behaviour of image degradation model in multiresolution

Multiresolution techniques are being extensively used in signal processing literature. This paper has two parts, in the first part we derive a relationship between the general degradation model (Y=BX+W) at coarse and fine resolutions. In the second part we develop a signal restoration scheme in a multiresolution framework and demonstrate through experiments that the knowledge of the relationship between the degradation model at different resolutions helps in obtaining computationally efficient restoration scheme.

A Taxonomy of image matching techniques for stereo vision

Stereo vision is a method of depth perception, in which depth information is inferred from two (or more) images of a scene, taken from different perspectives. Applications of stereo vision include aerial photogrammetry, autonomous vehicle guidance, robotics, industrial automation and stereomicroscopy. A key issue in stereo vision is that of image matching, or identifying corresponding points in a stereo pair. The difference in the positions of corresponding points in image coordinates is termed the parallax or disparity. When the orientation of the two cameras is known, corresponding points may be projected back to find the location of the original object point in world coordinates. Matching techniques are typically categorised according to the nature of the matching primitives they use and the matching strategy they employ. This report provides a detailed taxonomy of image matching techniques, including area based, transform based, feature based, phase based, hybrid, relaxation based, dynamic programming and object space methods. A number of area based matching metrics as well as the rank and census transforms were implemented, in order to investigate their suitability for a real-time stereo sensor for mining automation applications. The requirements of this sensor were speed, robustness, and the ability to produce a dense depth map. The Sum of Absolute Differences matching metric was the least computationally expensive; however, this metric was the most sensitive to radiometric distortion. Metrics such as the Zero Mean Sum of Absolute Differences and Normalised Cross Correlation were the most robust to this type of distortion but introduced additional computational complexity. The rank and census transforms were found to be robust to radiometric distortion, in addition to having low computational complexity. They are therefore prime candidates for a matching algorithm for a stereo sensor for real-time mining applications. A number of issues came to light during this investigation which may merit further work. These include devising a means to evaluate and compare disparity results of different matching algorithms, and finding a method of assigning a level of confidence to a match. Another issue of interest is the possibility of statistically combining the results of different matching algorithms, in order to improve robustness.

The impact of sulphur content of diesel fuel on ultrafine particle formation

Early this year the Australian Department of Environment and Heritage commissioned a desktop literature review with a focus on ultrafine particles including analysis of health impacts of the particles as well as the impact of sulphur content of diesel fuel on ultrafine particle emission. This paper summarizes the findings of the report on the link between the sulphur content of diesel fuels and the number of ultrafine particles in diesel emissions. The literature search on this topic resulted in over 150 publications. The majority of these publications, although investigating different aspects of the influence of fuel sulphur level on diesel vehicle emissions, were not directly concerned with ultrafine particle emissions. A specific focus of the paper is on: ----- ----- summary of state of knowledge established by the review, and ----- ----- summary of recommendations on the research priorities for Australia to address the information gaps for this issue, and on the appropriate management responses.

Spatial and temporal variations of mechanical properties and mineral content of the external callus during bone healing

After bone fracture, various cellular activities lead to the formation of different tissue types, which form the basis for the process of secondary bone healing. Although these tissues have been quantified by histology, their material properties are not well understood. Thus, the aim of this study is to correlate the spatial and temporal variations in the mineral content and the nanoindentation modulus of the callus formed via intramembranous ossification over the course of bone healing. Midshaft tibial samples from a sheep osteotomy model at time points of 2, 3, 6 and 9 weeks were employed. PMMA embedded blocks were used for quantitative back scattered electron imaging and nanoindentation of the newly formed periosteal callus near the cortex. The resulting indentation modulus maps show the heterogeneity in the modulus in the selected regions of the callus. The indentation modulus of the embedded callus is about 6 GPa at the early stage. At later stages of mineralization, the average indentation modulus reaches 14 GPa. There is a slight decrease in average indentation modulus in regions distant to the cortex, probably due to remodelling of the peripheral callus. The spatial and temporal distribution of mineral content in the callus tissue also illustrates the ongoing remodelling process observed from histological analysis. Most interestingly the average indentation modulus, even at 9 weeks, remains as low as 13 GPa, which is roughly 60% of that for cortical sheep bone. The decreased indentation modulus in the callus compared to cortex is due to the lower average mineral content and may be perhaps also due to the properties of the organic matrix which might be different from normal bone.

Probabilistic matching of image sets for video-based face recognition

We address the problem of face recognition on video by employing the recently proposed probabilistic linear discrimi-nant analysis (PLDA). The PLDA has been shown to be robust against pose and expression in image-based face recognition. In this research, the method is extended and applied to video where image set to image set matching is performed. We investigate two approaches of computing similarities between image sets using the PLDA: the closest pair approach and the holistic sets approach. To better model face appearances in video, we also propose the heteroscedastic version of the PLDA which learns the within-class covariance of each individual separately. Our experi-ments on the VidTIMIT and Honda datasets show that the combination of the heteroscedastic PLDA and the closest pair approach achieves the best performance.

Evaluation of image resolution and super-resolution on face recognition performance

While researchers strive to improve automatic face recognition performance, the relationship between image resolution and face recognition performance has not received much attention. This relationship is examined systematically and a framework is developed such that results from super-resolution techniques can be compared. Three super-resolution techniques are compared with the Eigenface and Elastic Bunch Graph Matching face recognition engines. Parameter ranges over which these techniques provide better recognition performance than interpolated images is determined.