Hyperspectral Image Classification with Nonlinear Methods

This thesis introduces two related lines of study on classification of hyperspectral images with nonlinear methods. First, it describes a quantitative and systematic evaluation, by the author, of each major component in a pipeline for classifying hyperspectral images (HSI) developed earlier in a joint collaboration [23]. The pipeline, with novel use of nonlinear classification methods, has reached beyond the state of the art in classification accuracy on commonly used benchmarking HSI data [6], [13]. More importantly, it provides a clutter map, with respect to a predetermined set of classes, toward the real application situations where the image pixels not necessarily fall into a predetermined set of classes to be identified, detected or classified with.

The particular components evaluated are a) band selection with band-wise entropy spread, b) feature transformation with spatial filters and spectral expansion with derivatives c) graph spectral transformation via locally linear embedding for dimension reduction, and d) statistical ensemble for clutter detection. The quantitative evaluation of the pipeline verifies that these components are indispensable to high-accuracy classification.

Secondly, the work extends the HSI classification pipeline with a single HSI data cube to multiple HSI data cubes. Each cube, with feature variation, is to be classified of multiple classes. The main challenge is deriving the cube-wise classification from pixel-wise classification. The thesis presents the initial attempt to circumvent it, and discuss the potential for further improvement.

A theory of slow feature analysis for transformation-based input signals with an application to complex cells

We develop a group-theoretical analysis of slow feature analysis for the case where the input data are generated by applying a set of continuous transformations to static templates. As an application of the theory, we analytically derive nonlinear visual receptive fields and show that their optimal stimuli, as well as the orientation and frequency tuning, are in good agreement with previous simulations of complex cells in primary visual cortex (Berkes and Wiskott, 2005). The theory suggests that side and end stopping can be interpreted as a weak breaking of translation invariance. Direction selectivity is also discussed. © 2011 Massachusetts Institute of Technology.

We just make the pictures…?’ How work is portrayed in children’s feature length films

This article explores how adult paid work is portrayed in 'family' feature length films. The study extends previous critical media literature which has overwhelmingly focused on depictions of gender and violence, exploring the visual content of films that is relevant to adult employment. Forty-two G/PG films were analyzed for relevant themes. Consistent with the exploratory nature of the research, themes emerged inductively from the films' content. Results reveal six major themes: males are more visible in adult work roles than women; the division of labour remains gendered; work and home are not mutually exclusive domains; organizational authority and power is wielded in punitive ways; there are avenues to better employment prospects; and status/money is paramount. The findings of the study reflect a range of subject matters related to occupational characteristics and work-related communication and interactions which are typically viewed by children in contemporary society.

Scale adaptive tracking using mean shift and efficient feature matching

The mean shift tracker has achieved great success in visual object tracking due to its efficiency being nonparametric. However, it is still difficult for the tracker to handle scale changes of the object. In this paper, we associate a scale adaptive approach with the mean shift tracker. Firstly, the target in the current frame is located by the mean shift tracker. Then, a feature point matching procedure is employed to get the matched pairs of the feature point between target regions in the current frame and the previous frame. We employ FAST-9 corner detector and HOG descriptor for the feature matching. Finally, with the acquired matched pairs of the feature point, the affine transformation between target regions in the two frames is solved to obtain the current scale of the target. Experimental results show that the proposed tracker gives satisfying results when the scale of the target changes, with a good performance of efficiency.

ESR studies of non-silicate inorganic glasses through their glass transformation ranges

ESR spectra of three inorganic glasses doped with Mn2+ and Fe3+ have been studied through their glass transition temperatures (Tg). Spectral features in each case have been discussed with reference to site symmetries. The intensity of the ESR signal has been bound to decrease in the region of Tg. An attempt has been made to explain this interesting feature on the basis of a two-state model.

Optimal feature extraction for bilingual OCR

Feature extraction in bilingual OCR is handicapped by the increase in the number of classes or characters to be handled. This is evident in the case of Indian languages whose alphabet set is large. It is expected that the complexity of the feature extraction process increases with the number of classes. Though the determination of the best set of features that could be used cannot be ascertained through any quantitative measures, the characteristics of the scripts can help decide on the feature extraction procedure. This paper describes a hierarchical feature extraction scheme for recognition of printed bilingual (Tamil and Roman) text. The scheme divides the combined alphabet set of both the scripts into subsets by the extraction of certain spatial and structural features. Three features viz geometric moments, DCT based features and Wavelet transform based features are extracted from the grouped symbols and a linear transformation is performed on them for the purpose of efficient representation in the feature space. The transformation is obtained by the maximization of certain criterion functions. Three techniques : Principal component analysis, maximization of Fisher's ratio and maximization of divergence measure have been employed to estimate the transformation matrix. It has been observed that the proposed hierarchical scheme allows for easier handling of the alphabets and there is an appreciable rise in the recognition accuracy as a result of the transformations.

On the athermal nature of the beta to omega transformation

One characteristic feature of the athermal beta -> omega transformation is the short time scale of the transformation. So far, no clear understanding of this issue exists. Here we construct a model that includes contributions from a Landau sixth-order free energy density, kinetic energy due to displacement, and the Rayleigh dissipation function to account for the dissipation arising from the rapid movement of the parent product interface during rapid nucleation. We also include the contribution from omega-like fluctuations to local stress. The model shows that the transformation is complete on a time scale comparable to the velocity of sound. The estimated nucleation rate is several orders higher than that for diffusion-controlled transformations. The model predicts that the athermal omega phase is limited to a certain range of alloying composition. The estimated nucleation rate and the size of ``isothermal'' particles beyond 17% Nb are also consistent with experimental results. The model provides an explanation for the reprecipitation process of the omega particles in the ``cleared'' channels formed during deformation of omega-forming alloys. The model also predicts that acoustic emission should be detectable during the formation of the athermal phase. (C) 2011 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.

Shear transformation zone volume determining ductile–brittle transition of bulk metallic glasses

Three-point bending experiments were performed on as-cast and annealed samples of Zr52.5Cu17.9Ni14.6Al10Ti5 (Vit105) bulk metallic glasses over a wide range of temperatures varying from room temperature (293 K) to liquid nitrogen temperature (77 K). The results demonstrated that the free volume decrease due to annealing and/or cryogenic temperature can reduce the propensity for the formation of multiple shear bands and hence deteriorate plastic deformation ability. We clearly observed a sharp ductile-to-brittle transition (DBT), across which microscopic fracture feature transfers from micro-scale vein patterns to nano-scale periodic corrugations. Macroscopically, the corresponding fracture mode changes from ductile shear fracture to brittle tensile fracture. The shear transformation zone volume, taking into account free volume, temperature and strain rate, is proposed to quantitatively characterize the DBT behavior in fracture of metallic glasses.

Feature Matching for Object Localization in the Presence of Uncertainty

We consider the problem of matching model and sensory data features in the presence of geometric uncertainty, for the purpose of object localization and identification. The problem is to construct sets of model feature and sensory data feature pairs that are geometrically consistent given that there is uncertainty in the geometry of the sensory data features. If there is no geometric uncertainty, polynomial-time algorithms are possible for feature matching, yet these approaches can fail when there is uncertainty in the geometry of data features. Existing matching and recognition techniques which account for the geometric uncertainty in features either cannot guarantee finding a correct solution, or can construct geometrically consistent sets of feature pairs yet have worst case exponential complexity in terms of the number of features. The major new contribution of this work is to demonstrate a polynomial-time algorithm for constructing sets of geometrically consistent feature pairs given uncertainty in the geometry of the data features. We show that under a certain model of geometric uncertainty the feature matching problem in the presence of uncertainty is of polynomial complexity. This has important theoretical implications by demonstrating an upper bound on the complexity of the matching problem, an by offering insight into the nature of the matching problem itself. These insights prove useful in the solution to the matching problem in higher dimensional cases as well, such as matching three-dimensional models to either two or three-dimensional sensory data. The approach is based on an analysis of the space of feasible transformation parameters. This paper outlines the mathematical basis for the method, and describes the implementation of an algorithm for the procedure. Experiments demonstrating the method are reported.

Evolution feature oriented model driven product line engineering approach for synergistic and dynamic service evolution in Clouds: four kinds of schema.

The proposed research will focus on developing a novel approach to solve Software Service Evolution problems in Computing Clouds. The approach will support dynamic evolution of the software service in clouds via a set of discovered evolution patterns. An initial survey informed us that such an approach does not exist yet and is in urgent need. Evolution Requirement can be classified into evolution features; researchers can describe the whole requirement by using evolution feature typology, the typology will define the relation and dependency between each features. After the evolution feature typology has been constructed, evolution model will be created to make the evolution more specific. Aspect oriented approach can be used for enhance evolution feature-model modularity. Aspect template code generation technique will be used for model transformation in the end. Product Line Engineering contains all the essential components for driving the whole evolution process.

Confronting the Settler Legacy: Indigenisation and Transformation in South Africa and Zimbabwe

This article examines attempts to negotiate a perceived residual dominance of settler populations in South Africa and Zimbabwe by means of developmental and cultural policies deemed necessary to restore sovereignty to Africans. Indigenisation has become a preferred strategy for reconstructing post-colonial states in Africa: indigenisation of the economy as part of a Third Chimurenga in Zimbabwe and Black Economic Empowerment in the socio-cultural context of Ubuntu in South Africa. These are issues arising from the regional legacy of contested and uneven transitions to majority rule. Identifying how governments frame the ‘settler problem’, and politicise space in doing so, is crucial for understanding post-colonial politics. Indigenisation in Zimbabwe allows the government to maintain a network of patronage and official rhetoric is highly divisive and exclusivist although couched in terms of reclaiming African values and sovereignty. Revival of Ubuntu as a cultural value system in South Africa facilitates a more positive approach to indigenisation, although Black Economic Empowerment displays elitist tendencies and cultural transformation remains controversial and elusive. The perceived need to anchor policy in socially acceptable (i.e., ostensibly indigenous/traditional) contexts has become a prominent feature of post-colonial politics and is indicative of an indigenous turn in Southern African politics.

State-of-the-Art: Transformation Invariant Descriptors

As the popularity of digital videos increases, a large number illegal videos are being generated and getting published. Video copies are generated by performing various sorts of transformations on the original video data. For effectively identifying such illegal videos, the image features that are invariant to various transformations must be extracted for performing similarity matching. An image feature can be its local feature or global feature. Among them, local features are powerful and have been applied in a wide variety of computer vision aplications .This paper focuses on various recently proposed local detectors and descriptors that are invariant to a number of image transformations.

Wirkung von Ernterückständen transgener Pflanzen auf die mikrobielle C- und N-Transformation in landwirtschaftlich genutzten Böden am Beispiel von Bt-Mais

In der vorliegenden Arbeit ging es um die Erarbeitung, Anwendung und Beurteilung von quantitativen Analysenverfahren / Methoden für ein Monitoring von durch Bt-Mais verursachbaren Umwelteffekten im Boden. Die Ausgangsthese besagte, dass sich transgene Maisstreu beim mikrobiellen Abbau anders verhält als konventionelle. Bezugnehmend auf die These wurden zwei Freilandversuche (Freilandmikrokosmenmethode nach Raubuch 1997 über 2 Jahre, Quantifizierung des Maisstreuabbaus mit Hilfe kleiner Bodensäulen über 1 Jahr) und zwei Inkubationsversuche im Labor (INK bei drei verschiedenen Temperaturen über 49 Tage und INK mit verschiedenen landwirtschaftlich genutzten Böden über 49 Tage mit jeweils kontinuierlicher Respirationsratenermittlung nach Isermeyer 1952) sowie Inhaltsstoffbestimmungen der Maisstreu durchgeführt. Für alle Untersuchungen wurde Streu der vier Maissorten Novelis (transgen, Monsanto 810), Nobilis (Isolinie von Novelis), Valmont (transgen, Bt 176, Fa. Syngenta) und Prelude (Isolinie von Valmont) eingesetzt. Nach Beendigung der Laborversuche sowie des Freilandversuches nach der Freilandmikrokosmenmethode wurden mikrobielle Messgrößen wie Adenylategehalt, Ergosterolgehalt, Cmik- und Nmik-Gehalt am Boden-Streu-Gemisch bestimmt. Der Einsatz der Isotopentechnik (Bestimmung von 13C/12C an gemahlenem Boden-Streu-Gemisch bzw. gefriergetrocknetem K2SO4 als Extrakt aus dem Boden-Streu-Gemisch) ermöglichte eine genaue Quantifizierung der abgebauten Maisstreu und brachte dadurch Aufschluss über das Abbauverhalten verschiedener Maissorten. Bezüglich der Ermittlung der mikrobiellen Messgrößen ergab sich für die transgene Sorte Novelis* stets eine durchschnittlich geringere pilzliche Biomasse. Langfristig ergaben sich bei der Kohlenstoff- und Stickstoffdynamik keine Trends hinsichtlich transgener bzw. konventioneller Maisstreu. Sowohl im Freilandversuch nach der Mikrokosmenmethode als auch in den Inkubationsversuchen trat das Phänomen der kurzzeitigen Respirationsratenerhöhung der Mikroorganismen nach Zugabe der transgenen Maissorten auf, welches nicht bei Zugabe der konventionellen Maisstreu auszumachen war. ______________________________