Rank Aggregation for Pattern Classifier Selection in Remote Sensing Images

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Multi-q pattern analysis: A case study in image classification

This paper compares the effectiveness of the Tsallis entropy over the classic Boltzmann-Gibbs-Shannon entropy for general pattern recognition, and proposes a multi-q approach to improve pattern analysis using entropy. A series of experiments were carried out for the problem of classifying image patterns. Given a dataset of 40 pattern classes, the goal of our image case study is to assess how well the different entropies can be used to determine the class of a newly given image sample. Our experiments show that the Tsallis entropy using the proposed multi-q approach has great advantages over the Boltzmann-Gibbs-Shannon entropy for pattern classification, boosting image recognition rates by a factor of 3. We discuss the reasons behind this success, shedding light on the usefulness of the Tsallis entropy and the multi-q approach. (C) 2012 Elsevier B.V. All rights reserved.

Zooplankton biomass estimation from digitized images: a comparison between subtropical and Antarctic organisms

The measurement of mesozooplankton biomass in the ocean requires the use of analytical procedures that destroy the samples. Alternatively, the development of methods to estimate biomass from optical systems and appropriate conversion factors could be a compromise between the accuracy of analytical methods and the need to preserve the samples for further taxonomic studies. The conversion of the body area recorded by an optical counter or a camera, by converting the digitized area of an organism into individual biomass, was suggested as a suitable method to estimate total biomass. In this study, crustacean mesozooplankton from subtropical waters were analyzed, and individual dry weight and body area were compared. The obtained relationships agreed with other measurements of biomass obtained from a previous study in Antarctic waters. Gelatinous mesozooplankton from subtropical and Antarctic waters were also sampled and processed for body area and biomass. As expected, differences between crustacean and gelatinous plankton were highly significant. Transparent gelatinous organisms have a lower dry weight per unit area. Therefore, to estimate biomass from digitized images, pattern recognition discerning, at least, between crustaceans and gelatinous forms is required.

An evolutive approach for smile recognition in video sequences

Facial expression recognition is one of the most challenging research areas in the image recognition ¯eld and has been actively studied since the 70's. For instance, smile recognition has been studied due to the fact that it is considered an important facial expression in human communication, it is therefore likely useful for human–machine interaction. Moreover, if a smile can be detected and also its intensity estimated, it will raise the possibility of new applications in the future

Algorithms for on-line image registration from multiple views

Images of a scene, static or dynamic, are generally acquired at different epochs from different viewpoints. They potentially gather information about the whole scene and its relative motion with respect to the acquisition device. Data from different (in the spatial or temporal domain) visual sources can be fused together to provide a unique consistent representation of the whole scene, even recovering the third dimension, permitting a more complete understanding of the scene content. Moreover, the pose of the acquisition device can be achieved by estimating the relative motion parameters linking different views, thus providing localization information for automatic guidance purposes. Image registration is based on the use of pattern recognition techniques to match among corresponding parts of different views of the acquired scene. Depending on hypotheses or prior information about the sensor model, the motion model and/or the scene model, this information can be used to estimate global or local geometrical mapping functions between different images or different parts of them. These mapping functions contain relative motion parameters between the scene and the sensor(s) and can be used to integrate accordingly informations coming from the different sources to build a wider or even augmented representation of the scene. Accordingly, for their scene reconstruction and pose estimation capabilities, nowadays image registration techniques from multiple views are increasingly stirring up the interest of the scientific and industrial community. Depending on the applicative domain, accuracy, robustness, and computational payload of the algorithms represent important issues to be addressed and generally a trade-off among them has to be reached. Moreover, on-line performance is desirable in order to guarantee the direct interaction of the vision device with human actors or control systems. This thesis follows a general research approach to cope with these issues, almost independently from the scene content, under the constraint of rigid motions. This approach has been motivated by the portability to very different domains as a very desirable property to achieve. A general image registration approach suitable for on-line applications has been devised and assessed through two challenging case studies in different applicative domains. The first case study regards scene reconstruction through on-line mosaicing of optical microscopy cell images acquired with non automated equipment, while moving manually the microscope holder. By registering the images the field of view of the microscope can be widened, preserving the resolution while reconstructing the whole cell culture and permitting the microscopist to interactively explore the cell culture. In the second case study, the registration of terrestrial satellite images acquired by a camera integral with the satellite is utilized to estimate its three-dimensional orientation from visual data, for automatic guidance purposes. Critical aspects of these applications are emphasized and the choices adopted are motivated accordingly. Results are discussed in view of promising future developments.

Verkehrsmonitoring mit Hilfe von Radarfernerkundung

Für die Zukunft wird eine Zunahme an Verkehr prognostiziert, gleichzeitig herrscht ein Mangel an Raum und finanziellen Mitteln, um weitere Straßen zu bauen. Daher müssen die vorhandenen Kapazitäten durch eine bessere Verkehrssteuerung sinnvoller genutzt werden, z.B. durch Verkehrsleitsysteme. Dafür werden räumlich aufgelöste, d.h. den Verkehr in seiner flächenhaften Verteilung wiedergebende Daten benötigt, die jedoch fehlen. Bisher konnten Verkehrsdaten nur dort erhoben werden, wo sich örtlich feste Meßeinrichtungen befinden, jedoch können damit die fehlenden Daten nicht erhoben werden. Mit Fernerkundungssystemen ergibt sich die Möglichkeit, diese Daten flächendeckend mit einem Blick von oben zu erfassen. Nach jahrzehntelangen Erfahrungen mit Fernerkundungsmethoden zur Erfassung und Untersuchung der verschiedensten Phänomene auf der Erdoberfläche wird nun diese Methodik im Rahmen eines Pilotprojektes auf den Themenbereich Verkehr angewendet. Seit Ende der 1990er Jahre wurde mit flugzeuggetragenen optischen und Infrarot-Aufnahmesystemen Verkehr beobachtet. Doch bei schlechten Wetterbedingungen und insbesondere bei Bewölkung, sind keine brauchbaren Aufnahmen möglich. Mit einem abbildenden Radarverfahren werden Daten unabhängig von Wetter- und Tageslichtbedingungen oder Bewölkung erhoben. Im Rahmen dieser Arbeit wird untersucht, inwieweit mit Hilfe von flugzeuggetragenem synthetischem Apertur Radar (SAR) Verkehrsdaten aufgenommen, verarbeitet und sinnvoll angewendet werden können. Nicht nur wird die neue Technik der Along-Track Interferometrie (ATI) und die Prozessierung und Verarbeitung der aufgenommenen Verkehrsdaten ausführlich dargelegt, es wird darüberhinaus ein mit dieser Methodik erstellter Datensatz mit einer Verkehrssimulation verglichen und bewertet. Abschließend wird ein Ausblick auf zukünftige Entwicklungen der Radarfernerkundung zur Verkehrsdatenerfassung gegeben.

Deep learning for computer vision: a comparison between convolutional neural networks and hierarchical temporal memories on object recognition tasks

In recent years, Deep Learning techniques have shown to perform well on a large variety of problems both in Computer Vision and Natural Language Processing, reaching and often surpassing the state of the art on many tasks. The rise of deep learning is also revolutionizing the entire field of Machine Learning and Pattern Recognition pushing forward the concepts of automatic feature extraction and unsupervised learning in general. However, despite the strong success both in science and business, deep learning has its own limitations. It is often questioned if such techniques are only some kind of brute-force statistical approaches and if they can only work in the context of High Performance Computing with tons of data. Another important question is whether they are really biologically inspired, as claimed in certain cases, and if they can scale well in terms of "intelligence". The dissertation is focused on trying to answer these key questions in the context of Computer Vision and, in particular, Object Recognition, a task that has been heavily revolutionized by recent advances in the field. Practically speaking, these answers are based on an exhaustive comparison between two, very different, deep learning techniques on the aforementioned task: Convolutional Neural Network (CNN) and Hierarchical Temporal memory (HTM). They stand for two different approaches and points of view within the big hat of deep learning and are the best choices to understand and point out strengths and weaknesses of each of them. CNN is considered one of the most classic and powerful supervised methods used today in machine learning and pattern recognition, especially in object recognition. CNNs are well received and accepted by the scientific community and are already deployed in large corporation like Google and Facebook for solving face recognition and image auto-tagging problems. HTM, on the other hand, is known as a new emerging paradigm and a new meanly-unsupervised method, that is more biologically inspired. It tries to gain more insights from the computational neuroscience community in order to incorporate concepts like time, context and attention during the learning process which are typical of the human brain. In the end, the thesis is supposed to prove that in certain cases, with a lower quantity of data, HTM can outperform CNN.

Pathogen recognition by the long pentraxin PTX3

Innate immunity represents the first line of defence against pathogens and plays key roles in activation and orientation of the adaptive immune response. The innate immune system comprises both a cellular and a humoral arm. Components of the humoral arm include soluble pattern recognition molecules (PRMs) that recognise pathogen-associated molecular patterns (PAMPs) and initiate the immune response in coordination with the cellular arm, therefore acting as functional ancestors of antibodies. The long pentraxin PTX3 is a prototypic soluble PRM that is produced at sites of infection and inflammation by both somatic and immune cells. Gene targeting of this evolutionarily conserved protein has revealed a nonredundant role in resistance to selected pathogens. Moreover, PTX3 exerts important functions at the cross-road between innate immunity, inflammation, and female fertility. Here, we review the studies on PTX3, with emphasis on pathogen recognition and cross-talk with other components of the innate immune system.