Modeling Invariances in Inferotemporal Cell Tuning

In macaque inferotemporal cortex (IT), neurons have been found to respond selectively to complex shapes while showing broad tuning ("invariance") with respect to stimulus transformations such as translation and scale changes and a limited tuning to rotation in depth. Training monkeys with novel, paperclip-like objects, Logothetis et al. could investigate whether these invariance properties are due to experience with exhaustively many transformed instances of an object or if there are mechanisms that allow the cells to show response invariance also to previously unseen instances of that object. They found object-selective cells in anterior IT which exhibited limited invariance to various transformations after training with single object views. While previous models accounted for the tuning of the cells for rotations in depth and for their selectivity to a specific object relative to a population of distractor objects, the model described here attempts to explain in a biologically plausible way the additional properties of translation and size invariance. Using the same stimuli as in the experiment, we find that model IT neurons exhibit invariance properties which closely parallel those of real neurons. Simulations show that the model is capable of unsupervised learning of view-tuned neurons. The model also allows to make experimentally testable predictions regarding novel stimulus transformations and combinations of stimuli.

Taxonomical musings

In the ‘Object as Subject’ exhibition held at the Stephen Lawrence Gallery, Greenwich University, myself and two other artists showed work which explores the use of the ‘found object’ in their respective practices. My work was selected by the gallery curator David Waterworth. The work exhibited by me, two multi-media pieces and two films, continues my (practice as research) investigation into using everyday objects as starting points for creating work in a variety of mediums including: sculpture, films, installations and multiples. In this work I address a range of subject matters – philosophical, social and cultural. The history of the use of found object in art began in early 20th century European art when Marcel Duchamp and Pablo Picasso independently introduced everyday objects into their practice. My work continues this research.

Closer to life : the work of sari dienes

Like many of her female contemporaries, artist Sari Dienes’s contributions to the art historical dialogue have been largely overlooked in favor of her male counterparts. Often seen as a mentor and mother figure to neo-Dada artists Jasper Johns and Robert Rauschenberg, Dienes was an active member of the New York avant-garde circle surrounding composer/choreographer duo John Cage and Merce Cunningham in the 1950s and 1960s. These social relationships are central to the existing discourse on Sari Dienes, while her work remains little discussed. The fact that her dynamic, ever-changing style lacked aesthetic consistency was commonly lamented by notable figures such as Betty Parsons, however, I argue that Dienes’s diverse oeuvre is unified by her philosophies on art and life. The unification of art and life, denoted clearly by Dienes’s use of the found object, experimentation and chance happenings, and sensory experience, marks her as an innovator and catalyst in the neo-Dada movement as well as in other experimental art endeavors that took place in the aftermath of Abstract Expressionism.

Structuring real-time Object-Z specifications

This paper presents a means of structuring specifications in real-time Object-Z: an integration of Object-Z with the timed refinement calculus. Incremental modification of classes using inheritance and composition of classes to form multi-component systems are examined. Two approaches to the latter are considered: using Object-Z's notion of object instantiation and introducing a parallel composition operator similar to those found in process algebras. The parallel composition operator approach is both more concise and allows more general modelling of concurrency. Its incorporation into the existing semantics of real-time Object-Z is presented.

Land use / land cover change detection: an object oriented approach, Münster, Germany

Dissertation submitted in partial fulfilment of the requirements for the Degree of Master of Science in Geospatial Technologies

Object recognition for autonomous objects: comparison of two approaches

Report for the scientific sojourn at the Swiss Federal Institute of Technology Zurich, Switzerland, between September and December 2007. In order to make robots useful assistants for our everyday life, the ability to learn and recognize objects is of essential importance. However, object recognition in real scenes is one of the most challenging problems in computer vision, as it is necessary to deal with difficulties. Furthermore, in mobile robotics a new challenge is added to the list: computational complexity. In a dynamic world, information about the objects in the scene can become obsolete before it is ready to be used if the detection algorithm is not fast enough. Two recent object recognition techniques have achieved notable results: the constellation approach proposed by Lowe and the bag of words approach proposed by Nistér and Stewénius. The Lowe constellation approach is the one currently being used in the robot localization project of the COGNIRON project. This report is divided in two main sections. The first section is devoted to briefly review the currently used object recognition system, the Lowe approach, and bring to light the drawbacks found for object recognition in the context of indoor mobile robot navigation. Additionally the proposed improvements for the algorithm are described. In the second section the alternative bag of words method is reviewed, as well as several experiments conducted to evaluate its performance with our own object databases. Furthermore, some modifications to the original algorithm to make it suitable for object detection in unsegmented images are proposed.

Fear assessment in pigs exposed to a novel object test

The experiment aimed to study approach and locomotive behaviour as indicators of fear in a novel object test carried out in pigs. Thirty post-weaning (30 kg) and 30 finishing (90 kg) pigs were exposed to visual, auditory and olfactory novel stimuli during 2 different experiments. The facilities consisted of a test pen in which a trough was located. The trough contained chopped apples. Once the animals were trained to enter the test pen individually they were subjected to 3 different fear stimuli. These stimuli were applied in the test pen and next to the trough. The variables studied were feeding behaviour, approach behaviour (the distance and position of the animal with respect to the trough) and locomotive behaviour (general activity, reluctance to move, turning back and retreat attempts). Two groups were studied: saline and midazolam treated group. Twenty minutes before the start of the sessions, 15 post-weaning and finishing pigs received an intramuscular injection of 0.20 and 0.15 mg/kg, respectively, midazolam (Dormicum1). The saline pigs (15 animals per group) were injected with saline. The administration of midazolam increased the feeding behaviour and approaching behaviour, and reduced the locomotive behaviour. In front of the visual and olfactory stimuli post-weaning pigs showed a higher general activity than finishing pigs, but the contrary was found when the auditory stimulus was applied. The olfactory stimulus was more related to the turning back behaviour, whereas the visual stimulus was more related to retreat attempts. Although it could be concluded that reluctant to move was the most common response to the different fear stimuli applied in our study regardless of the age of animals, the combination of reluctant to move and turning back would be a good criterion to assess fear in domestic pigs. The use of midazolam as anxiolytic for studies of fear in commercial conditions in pigs is recommended.

Sex differences: From mental rotation to object location memory, an ERP study

Sex differences in cognition have been largely investigated. The most consistent sex differences favoring females are observed in object location memory involving the left hemisphere whereas the most consistent sex differences favoring males are observed in tasks that require mental rotation involving the right hemisphere. Here we used a task involving these two abilities to see the impact of mental rotation on object location memory. To that end we used a combination of behavioral and event-related potential (ERP) electroencephalography (EEG) measures.A computer screen displayed a square frame of 4 pairs of images (a "teddy" bear, a shoe, an umbrella and a lamp) randomly arranged around a central fixation cross. After a 10-second interval for memorization, images disappeared and were replaced by a test frame with no image but a random pair of two locations marked in black. In addition, this test frame was randomly displayed either in the original orientation (0° rotation) or in the rotated one (90° clockwise - CW - or 90° counterclockwise - CCW). Preceding the test frame, an arrow indicating the presence or the absence of rotation of the frame was displayed on the screen. The task of the participants (15 females and 15 males) was to determine if two marked locations corresponded or not to a pair of identical images. Each response was followed by feedback.Findings showed no significant sex differences in the performance of the original orientation. In comparison with this position, the rotation of the frame produced an equal decrease of male and female performance. In addition, this decrease was significantly higher when the rotation of the frame was in a CCW direction. We further assessed the ERP when the arrow indicated the direction of rotation as stimulus-onset, during four time windows representing major components C1, P1, N1 and N2. Although no sex differences were observed in performance, brain activities differed according to sex. Enhanced amplitudes were found for the CCW compared to CW rotation over the right posterior areas for the P1, N1 and N2 components for men as well as for women. Major topographical differences related to sex were measured for the CW rotation condition as marked lateralized amplitude: left-hemisphere amplitude larger than right one was measured during P1 time range for men. These similar patterns prolonged from P1 to N1 for women. Early distinctions were found in interaction with sex between CCW and CW waveform amplitudes, expressing over anterior electrode sites during C1 time range (0-50 ms post-stimulus).In conclusion (i) women do not outperform men in object location memory in this study (absence of rotation condition); (ii) mental rotation, in particular the direction of rotation, influences performance on object location memory; (iii) CCW rotation is associated with activity in the right parietal hemisphere whereas the CW rotation involves the left parietal hemisphere; (iv) this last effect is less pronounced in males, which could explain why greater involvement of right parietal areas in men and of bilateral posterior areas in women is generally reported in mental rotation tasks; and (v) the early distinctions between both directions of rotation located over anterior sites could be related to sex differences in their respective involvement of control mechanisms.

Sex differences: From mental rotation to object location memory, an ERP study

Sex differences in cognition have been largely investigated. The most consistent sex differences favoring females are observed in object location memory involving the left hemisphere whereas the most consistent sex differences favoring males are observed in tasks that require mental rotation involving the right hemisphere. Here we used a task involving these two abilities to see the impact of mental rotation on object location memory. To that end we used a combination of behavioral and event-related potential (ERP) electroencephalography (EEG) measures.A computer screen displayed a square frame of 4 pairs of images (a "teddy" bear, a shoe, an umbrella and a lamp) randomly arranged around a central fixation cross. After a 10-second interval for memorization, images disappeared and were replaced by a test frame with no image but a random pair of two locations marked in black. In addition, this test frame was randomly displayed either in the original orientation (0° rotation) or in the rotated one (90° clockwise - CW - or 90° counterclockwise - CCW). Preceding the test frame, an arrow indicating the presence or the absence of rotation of the frame was displayed on the screen. The task of the participants (15 females and 15 males) was to determine if two marked locations corresponded or not to a pair of identical images. Each response was followed by feedback.Findings showed no significant sex differences in the performance of the original orientation. In comparison with this position, the rotation of the frame produced an equal decrease of male and female performance. In addition, this decrease was significantly higher when the rotation of the frame was in a CCW direction. We further assessed the ERP when the arrow indicated the direction of rotation as stimulus-onset, during four time windows representing major components C1, P1, N1 and N2. Although no sex differences were observed in performance, brain activities differed according to sex. Enhanced amplitudes were found for the CCW compared to CW rotation over the right posterior areas for the P1, N1 and N2 components for men as well as for women. Major topographical differences related to sex were measured for the CW rotation condition as marked lateralized amplitude: left-hemisphere amplitude larger than right one was measured during P1 time range for men. These similar patterns prolonged from P1 to N1 for women. Early distinctions were found in interaction with sex between CCW and CW waveform amplitudes, expressing over anterior electrode sites during C1 time range (0-50 ms post-stimulus).In conclusion (i) women do not outperform men in object location memory in this study (absence of rotation condition); (ii) mental rotation, in particular the direction of rotation, influences performance on object location memory; (iii) CCW rotation is associated with activity in the right parietal hemisphere whereas the CW rotation involves the left parietal hemisphere; (iv) this last effect is less pronounced in males, which could explain why greater involvement of right parietal areas in men and of bilateral posterior areas in women is generally reported in mental rotation tasks; and (v) the early distinctions between both directions of rotation located over anterior sites could be related to sex differences in their respective involvement of control mechanisms.

Multisensory context portends object memory.

Multisensory processes facilitate perception of currently-presented stimuli and can likewise enhance later object recognition. Memories for objects originally encountered in a multisensory context can be more robust than those for objects encountered in an exclusively visual or auditory context [1], upturning the assumption that memory performance is best when encoding and recognition contexts remain constant [2]. Here, we used event-related potentials (ERPs) to provide the first evidence for direct links between multisensory brain activity at one point in time and subsequent object discrimination abilities. Across two experiments we found that individuals showing a benefit and those impaired during later object discrimination could be predicted by their brain responses to multisensory stimuli upon their initial encounter. These effects were observed despite the multisensory information being meaningless, task-irrelevant, and presented only once. We provide critical insights into the advantages associated with multisensory interactions; they are not limited to the processing of current stimuli, but likewise encompass the ability to determine the benefit of one's memories for object recognition in later, unisensory contexts.

Bag-of-Features Approach to Unsupervised Visual Object Categorisation

The large and growing number of digital images is making manual image search laborious. Only a fraction of the images contain metadata that can be used to search for a particular type of image. Thus, the main research question of this thesis is whether it is possible to learn visual object categories directly from images. Computers process images as long lists of pixels that do not have a clear connection to high-level semantics which could be used in the image search. There are various methods introduced in the literature to extract low-level image features and also approaches to connect these low-level features with high-level semantics. One of these approaches is called Bag-of-Features which is studied in the thesis. In the Bag-of-Features approach, the images are described using a visual codebook. The codebook is built from the descriptions of the image patches using clustering. The images are described by matching descriptions of image patches with the visual codebook and computing the number of matches for each code. In this thesis, unsupervised visual object categorisation using the Bag-of-Features approach is studied. The goal is to find groups of similar images, e.g., images that contain an object from the same category. The standard Bag-of-Features approach is improved by using spatial information and visual saliency. It was found that the performance of the visual object categorisation can be improved by using spatial information of local features to verify the matches. However, this process is computationally heavy, and thus, the number of images must be limited in the spatial matching, for example, by using the Bag-of-Features method as in this study. Different approaches for saliency detection are studied and a new method based on the Hessian-Affine local feature detector is proposed. The new method achieves comparable results with current state-of-the-art. The visual object categorisation performance was improved by using foreground segmentation based on saliency information, especially when the background could be considered as clutter.

Building object-oriented software with the D-Bus messaging system

Object-oriented programming is a widely adopted paradigm for desktop software development. This paradigm partitions software into separate entities, objects, which consist of data and related procedures used to modify and inspect it. The paradigm has evolved during the last few decades to emphasize decoupling between object implementations, via means such as explicit interface inheritance and event-based implicit invocation. Inter-process communication (IPC) technologies allow applications to interact with each other. This enables making software distributed across multiple processes, resulting in a modular architecture with benefits in resource sharing, robustness, code reuse and security. The support for object-oriented programming concepts varies between IPC systems. This thesis is focused on the D-Bus system, which has recently gained a lot of users, but is still scantily researched. D-Bus has support for asynchronous remote procedure calls with return values and a content-based publish/subscribe event delivery mechanism. In this thesis, several patterns for method invocation in D-Bus and similar systems are compared. The patterns that simulate synchronous local calls are shown to be dangerous. Later, we present a state-caching proxy construct, which avoids the complexity of properly asynchronous calls for object inspection. The proxy and certain supplementary constructs are presented conceptually as generic object-oriented design patterns. The e ect of these patterns on non-functional qualities of software, such as complexity, performance and power consumption, is reasoned about based on the properties of the D-Bus system. The use of the patterns reduces complexity, but maintains the other qualities at a good level. Finally, we present currently existing means of specifying D-Bus object interfaces for the purposes of code and documentation generation. The interface description language used by the Telepathy modular IM/VoIP framework is found to be an useful extension of the basic D-Bus introspection format.

Generative Part-Based Gabor Object Detector

Object detection is a fundamental task of computer vision that is utilized as a core part in a number of industrial and scientific applications, for example, in robotics, where objects need to be correctly detected and localized prior to being grasped and manipulated. Existing object detectors vary in (i) the amount of supervision they need for training, (ii) the type of a learning method adopted (generative or discriminative) and (iii) the amount of spatial information used in the object model (model-free, using no spatial information in the object model, or model-based, with the explicit spatial model of an object). Although some existing methods report good performance in the detection of certain objects, the results tend to be application specific and no universal method has been found that clearly outperforms all others in all areas. This work proposes a novel generative part-based object detector. The generative learning procedure of the developed method allows learning from positive examples only. The detector is based on finding semantically meaningful parts of the object (i.e. a part detector) that can provide additional information to object location, for example, pose. The object class model, i.e. the appearance of the object parts and their spatial variance, constellation, is explicitly modelled in a fully probabilistic manner. The appearance is based on bio-inspired complex-valued Gabor features that are transformed to part probabilities by an unsupervised Gaussian Mixture Model (GMM). The proposed novel randomized GMM enables learning from only a few training examples. The probabilistic spatial model of the part configurations is constructed with a mixture of 2D Gaussians. The appearance of the parts of the object is learned in an object canonical space that removes geometric variations from the part appearance model. Robustness to pose variations is achieved by object pose quantization, which is more efficient than previously used scale and orientation shifts in the Gabor feature space. Performance of the resulting generative object detector is characterized by high recall with low precision, i.e. the generative detector produces large number of false positive detections. Thus a discriminative classifier is used to prune false positive candidate detections produced by the generative detector improving its precision while keeping high recall. Using only a small number of positive examples, the developed object detector performs comparably to state-of-the-art discriminative methods.

Winâ Foy : functional object-oriented programming language

This thesis will introduce a new strongly typed programming language utilizing Self types, named Win--*Foy, along with a suitable user interface designed specifically to highlight language features. The need for such a programming language is based on deficiencies found in programming languages that support both Self types and subtyping. Subtyping is a concept that is taken for granted by most software engineers programming in object-oriented languages. Subtyping supports subsumption but it does not support the inheritance of binary methods. Binary methods contain an argument of type Self, the same type as the object itself, in a contravariant position, i.e. as a parameter. There are several arguments in favour of introducing Self types into a programming language (11. This rationale led to the development of a relation that has become known as matching [4, 5). The matching relation does not support subsumption, however, it does support the inheritance of binary methods. Two forms of matching have been proposed (lJ. Specifically, these relations are known as higher-order matching and I-bound matching. Previous research on these relations indicates that the higher-order matching relation is both reflexive and transitive whereas the f-bound matching is reflexive but not transitive (7]. The higher-order matching relation provides significant flexibility regarding inheritance of methods that utilize or return values of the same type. This flexibility, in certain situations, can restrict the programmer from defining specific classes and methods which are based on constant values [21J. For this reason, the type This is used as a second reference to the type of the object that cannot, contrary to Self, be specialized in subclasses. F-bound matching allows a programmer to define a function that will work for all types of A', a subtype of an upper bound function of type A, with the result type being dependent on A'. The use of parametric polymorphism in f-bound matching provides a connection to subtyping in object-oriented languages. This thesis will contain two main sections. Firstly, significant details concerning deficiencies of the subtype relation and the need to introduce higher-order and f-bound matching relations into programming languages will be explored. Secondly, a new programming language named Win--*Foy Functional Object-Oriented Programming Language has been created, along with a suitable user interface, in order to facilitate experimentation by programmers regarding the matching relation. The construction of the programming language and the user interface will be explained in detail.

Natural Object Categorization

This thesis addresses the problem of categorizing natural objects. To provide a criteria for categorization we propose that the purpose of a categorization is to support the inference of unobserved properties of objects from the observed properties. Because no such set of categories can be constructed in an arbitrary world, we present the Principle of Natural Modes as a claim about the structure of the world. We first define an evaluation function that measures how well a set of categories supports the inference goals of the observer. Entropy measures for property uncertainty and category uncertainty are combined through a free parameter that reflects the goals of the observer. Natural categorizations are shown to be those that are stable with respect to this free parameter. The evaluation function is tested in the domain of leaves and is found to be sensitive to the structure of the natural categories corresponding to the different species. We next develop a categorization paradigm that utilizes the categorization evaluation function in recovering natural categories. A statistical hypothesis generation algorithm is presented that is shown to be an effective categorization procedure. Examples drawn from several natural domains are presented, including data known to be a difficult test case for numerical categorization techniques. We next extend the categorization paradigm such that multiple levels of natural categories are recovered; by means of recursively invoking the categorization procedure both the genera and species are recovered in a population of anaerobic bacteria. Finally, a method is presented for evaluating the utility of features in recovering natural categories. This method also provides a mechanism for determining which features are constrained by the different processes present in a multiple modal world.