Simon Winder

University of Bath | UB · Department of Mathematical Sciences

Various technologies described herein pertain to computing surface normals for points in a point cloud. The point cloud is representative of a measured surface of a physical object. A point in the point cloud can be set as a point of origin, and points in the point cloud can be modeled as electrostatic point charges. Moreover, a point of least elec...

An interactive concept learning image search technique that allows end-users to quickly create their own rules for re-ranking images based on the image characteristics of the images. The image characteristics can include visual characteristics as well as semantic features or characteristics, or may include a combination of both. End-users can then...

Image descriptor quantization technique embodiments are presented which quantize an image descriptor defined by a vector of number elements. This is generally accomplished by lowering the number of bits per number element to a prescribed degree. The resulting quantized image descriptor exhibits minimal loss of matching reliability while at the same...

This paper develops a family of multi-pass image resampling algorithms that use one-dimensional filtering stages to achieve high-quality results at low computational cost. Our key insight is to perform a frequency-domain analysis to ensure that very little aliasing occurs at each stage in the multi-pass transform and to insert additional stages whe...

In this paper, we explore methods for learning local image descriptors from training data. We describe a set of building blocks for constructing descriptors which can be combined together and jointly optimized so as to minimize the error of a nearest-neighbor classifier. We consider both linear and nonlinear transforms with dimensionality reduction...

Local image descriptors that are highly discriminative, computational efficient, and with low storage footprint have long been a dream goal of computer vision research. In this paper, we focus on learning such descriptors, which make use of the DAISY configuration and are simple to compute both sparsely and densely. We develop a new training set of...

Web image search is difficult in part because a handful of keywords are generally insufficient for characterizing the visual properties of an image. Popular engines have begun to provide tags based on simple characteristics of images (such as tags for black and white images or images that contain a face), but such approaches are limited by the fact...

Known object recognition is the task of recognizing specific objects, such as cereal boxes or soda cans. Millions of such objects exist, and finding a computationally feasible method for recognition can be difficult. Ideally, the computational costs should scale with the complexity of the testing image, and not the size of the object database. To a...

Invariant feature descriptors such as SIFT and GLOH have been demonstrated to be very robust for image matching and visual recognition. However, such descriptors are generally parameterised in very high dimensional spaces e.g. 128 dimensions in the case of SIFT. This limits the performance of feature matching techniques in terms of speed and scalab...

In this paper we study interest point descriptors for image matching and 3D reconstruction. We examine the building blocks of descriptor algorithms and evaluate numerous combinations of components. Various published descriptors such as SIFT, GLOH, and Spin images can be cast into our framework. For each candidate algorithm we learn good choices for...

This paper describes a novel multi-view matching framework based on a new type of invariant feature. Our features are located at Harris corners in discrete scale-space and oriented using a blurred local gradient. This defines a rotationally invariant frame in which we sample a feature descriptor, which consists of an 8 × 8 patch of bias/gain normal...

The ability to interactively control viewpoint while watching a video is an exciting application of image-based rendering. The goal of our work is to render dynamic scenes with interactive viewpoint control using a relatively small number of video cameras. In this paper, we show how high-quality video-based rendering of dynamic scenes can be accomp...

Interactive scene walkthroughs have long been an important computer graphics application area. More recently, researchers have developed techniques for constructing photorealistic 3D architectural models from real-world images. We present an image-based rendering system that brings us a step closer to a compelling sense of being there. Whereas many...

This paper describes a novel multi-view matching framework based on a new type of invariant feature. Our features are located at Harris corners in discrete scale-space and oriented using a blurred local gradient. This defines a rotationally invariant frame in which we sample a feature descriptor, which consists of an 8x8 patch of bias/gain normalis...

Typical video footage captured using an off-the-shelf camcorder suffers from limited dynamic range. This paper describes our approach to generate high dynamic range (HDR) video from an image sequence of a dynamic scene captured while rapidly varying the exposure of each frame. Our approach consists of three parts: automatic exposure control during...

I present an overview of primate vision with a particular focus on the processing and representation of spatial features by the visual cortex. I discuss the different neural pathways involved and outline some of the problems that they must solve. Topics covered include attention, saliency, population coding, feedback connections and the role of the...

Neurons in the striate cortex have a compressive contrast response but possess orientation and spatial frequency tuning functions which do not saturate at high contrasts. This suggests that contrast compression is achieved by means of gain control rather than by output saturation. I present the results of including a contrast gain control model as...

I present a simulation of contrast gain control mechanisms operating among transient M-cells in the monkey's retina, in order to investigate the spatial consequences of this interaction. The simulation stages include a realistic viewing model, non-linear receptor model, linear spatial filtering and a saturating output function. Contrast gain contro...

In this paper, we consider competitive neural networks with lateral inhibitory feedback. In the feline LGN, lateral inhibition is known to modulate the gain of NMDA-mediated excita- tion. We formulate a population model for this behaviour in which the excitatory gain of each neuron is modulated as a function of the ratio between current activity an...

Emphasis and MoMuSys are two European ACTS-funded projects which are currently involved in the MPEG-4 standardisation process. MoMuSys has produced an early implementation of the VM for the purposes of performing core experiments and implementing MPEG-4 functionalities. Emphasis has been implementing a real-time oriented version of the VM as a basi...

Local image descriptors that are highly discriminative, computationalefficient, and with low storage footprint have long been a dream goal of computer vision research. In this paper, we focus on learning such descriptors, which make use of the DAISY configuration and are simple to compute both sparsely and densely. We develop a new training set of...

We obtained statistics for the estimation of scale, ori-entation and position for interest points detected using the Harris-Laplace and SIFT DoG detectors [2, 1]. Our test set consisted of images from the Oxford Graffiti data set, and we applied 100 random synthetic affine warps to each with 1 unit of additive Gaussian noise. We detected interest p...

Thesis (Ph. D.)--University of Bath, 1995.