Nette Schultz

An intuitive text input method for touch wheels

In this paper we describe a new method for doing text input with touch sensitive wheels. The method is called Transparent User guided Prediction (TUP). With TUP all characters are assigned to fixed positions on the wheel. A language prediction algorithm is used to make it easy to select the most likely characters. The use of the prediction algorithm is transparent for the users, which makes the use of TUP very intuitive. A prototype of TUP is evaluated against the date stamp method for doing wheel text input. Text entry speed for TUP is about 6-7 words per minute for novice users. This is approximately 30% faster than the date stamp method.

A general scheme for training and optimization of the Grenander deformable template model

General deformable models have reduced the need for hand crafting new models for every new problem, but still most of the general models rely on manual interaction by an expert, when applied to a new problem, e.g. for selecting parameters and initialization. We propose a full and unified scheme for applying the general deformable template model proposed by (Grenander et al., 1991) to a new problem with minimal manual interaction, beside supplying a training set, which can be done by a non-expert user. The main contributions compared to previous work are a supervised learning scheme for the model parameters, a very fast general initialization algorithm and an adaptive likelihood model based on local means. The model parameters are trained by a combination of a 2D shape learning algorithm and a maximum likelihood based criteria. The fast initialization algorithm is based on a search approach using a filter interpretation of the likelihood model.

2D vector-cycle deformable templates

Abstract In this paper the theory of deformable templates as a vector cycle in 2D is described. The deformable template model originated in (Grenander, 1983) and was further investigated in (Grenander et al., 1991). A template vector distribution is induced by parameter distributions from transformation matrices applied to the vector cycle. An approximation in the parameter distribution is introduced. The main advantage by using the deformable template model is the ability to simulate a wide range of objects constrained by e.g. their biological variations, and thereby improve restoration, segmentation and classification tasks. For the segmentation the Metropolis algorithm and simulated annealing are used in a Bayesian scheme to obtain a maximum a posteriori estimator. Different energy functions are introduced and applied to different tasks in a case study. The energy functions are local mean, local gradient and probability measurement. The case study concerns estimation of meat percent in pork carcasses. Given two cross-sectional images – one at the front and one near the ham of the carcass – the areas of lean and fat and a muscle in the lean area are measured automatically by the deformable templates.

MOBILE PROBING KIT: User centered development of personal networks services and applications

Mobile Probing Kit is a low tech and low cost methodology for obtaining inspiration and insights into user needs, requirements and ideas in the early phases of a systems development process. The methodology is developed to identify user needs, requirements and ideas among knowledge workers characterized as being highly nomadic and thus potential users of mobile and ubiquitous technologies. The methodology has been applied in the 1ST MAGNET Beyond project in order to obtain user needs and requirements in the process of developing pilot services. We report on the initial findings from applying this methodology in the early phases of this large scale research and development process.

Structural Inference Using Deformable Models

Deformable models have proved useful in many machine vision applications during the last decade. To increase performance and to make their use computationally feasible they have to be specifically tuned for the application domain. Model identification and parameter estimation are receiving increasing attention. The aim of the paper is by no means to give a thorough treatment of the theory behind deformable models, but to illustrate their merits in three practical applications using different types of deformable models: segmenting nano particles, hybridization filter analysis, and shape analysis in the meat industry. Although not directly developed with remote sensing applications in mind analogous models may be useful in this area.

Bimodal Histogram Transformation Based on Maximum Likelihood Parameter Estimates in Univariate Gaussian Mixtures

This paper presents a bimodal histogram transformation procedure where conjugate gradient optimization is used for estimating maximum likelihood parameters of univariate Gaussian mixtures. The paper only deals with bimodal distributions but extension to multimodal distributions is fairly straightforward. The transformation is suggested as a preprocessing step that provides a standardized input to e.g. a classifier. This approach is used for pixelwise classification in RGB-images of meat.