Showing papers by "Peter Bajcsy published in 2012"

Toward a Recommendation System for Image Similarity Metrics

Abstract: This paper addresses the problem of mapping application specific requirements on image similarity metrics to the plethora of existing image similarity computations. The work is motivated by the fact that there is no method for choosing a similarity metric that is suitable for a given application. We approached the problem by designing a theoretical and experimental framework for creating sensitivity signatures of similarity metrics. In this paper, we outline the classifications of image similarity metrics found in the literature, the space of application parameters and requirements, derivations of similarity dependencies on application parameters, and experimentally obtained sensitivity signatures of similarity metrics using image simulations. These sensitivity signatures provide a way for users to query a reference database of sensitivity signatures and retrieve a recommendation for an image similarity metric. We illustrate the use of the prototype recommendation system by considering spectral calibration and spatial registration application requirements.

How to select microscopy image similarity metrics

Abstract: Comparisons of two microscopy images can be accomplished in many different ways. This paper presents a system that recommends appropriate similarity metrics for microscopy image comparisons based on biological application requirements. The motivation stems from the fact that task requirements can drive the automatic selection of a similarity metric. The suitability of a particular image similarity metric is modeled as the sensitivity and invariance of the metric to microscopy image content and the associated dynamic changes of this content.. In this paper, we describe a mathematical and experimental basis of an image similarity metric recommendation system. In this system, we build a database of sensitivity signatures, and query this reference database to retrieve a similarity metric based on given biological requirements. We illustrate a prototype recommendation system based on synthetic and measured images for spectral calibration and spatial registration applications.

Biases from model assumptions in texture sub-cellular image segmentation

Abstract: Actin is the most abundant protein in most multicellular animal cells. It forms a diverse array of structures, particularly filaments, that participate in important processes such as cell motility, division, and contraction. The location and structure of actin filaments used in cell motility has been studied at whole cell spatial resolution. But studies at the sub-cellular level are limited by the optical diffraction limits of light microscopes and by the destructive nature of imaging at resolutions higher than half of the wavelength of visible light. Previous studies at the sub-cellular level focused on actin interaction with myosin, another protein with which it often works in concert.1 Our work focuses specifically on actin structures, and analyzes sub-cellular regions using optical confocal fluorescent microscopy images at 200 nanometer resolution. Segmentation techniques partition images (in this case, of sub-cellular regions) into segments or sets of pixels. The goal is to simplify the image and make it easier to analyze. Several sub-cellular segmentation techniques, many of which are based on the Gaussian mixture model (GMM) Bayes classifier, have been developed by researchers.2–4 GMM Bayes classifier assumes that cell features follow a Gaussian probability density function and are conditionally independent. Only a few studies have focused on how well cell features actually conform to Bayes classifier GMMs.5 Our objective is to analyze the model biases in these sub-cellular region segmentation techniques and so learn how the sub-cellular structures differ from these Gaussian assumptions. The segmentation technique developed in this work is outlined in Figure 1. We used the gray-level co-occurrence matrix Figure 1. Overview of the segmentation algorithm for biologically meaningful image representation. GMM: Gaussian Mixture Model.