Biomedical subjects

Jitendra Malik

Publications and source records attributed to Jitendra Malik.

8 recordsLinked to original sources

PubMed2006

Recovering 3D human body configurations using shape contexts.

The problem we consider in this paper is to take a single two-dimensional image containing a human figure, locate the joint positions, and use these to estimate the body configuration and pose in three-dimensional space. The basic approach is to store a number of exemplar 2D views of the human body in a variety of different configurations and viewpoints with respect to the camera. On each of these stored views, the locations of the body joints (left elbow, right knee, etc.) are manually marked and labeled for future use. The input image is then matched to each stored view, using the technique of shape context matching in conjunction with a kinematic chain-based deformation model. Assuming that there is a stored view sufficiently similar in configuration and pose, the correspondence process will succeed. The locations of the body joints are then transferred from the exemplar view to the test shape. Given the 2D joint locations, the 3D body configuration and pose are then estimated using an existing algorithm. We can apply this technique to video by treating each frame independently--tracking just becomes repeated recognition. We present results on a variety of data sets.

Algorithms↗

PubMed2006

Three-dimensional morphology and gene expression in the Drosophila blastoderm at cellular resolution I: data acquisition pipeline.

BACKGROUND: To model and thoroughly understand animal transcription networks, it is essential to derive accurate spatial and temporal descriptions of developing gene expression patterns with cellular resolution. RESULTS: Here we describe a suite of methods that provide the first quantitative three-dimensional description of gene expression and morphology at cellular resolution in whole embryos. A database containing information derived from 1,282 embryos is released that describes the mRNA expression of 22 genes at multiple time points in the Drosophila blastoderm. We demonstrate that our methods are sufficiently accurate to detect previously undescribed features of morphology and gene expression. The cellular blastoderm is shown to have an intricate morphology of nuclear density patterns and apical/basal displacements that correlate with later well-known morphological features. Pair rule gene expression stripes, generally considered to specify patterning only along the anterior/posterior body axis, are shown to have complex changes in stripe location, stripe curvature, and expression level along the dorsal/ventral axis. Pair rule genes are also found to not always maintain the same register to each other. CONCLUSION: The application of these quantitative methods to other developmental systems will likely reveal many other previously unknown features and provide a more rigorous understanding of developmental regulatory networks.

Animals↗

PubMed2006

Three-dimensional morphology and gene expression in the Drosophila blastoderm at cellular resolution II: dynamics.

BACKGROUND: To accurately describe gene expression and computationally model animal transcriptional networks, it is essential to determine the changing locations of cells in developing embryos. RESULTS: Using automated image analysis methods, we provide the first quantitative description of temporal changes in morphology and gene expression at cellular resolution in whole embryos, using the Drosophila blastoderm as a model. Analyses based on both fixed and live embryos reveal complex, previously undetected three-dimensional changes in nuclear density patterns caused by nuclear movements prior to gastrulation. Gene expression patterns move, in part, with these changes in morphology, but additional spatial shifts in expression patterns are also seen, supporting a previously proposed model of pattern dynamics based on the induction and inhibition of gene expression. We show that mutations that disrupt either the anterior/posterior (a/p) or the dorsal/ventral (d/v) transcriptional cascades alter morphology and gene expression along both the a/p and d/v axes in a way suggesting that these two patterning systems interact via both transcriptional and morphological mechanisms. CONCLUSION: Our work establishes a new strategy for measuring temporal changes in the locations of cells and gene expression patterns that uses fixed cell material and computational modeling. It also provides a coordinate framework for the blastoderm embryo that will allow increasingly accurate spatio-temporal modeling of both the transcriptional control network and morphogenesis.

Animals↗

PubMed2005

Efficient shape matching using shape contexts.

We demonstrate that shape contexts can be used to quickly prune a search for similar shapes. We present two algorithms for rapid shape retrieval: representative shape contexts, performing comparisons based on a small number of shape contexts, and shapemes, using vector quantization in the space of shape contexts to obtain prototypical shape pieces.

Algorithms↗

PubMed2005

An information maximization model of eye movements.

We propose a sequential information maximization model as a general strategy for programming eye movements. The model reconstructs high-resolution visual information from a sequence of fixations, taking into account the fall-off in resolution from the fovea to the periphery. From this framework we get a simple rule for predicting fixation sequences: after each fixation, fixate next at the location that minimizes uncertainty (maximizes information) about the stimulus. By comparing our model performance to human eye movement data and to predictions from a saliency and random model, we demonstrate that our model is best at predicting fixation locations. Modeling additional biological constraints will improve the prediction of fixation sequences. Our results suggest that information maximization is a useful principle for programming eye movements.

Algorithms↗

PubMed2004

When is scene identification just texture recognition?

Subjects were asked to identify scenes after very brief exposures (<70 ms). Their performance was always above chance and improved with exposure duration, confirming that subjects can get the gist of a scene with one fixation. We propose that a simple texture analysis of the image can provide a useful cue towards rapid scene identification. Our model learns texture features across scene categories and then uses this knowledge to identify new scenes. The texture analysis leads to similar identifications and confusions as subjects with limited processing time. We conclude that early scene identification can be explained with a simple texture recognition model.

Humans↗

PubMed2004

Spectral grouping using the Nyström method.

Spectral graph theoretic methods have recently shown great promise for the problem of image segmentation. However, due to the computational demands of these approaches, applications to large problems such as spatiotemporal data and high resolution imagery have been slow to appear. The contribution of this paper is a method that substantially reduces the computational requirements of grouping algorithms based on spectral partitioning making it feasible to apply them to very large grouping problems. Our approach is based on a technique for the numerical solution of eigenfunction problems known as the Nyström method. This method allows one to extrapolate the complete grouping solution using only a small number of samples. In doing so, we leverage the fact that there are far fewer coherent groups in a scene than pixels.

Algorithms↗

PubMed2004

Learning to detect natural image boundaries using local brightness, color, and texture cues.

The goal of this work is to accurately detect and localize boundaries in natural scenes using local image measurements. We formulate features that respond to characteristic changes in brightness, color, and texture associated with natural boundaries. In order to combine the information from these features in an optimal way, we train a classifier using human labeled images as ground truth. The output of this classifier provides the posterior probability of a boundary at each image location and orientation. We present precision-recall curves showing that the resulting detector significantly outperforms existing approaches. Our two main results are 1) that cue combination can be performed adequately with a simple linear model and 2) that a proper, explicit treatment of texture is required to detect boundaries in natural images.

Algorithms↗