Robust segmentation based tracing using an adaptive wrapper for inducing priors.

Segmentation based tracing algorithms detect the extent and borders of an object in a given frame IZ by propagating results from frames I1 ≤ z < Z. Although application specific tracers have been forthcoming, techniques that automatically adapt across applications have been less explored. We approach this problem by learning a prior model on topological dynamics that encourages segmentation transitions across frames that are most likely for a given application. Further, we augment a generic tracing technique with a locality sensitive prior derived from dense optic flow fields for deformation guidance. The proposed approach comprises two stages where the generic tracer initially yields multiple segmentation transitions when its parameters are perturbed, and the learnt topology prior subsequently propagates high scoring segmentations. Because the learnt topology model wraps around a generic tracer and adapts it by setting its free parameters, the need for careful parameter tuning is completely obviated. Through extensive experimental validation in surveillance, biological and medical image datasets, we verify the applicability of the proposed model while demonstrating good tracing performance under severe clutter.

Scalable tracing of electron micrographs by fusing top down and bottom up cues using hypergraph diffusion.

A novel framework for robust 3D tracing in electron micrographs is presented. The proposed framework is built using ideas from hypergraph diffusion, and achieves two main objectives. Firstly, the approach scales to trace hundreds of targets without noticeable increase in runtime complexity. Secondly, the framework yields flexibility to fuse top down (global cues as hyperedges) and bottom up (local superpixels as nodes) information. Subsequently, a procedure for auto-seeding to initialize the tracing procedure is proposed. The paper concludes with experimental validation on a challenging large scale tracing problem for simultaneously tracing 95 structures, illustrating applicability of the proposed algorithm.

Multiple structure tracing in 3D electron micrographs.

Automatic interpretation of Transmission Electron Micrograph (TEM) volumes is central to advancing current understanding of neural circuitry. In the context of TEM image analysis, tracing 3D neuronal structures is a significant problem. This work proposes a new model using the conditional random field (CRF) framework with higher order potentials for tracing multiple neuronal structures in 3D. The model consists of two key features. First, the higher order CRF cost is designed to enforce label smoothness in 3D and capture rich textures inherent in the data. Second, a technique based on semi-supervised edge learning is used to propagate high confidence structural edges during the tracing process. In contrast to predominantly edge based methods in the TEM tracing literature, this work simultaneously combines regional texture and learnt edge features into a single framework. Experimental results show that the proposed method outperforms more traditional models in tracing neuronal structures from TEM stacks.