Agglomerative clustering for image segmentation

Mohanta, Partha Pratim; Mukherjee, D.; Acton, Scott T.

doi:10.1109/icpr.2002.1044838

Cited by 6 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…No single algorithm was used on all data, since many different segmentation techniques were tried in parallel with proofreading efforts, and it was counterproductive to re-segment portions already corrected. A typical 2D segmentation step entailed creating boundary probability maps using morphological features 50–52 followed by Boosted Edge Learning 53 , mitochondria detection to reduce false boundaries 54 , followed by watershed segmentation 55 and agglomerative clustering 56 using mean and median boundary values to create 2D segments. The 3D linkage step constructed a linkage graph of consecutive 2D segments in adjacent sections.…”

Section: Methodsmentioning

confidence: 99%

A visual motion detection circuit suggested by Drosophila connectomics

Takemura

Bharioke

Lǚ

et al. 2013

Nature

694

952

View full text Add to dashboard Cite

SummaryAnimal behavior arises from computations in neuronal circuits, but our understanding of these computations has been frustrated by the lack of detailed synaptic connection maps, or connectomes. For example, despite intensive investigations over half a century, the neuronal implementation of local motion detection in the insect visual system remains elusive. Here, we developed a semi-automated pipeline using electron microscopy to reconstruct a connectome, containing 379 neurons and 8,637 chemical synaptic contacts, within the Drosophila optic medulla. By matching reconstructed neurons to examples from light microscopy, we assigned neurons to cell types and assembled a connectome of the medulla's repeating module. Within this module, we identified cell types constituting a motion detection circuit and showed that the connections onto individual motion-sensitive neurons in this circuit were consistent with their direction selectivity. Our results identify cellular targets for future functional investigations, and demonstrate that connectomes can provide key insights into neuronal computations.

show abstract

Section: Methodsmentioning

confidence: 99%

A visual motion detection circuit suggested by Drosophila connectomics

Takemura

Bharioke

Lǚ

et al. 2013

Nature

694

952

View full text Add to dashboard Cite

show abstract

“…Initially, each data element was itself a cluster [8]. Sequentially, the data elements were evaluated for cluster membership by the Euclidean distance between its feature vector and each cluster's epicenter.…”

Section: Agglomerative K-meansmentioning

confidence: 99%

Evolutionary facial feature selection

Baughman¹

2008

Proceedings of the 10th Annual Conference Companion on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

With the growing number of acquired physiological and behavioral biometric samples, biometric data sets are experiencing tremendous growth. As database sizes increase, exhaustive identification searches by matching with entire biometric feature sets become computationally unmanageable. An evolutionary facial feature selector chooses a set of features from prior contextual or meta face features that reduces the search space. This paper discusses and shows the results of an evolutionary computing approach with agglomerative k-means cluster spaces as input parameters into a LDA evaluation function to select facial features from the Carnegie Mellon University Pose, Illumination, and Expression database of human faces (PIE).

show abstract

“…These algorithms not only allow a user to choose a particular clustering granularity, but in many domains [24,18,13] clusters naturally form a hierarchy; that is, clusters are part of other clusters such as in the case of phylogenetic (evolutionary) trees. The popular agglomerative algorithms are easy to implement as they just begin with each point in its own cluster and progressively join two closest clusters to reduce the number of clusters by 1 until k = 1.…”

Section: Standard Agglomerative Clusteringmentioning

confidence: 99%

Using instance-level constraints in agglomerative hierarchical clustering: theoretical and empirical results

Davidson

Ravi

2008

Data Min Knowl Disc

View full text Add to dashboard Cite

Clustering with constraints is a powerful method that allows users to specify background knowledge and the expected cluster properties. Significant work has explored the incorporation of instance-level constraints into non-hierarchical clustering but not into hierarchical clustering algorithms. In this paper we present a formal complexity analysis of the problem and show that constraints can be used to not only improve the quality of the resultant dendrogram but also the efficiency of the algorithms. This is particularly important since many agglomerative style algorithms have running times that are quadratic (or faster growing) functions of the number of instances to be clustered. We present several bounds on the improvement in the running times of algorithms obtainable using constraints.

show abstract

Agglomerative clustering for image segmentation

Cited by 6 publications

References 5 publications

A visual motion detection circuit suggested by Drosophila connectomics

A visual motion detection circuit suggested by Drosophila connectomics

Evolutionary facial feature selection

Using instance-level constraints in agglomerative hierarchical clustering: theoretical and empirical results

Contact Info

Product

Resources

About