<title>Finding regions of interest for content extraction</title>

A new cluster isolation criterion based on dissimilarity increments

“…Other optimization-based clustering algorithms do not assume particular cluster shapes, such as the work in [17], proposing a pairwise clustering cost function emphasizing cluster connectedness. Nonparametric density-based clustering methods attempt to identify high-density clusters separated by low-density regions by either exploiting regions of high sample density [18] or regions with less data, such as in valley seeking clustering algorithms [19], [20].…”

“…A final partition is selected among the clustering hierarchy by thresholding techniques or based on measures of cluster validity. Density-based techniques usually define initial clusters by seeking high-density points (by simple use of K-means clustering [28], applying kernel-based density estimation [18] or using density gradient estimation, the modes being detected with the hill climbing mean shift procedure [29], [30]), density similarity guiding the merging process; simple thresholding [28] or cluster validity indices weighting intercluster connectivity and cluster isolation (lowdensity regions separating clusters) [18] are used to select a clustering. In the work in [30], an initial random space tessellation is produced to which a mean shift procedure is applied to detect cluster centers.…”

Finding Consistent Clusters in Data Partitions

“…They provide a means to explore and ascertain structure within the data, by organizing it into groups or clusters. Many clustering algorithms exist in the literature [6,8], from model-based [5,13,16], nonparametric density estimation based methods [15], central clustering [2] and square-error clustering [14], graph theoretical based [4,18], to empirical and hybrid approaches. They all underly some concept about data organization and cluster characteristics.…”

Evidence Accumulation Clustering Based on the K-Means Algorithm

“…Examples of different classes of algorithms are model-based techniques [8,18,23], non-parametric density estimation based methods [21], central clustering [2], square-error clustering [19], and graph theoretical based [4,26] methods. Each handles differently the issues related to cluster validity [1,10,20,8], number of clusters [15,25], and structure imposed on the data [6,24,16]; yet, no single algorithm can adequately handle all sorts of cluster shapes and structures.…”