System and method for clustering data objects in a collection

A computer readable medium storing instructions for wavefront clustering a collection of objects, each object being represented by a set of multi-modal feature vectors, comprising the instructions for:

• randomly selecting a first number of first objects from the collection;
• computing a vector centroid of the first objects using the set of multi-modal feature vectors associated with each object;
• randomly selecting a second number of second objects from the collection;
• identifying a second number of initial cluster centers between the centroid and the second objects;
• and
• performing iterated k-means wavefront clustering around the initial cluster centers to cluster the objects.

A signal for transmitting computer instructions for selecting a set of initial cluster centers in wavefront clustering a collection of objects, each object being represented by a set of multi-modal feature vectors, the instructions comprising:

• randomly selecting a first number of first objects from the collection, the first number being less than a number of objects in the collection;
• computing a vector centroid of the first objects using the set of multi-modal feature vectors associated with each object;
• selecting a second number of second objects from the collection, the second number equaling a desired number of initial cluster centers;
• identifying a second number of initial cluster centers between the centroid and the second objects;
• and
• wavefront clustering the collection of objects using the second number of initial cluster centers.