GENERATING REPRESENTATIVE SETS AND SUMMARIES FOR LARGE COLLECTION OF IMAGES: APPROACH FOR GENERATING (1)

GENERATING (1)

We begin by defining some terminologies. Throughout the report, we use the term photo interchangeably with image, all of which refers to an ordinary 2D image. We define collection as a set of photos and windows as cropped images. The representative set is loosely defined as a subset that captures representativeness, relevance and breadth in the original collection. Well we use two different notations for the random windows and sequential windows. For the random we use IN-C and for the sequence SN-C, where N is number of windows of each image and C is coverage need to be covered. For example with number of random or sequence windows that are 3 and with coverage 85%, we will represent as I3-85 if random images and S3-85 for sequence images respectively. A summary is a set of photos ordered by applying ranking mechanism and selecting any arbitrary number of images from the given representative set.

Given a set of photos P, Our goal is to compute a representative set RS □ P and then summary S □ RS such that S represents highly diverse representative images of set P.

APPROACH FOR GENERATING REPRESENTATIVE SET AND SUMMARY

In this section we introduce the selection criteria for the representative set and overview of the proposed solution.

Selection Criteria

As there is no accurate formal model which constitutes a “good” representative set and summary of a collection of images, we follow some simple heuristics that try to model and capture human attention.

These heuristics are as following:

• Images are taken at a location that provides views of some important objects or landmarks.

• Image is more relevant and should be included in representative set, if it matches with many other images of the collection.

• The representative set and summary should contain highly distinct or diverse images.