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

INTRODUCTION (1)

Due to technological growth in electronic gadgets and digital media such as mobiles, tablets, digital cameras, memory cards and many more, there is a big increase in large image collection on our hard drives and in the web storage. The main purpose of capturing photos is to keep and refresh memories about our life events. The new coming trend is to share photos with family and friends using social websites. Nevertheless the growth of images raises challenges such as the difficulty browsing large image set while avoiding large number of duplicates and similar images.

Our goal is to find the diverse representative set and summary of the collection of images. To deal with this problem, we started focusing on a cropped image that is called window. This means that we would like to concentrate on some portion instead of whole image to generate the representative set and summary. This approach is initiated from the idea of n-gram model. An л-gram is a subsequence of n items from a given sequence. It is a model based on text and is widely used in statistical natural language processing. The items in question can be phonemes, syllables, letters, words or base pairs according to the application. We want to see whether this model can be applied to process images and what the outcomes will be. So we proposed two algorithms for windows cropping, namely random and sequence. That is, the cropping points are generated randomly and in sequence respectively.