ImageSorter is an image browsing application, which allows an automatic sorting by color, date taken, name, or size.
The idea of ImageSorter is to find images of which you remember how they look but you forgot in which folder they were. If one or several folders are selected, all images from these folders will be visually arranged such that similar images are close to each other. In this sorted display it will be much easier to find a particular image. Selected images can be copied, moved or deleted (right mouse click).
ImageSorter does cache thumbnails and sortings, therefore after images have been loaded once, everything will be much faster.
The current version of ImageSorter is 4.0 BETA for Windows and V2.0.2 for Mac OS X. ImageSorter 3 introduced an Internet image search (Yahoo! and Flickr) and the possibility to search for similar images on the local disk or the Internet. Version 4 has an optimized user interface and is much easier to use. The software profits from a greatly improved stability and run-time performance. Furthermore quite a few suggestions made in the forum have been included. See the change log for a detailed list of changes.
Introduction
The use of digital images has increased enormously over recent years, however searching and browsing large collections of images efficiently remains a problem. Existing applications allow sorting images by name, date or file size. However images cannot be sorted by their content.
Content-based image retrieval (CBIR) systems perform an image search by comparing elementary statistical features of the images. Typical image retrieval systems use low-level features like shape, color or texture, whereas human understanding of an image is considered to be much deeper based on years of acquired knowledge. Due to this “semantic gap” none of these approaches could reach the readiness for marketing until now – mainly because users rate the search results as unsatisfactory. In addition the user has no feedback if all relevant images are found. If no query image is available, the search cannot be performed at all.
The program ImageSorter takes a different approach. The methods for content based image retrieval are not used for searching but for performing an automatic sorting of huge image collections. The current version of ImageSorter sorts images by the similarity of their color layouts. Future versions of the program will support additional ordering criteria. All images within a folder are sorted in such a way, that similar images are positioned close to each other. This sorting scheme makes it much easier to find a particular image within a huge image set.
Naturally also ImageSorter does not understand or recognize image content and cannot distinguish between different people or landscapes. However this program does not need a query image and is suited to display large sets of up to some thousands images in a visually well organized way that can easily be navigated.