Image sorting for your desktop
ImageSorter is a for automatic visual sorting images on your computer. It also does help to find visually similar images on your computer.
We do research
We are constantly researching to improve the way we search for images. We do this in close cooperation with HTW Berlin (University of Applied Sciences).
Have a look at our latest demos and experiments.
Automatic image clustering
palm is an image search engine that groups image search results according to their visual and conceptual similarities. Clustering helps to get an overview of different concepts associated with a query.
Cluster your images to gain overview
Clustering helps to get an overview of different concepts associated with a query. Even with very vague keywords particular images can be found very quickly by focusing on similar clusters or images.
Workflow
The use of the palm image search engine is very simple:
Type one or more keywords and press enter or click “Search”.
The search result will be clustered into 10 groups displayed at the top.
Click a cluster or browse the images shown below.
Clicking an image allows to search for similar images or to build new clusters.
Visual navigation search
PicsLikeThat combines our visual sorting and search solution with our new recommendation technology.
Image navigation the better way
Normal keyword image search systems display sets of 20 to 50 images on separate web pages. Performance is drastically affected when searching for images with particular attributes, because both the semantic relationships between them and the user's intention are unknown to the search system. Homonyms and incorrectly assigned keywords are yet another problem. Usually people do not look at more than 2 or 3 result pages.
Due to the visual sorting, PicsLikeThat can show several hundred images allowing easy inspection. In most cases this is sufficient to get a good overview of the entire search result set. The user can quickly identify desired images, which are used to refine the result by retrieving visually and semantically similar images.
PicsLikeThat uses a semantic network that is learned from the visual appearance of the image, the image keywords and by tracking user interaction.
1. Assume you intend to find pictures with a palm tree at a beach. A search request for "palm" results in various distinct result categories.
2. Double-clicking on any image similar to your desire will serve you more "pics like that"
3. Within a few clicks, the request is narrowed to the desired category.
Semi-automatic image tagging
akiwi is a semi-automatic image tagging system able to suggest keywords for unknown images with minimal user input. Use akiwi to find keywords for your images with just a few clicks.