ACQUINE (Aesthetic Quality Inference Engine) is a machine-learning based online system of computer-based prediction of aesthetic quality for color natural photographic pictures. We believe that this is an important step in computer science research because it shows that computers can learn about and exhibit “emotional responses” to visual stimilus like humans do. It has been developed at Penn State since about 2005. Dr. Ritendra Datta (now with the Google engineering office in Pittsburgh) was the main developer, working with Prof. Jia Li and Prof. James Z. Wang. The system was placed online for public use in April 2009. This is work-in-progress and hence it undergoes algorithmic changes from time to time, in an effort to improve performance. The work is Patent Pending. If you are interested in licensing this technology from Penn State, please contact James Wang.
What is Acquine Designed to Handle?
Acquine is designed mainly to assess the aesthetic quality of color professional photographs. It is NOT designed for computer graphics, artificially-produced diagrams, figures, paintings, composite pictures, casual family photos, screenshots, out-of-focus shots, advertisement images, cartoons, political photos, etc. Please do not upload objectionable photos or any photo containing private information that you do not wish to share with others. We remove uploaded photos inappropriate for this site. Full color photos are more suitable than black-and-white photos. The system is not designed to assess very low resolution images. Our recommended resolution is for photo images with 600×600 or more pixels. Acquine is not designed to rate the look or the attractiveness of a person.
As for most computer-based systems, it is possible to find special cases where the system is clearly not functioning as intended. For instance, one may find that a very poor quality photo gets a good score, or an award-winning photo gets a low score. A rule of thumb is that if the aesthetic quality of a photo is obvious to most people, it may not be worthwhile to seek Acquine’s opinion on it because Acquine may choose to assign funny scores in such cases. Please be serious if you would like Acquine to help you.
How to Use Acquine to Score Photographs:
There are three ways in which Acquine can be seen in action:
- Uploading a Photo from your Local Disk
- Providing an URL of a Photo on the Web
- Show Photos Randomly Sampled from the Photo.net Website
rsizr is a Flash application that lets you resize JPG, PNG, and GIF images on your computer. With rsizr, in addition to normal image rescaling and cropping, you can also resize images using a new image resizing algorithm called seam carving (a method of image retargeting) that tries to keep intact areas in your image that are richer in detail.
Seam carving is a brilliant image resizing technique pioneered by Shai Avidan and Ariel Shamir.
It’s free, of course!
LiteFlick is a fast way to see the most interesting Flickr photos of the day, and display Flickr search results in a nice-looking layout that makes it easy to find what you’re looking for. It uses a jQuery lightbox plugin so you don’t have to load a Flickr page to see a larger version and a caption of each photo.
Flickr’s search results are great, and very detailed, but all the information they give you makes it tough to browse through pages of results looking for something you’ll know when you see it. That’s what makes LiteFlick’s 10 x 8 grid of photos so useful. You can scan through 80 photos in seconds, and easily get more details when you want them. The crucial feature LiteFlick is missing is a Creative-Commons-only search, which would make finding photos for blog posts a whole lot faster.
Anyone who has posted images to a Web site or blog knows that making the image “Internet-friendly” is crucial to fast page-loading times. Similarly, optimizing images for e-mail is important because sending enormous image files through your e-mail client can cause problems for those with slower connection speeds. There are several software tools available to reformat and optimize your images, but I found one recently that’s free, easy, and effective.
RIOT (Radical Image Optimization Tool) (Free) for Windows takes the side-by-side interface approach for painless image optimization. Those who have used Adobe ImageReady will immediately recognize the layout of the interface, with the original image on the left and the optimized image on the right. The file size is listed above both the before and after images, so you can tell how your tweaks will affect the end result. You also can zoom in to see how much your changes effect image details.
If you’ve ever optimized images before, you know that there are many ways to lower image size without degrading the quality of the image to the human eye. RIOT lets you output to Internet-friendly formats like JPEG, GIF, or PNG, and lets you tweak different settings for each format. For a JPEG image, you are given a slider you can adjust to tweak the quality or you can adjust between four levels of Chroma subsampling (Wikipedia link) to reduce size. GIF and PNG formats allow for color reduction (often the most effective method), which you can choose from a dropdown menu or use a slider. Alternatively, RIOT also lets you choose between two predetermined color quantization algorithms to take the guesswork out of optimizing. Our favorite feature is the “Compress to size” button, which lets you pick your optimal size and RIOT gives you the result. Obviously, you’ll need to experiment with this option to get your desired results.
Along with the handy side-by-side optimization features, RIOT offers basic image editing tools like rotation and flip horizontal and vertical. We should point out that RIOT is still in beta, but in all of our tests the software performed without a hitch. One thing we would like to see in future versions is the capability to batch optimize, but as a standalone, free image optimization tool, RIOT is definitely worth checking out.
ThetaWall changes desktop wallpapers periodically using the image files it finds in subdirectories. Perfect for your single-monitor, dual-monitor, triple-monitor, and multi-screen computers, ThetaWall knows how to span images across displays, make collages of many photos, or simply put one image on each monitor. It includes options to enlarge and reduce images to fit, and can even act as a screen saver. No installation is required if you already have the .NET Framework.