At its annual research symposium, Microsoft Research demoed many projects that they were working on. We have seen many of them a week before, if you haven’t,find it here. Microsoft Research is also working on couple of mobile research projects based on Windows Phone. The first one is a mobile photography application which lets you take images in your mobile and instead of retouching the photo in the mobile manually, the photo will be uploaded to the cloud where the photo processing such as de-blurring, contrast correction,etc.,will be done automatically and the photo will be pushed back to your phone. The advantage of doing is ,reducing the manual work and power consumption in mobile. See the video below,
The mobile phone is becoming the most popular consumer camera. While the benefits are quite clear, the mobile scenario presents several challenges. It is not always easy to capture good photos. Image-processing tools can improve photos after capture, but there are few tools tailored to on-phone image manipulation. We present phone-based image enhancement tools that are tightly integrated with cloud services. Heavy computation is off-loaded to the cloud, which enables faster results without impacting the phoneâ€™s performance.
The next project is on improving contacts search in mobile using hashing,
Mobile-phone users typically search for contacts in their contact list by keying in names or email IDs. Users frequently make various types of mistakes, including phonetic, transposition, deletion, and substitution errors, and, in the specific case of mobile phones, the nature of the input mechanism makes mistakes more probable. We propose a fuzzy-contact-search feature to help users find the right contacts despite making mistakes while keying in a query. The feature is based on the novel, hashing-based spelling-correction technology developed by Microsoft Research India. We support many languages, including English, French, German, Italian, Spanish, Portuguese, Polish, Dutch, Japanese, Russian, Arabic, Hebrew, Chinese, Korean, and Hindi. We have built a Windows Phone 7 app to demonstrate our fuzzy contact search. The solution is lightweight and can be used in any client-side contact-search scenario.
We have developed a hashing-based technology for addressing both spelling mistakes and multilinguality. The key idea is to represent names by hash codes and transform the problem into a similarity search problem involving hash codes.
Source: Microsoft Research