Abstract. We present a novel template matching framework for detecting geometrically transformed objects. A template is a simplified representation of the object of interest by a s...
In this article, we describe a feature selection algorithm which can automatically find relevant features for multiple instance learning. Multiple instance learning is considered a...
In this paper we are concerned with innovation in the development of mobile applications. In particular, we address how we may come to think systematically about innovative aspects...
Jens Henrik Hosbond, Peter Axel Nielsen, Ivan Aaen
Most existing binaural approaches to speech segregation rely on spatial filtering. In environments with minimal reverberation and when sources are well separated in space, spatial...
John Woodruff, Rohit Prabhavalkar, Eric Fosler-Lus...
A new method for text detection and recognition in natural scene images is presented in this paper. In the detection process, color, texture, and OCR statistic features are combin...