Color is known to be highly discriminative for many object recognition tasks, but is difficult to infer from uncontrolled images in which the illuminant is not known. Traditional...
Trevor Owens, Kate Saenko, Trevor Darrell, Ayan Ch...
We devise techniques to manipulate a collection of loosely interpenetrating spheres in threedimensional space. Our study is motivated by the representation and manipulation of mol...
We introduce an efficient statistical modeling technique called Mixture of Principal Components (MPC). This model is a linear extension to the traditional Principal Component Anal...
This paper presents a document image thresholding technique that binarizes badly illuminated document images by the photometric correction. Based on the observation that illuminat...
When we use range finders to observe the shape of an object, many occluded areas may occur. These become holes and gaps in the model and make it undesirable to utilize the model ...