This paper presents a system for 3D ultrasound which aims to reconstruct a volume of interest from a set of ultrasound images. A Bayesian reconstruction algorithm has been recently...
Histograms of local appearance descriptors are a popular representation for visual recognition. They are highly discriminant with good resistance to local occlusions and to geomet...
We present a new approach to detecting defects in random textures which requires only very few defect free samples for unsupervised training. Each product image is divided into ove...
ABSTRACT: OCR is an error-prone process. It is time-consuming and expensive to manually proofread OCR results. The errors remaining in OCRed texts can cause serious problems in rea...
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...