Aria Pezeshk

Learn More
A system for automatic extraction of various feature layers and recognition of the text content of scanned topographic maps is presented here. Linear features which are often intersecting with the text are first extracted using a novel line representation method and a set of directional morphological operations. Other graphical objects are then removed in(More)
Separation of the text and graphics layers in maps with dense and overlapping sets of features (e.g. topographic maps) is a challenging problem. Multi Angled Parallelism (MAP) provides an efficient tool to detect miscellaneous linear features using directional morphological operations and higher order feature representation. However, in its original(More)
Topographic maps contain a small amount of text compared to other forms of printed documents. Furthermore, the text and graphical components typically intersect with one another thus making the extraction of text a very difficult task. Creating training sets with a suitable size from the actual characters in maps would therefore require the laborious(More)
Text reading in images or video is important step to achieve content retrieval from images. The content retrieve from image or video content useful information it act as clue for many image based applications such as scene understanding, content based image retrieval text based image indexing, industrial automation. Locating or detecting text from complex(More)
Scores produced by statistical classifiers in many clinical decision support systems and other medical diagnostic devices are generally on an arbitrary scale, so the clinical meaning of these scores is unclear. Calibration of classifier scores to a meaningful scale such as the probability of disease is potentially useful when such scores are used by a(More)
Virtual nodule insertion paves the way towards the development of standardized databases of hybrid CT images with known lesions. The purpose of this study was to assess three methods (an established and two newly developed techniques) for inserting virtual lung nodules into CT images. Assessment was done by comparing virtual nodule volume and shape to the(More)
Deep convolutional neural networks (CNNs) form the backbone of many state-of-the-art computer vision systems for classification and segmentation of 2D images. The same principles and architectures can be extended to three dimensions to obtain 3D CNNs that are suitable for volumetric data such as CT scans. In this work, we train a 3D CNN for automatic(More)
The availability of large medical image datasets is critical in many applications, such as training and testing of computer-aided diagnosis systems, evaluation of segmentation algorithms, and conducting perceptual studies. However, collection of data and establishment of ground truth for medical images are both costly and difficult. To address this problem,(More)
The performance of a classifier is largely dependent on the size and representativeness of data used for its training. In circumstances where accumulation and/or labeling of training samples is difficult or expensive, such as medical applications, data augmentation can potentially be used to alleviate the limitations of small datasets. We have previously(More)
  • 1