• Publications
  • Influence
Computer and Robot Vision
This two-volume set is an authoritative, comprehensive, modern work on computer vision that covers all of the different areas of vision with a balanced and unified approach.
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
A fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints, which outperforms all the current efficient CNN networks such as MobileNet, ShuffleNet, and ENet on both standard metrics and the newly introduced performance metrics that measure efficiency on edge devices.
Image Segmentation Techniques
Each of the major classes of image segmentation techniques is defined and several specific examples of each class of algorithm are described, illustrated with examples of segmentations performed on real images.
ESPNetv2: A Light-Weight, Power Efficient, and General Purpose Convolutional Neural Network
We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2, for modeling visual and sequential data. Our network uses group point-wise and depth-wise
Computer vision and image processing
On the use of morphological operators in a class of edge detectors, L. Hertz and R. Schafer a valley-seeking threshold selection technique, and a pattern recognition of binary image objects using morphological shape decomposition.
Structural Descriptions and Inexact Matching
  • L. Shapiro, R. Haralick
  • Computer Science, Medicine
    IEEE Transactions on Pattern Analysis and Machine…
  • 1 May 1981
The structural description of an object and the concepts of exact and inexact matching of two structural descriptions are formally defined and the formula for the expected number of nodes in the tree for backtracking alone and with a forward checking algorithm is developed.
Computer Vision
Computer Vision presents the necessary theory and techniques for students and practitioners who will work in fields where significant information must be extracted automatically from images, a useful resource book for professionals and a core text for both undergraduate and beginning graduate computer vision and imaging courses.
A SIFT descriptor with global context
A feature descriptor is presented that augments SIFT with a global context vector that adds curvilinear shape information from a much larger neighborhood, thus reducing mismatches when multiple local descriptors are similar.
Computer and Robot Vision (Volume II)
Modeling Stylized Character Expressions via Deep Learning
This work first train two Convolutional Neural Networks to recognize the expression of humans and stylized characters independently and utilizes a transfer learning technique to learn the mapping from humans to characters to create a shared embedding feature space.