Select All | Select None
You can now keep track of new articles from Computer Vision and Image Understanding on your personalized homepage!
Highlights ► Combinatorial maps are an extension of planar graphs in any dimension. ► We formally define map and submap isomorphism for nD open combinatorial maps. ► We give polynomial time algorithms for solving both problems. ► We illustrate the interest of these tools by searching 2D...
Highlights ► Extends vector quantazation to the quantization of graphs. ► Proves the Lloyd-Max conditions for optimality of graph quantization. ► Provides consistency statements for optimal graph quantizer design. ► Presents an accelerated version of competitive learning graph quantization.
Highlights ► Approximate median graph computation. ► Graph embedding into vector spaces. ► Recursive algorithms. ► Graph matching. ► Structural pattern recognition.
Highlights ► The computation of graph prototypes reduces the complexity of graph classification. ► Discriminative prototypes have a better classification power than median graphs. ► Generalized prototypes provide better classification results than set prototypes. ► Dedicated genetic...
Highlights ► We tackle the problem of embedding a set of relational structures into a metric. ► The embedding is defined as a mixture of class-specific submersions from a Riemannian perspective. ► Submersions are recovered using iterative trust-region method. ► The method is general in...
Highlights ► One of the most important points on computing a graph prototype is to compute the common labelling among all graphs in the set. Most of the approaches up to date perform pair-wise graph matching operations in order to compute the common labelling. We present a set of methods to...
Highlights ► A novel shape parsing approach based on the medial axis is presented. ► A shape is decomposed into a set of salient skeletal parts and their relations. ►The parts and relations are captured in a hierarchical abstraction - the bone graph. ► The bone graph avoids the...
Highlights ► We prove structure as a class identity for visual classification. ► We use spectral graph theory as a way to characterise invariant image structures. ► We propose graph energy as a efficient way for image structure extraction.
Highlights ► We compute representative cocycles invariant to scanning and rotation of the object. ► A graph pyramid provides a reduced object-representation (ROR), preserving topology. ► Cocycles in the ROR are down-projected to the original object, in the pyramid. ► Rotation invariance...
results per page
Save this article to read later. You can see your Read Later on your DeepDyve homepage.
To save an article, log in first, or sign up for a DeepDyve account if you don't already have one.
Sign Up Log In
To subscribe to email alerts, please log in first, or sign up for a DeepDyve account if you don't already have one.
Read and print from thousands of top scholarly journals.
Sign up with Facebook
Sign up with Google
Already have an account? Log in
To get new article updates from a journal on your personalized homepage, please log in first, or sign up for a DeepDyve account if you don't already have one.