Object categorization using bone graphs
نویسندگان
چکیده
منابع مشابه
Object categorization using bone graphs
The bone graph (Macrini et al., in press, 2008) [23,25] is a graph-based medial shape abstraction that offers improved stability over shock graphs and other skeleton-based descriptions that retain unstable ligature structure. Unlike the shock graph, the bone graph’s edges are attributed, allowing a richer specification of relational information, including how and where two medial parts meet. In...
متن کاملObject Categorization Using Kernels Combining Graphs and Histograms of Gradients
This paper presents a method for object categorization. This problem is difficult and can be solved by combining different information sources such as shape or appearance. In this paper, we aim at performing object recognition by mixing kernels obtained from different cues. Our method is based on two complementary descriptions of an object. First, we describe its shape thanks to labeled graphs....
متن کاملImage Categorization Using Directed Graphs
Most existing graph-based semi-supervised classification methods use pairwise similarities as edge weights of an undirected graph with images as the nodes of the graph. Recently several new graph construction methods produce, however, directed graph (asymmetric similarity between nodes). A simple symmetrization is often used to convert a directed graph to an undirected one. This, however, loses...
متن کاملVisual Object Categorization using Topic Models
This project investigates the applicability of image annotation algorithms based on Latent Dirichlet Allocation (LDA) to a task different from the one for which they were originally designed: visual object categorization. We developed a topic model which is based on an existing approach and evaluated its performance on four datasets which we created from the PASCAL database using different feat...
متن کاملPlane-based Object Categorization using Relational Learning
We use Inductive Logic Programming (ILP) to learn classifiers for generic object recognition from point clouds, as generated by 3D cameras, such as the Kinect. Each point cloud is segmented into planar surfaces. Each subset of planes that represents an object is labelled and predicates describing those planes and their relationships are used for learning. Our claim is that a relational descript...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computer Vision and Image Understanding
سال: 2011
ISSN: 1077-3142
DOI: 10.1016/j.cviu.2011.03.002