skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Object detection approach using generative sparse, hierarchical networks with top-down and lateral connections for combining texture/color detection and shape/contour detection

Patent ·
OSTI ID:1330321

An approach to detecting objects in an image dataset may combine texture/color detection, shape/contour detection, and/or motion detection using sparse, generative, hierarchical models with lateral and top-down connections. A first independent representation of objects in an image dataset may be produced using a color/texture detection algorithm. A second independent representation of objects in the image dataset may be produced using a shape/contour detection algorithm. A third independent representation of objects in the image dataset may be produced using a motion detection algorithm. The first, second, and third independent representations may then be combined into a single coherent output using a combinatorial algorithm.

Research Organization:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Organization:
USDOE
DOE Contract Number:
AC52-06NA25396
Assignee:
Los Alamos National Security, LLC (Los Alamos, NM)
Patent Number(s):
9,477,901
Application Number:
14/805,540
OSTI ID:
1330321
Resource Relation:
Patent File Date: 2015 Jul 22
Country of Publication:
United States
Language:
English

References (33)

Hierarchical pattern recognition system with variable selection weights patent May 1994
System and method for performing high-precision, multi-channel blending using multiple blending passes patent August 2000
Image editing apparatus and method patent June 2006
Evaluation of images of the brain obtained by means of functional magnetic resonance tomography patent March 2008
Feature selection method using support vector machine classifier patent June 2009
Detecting objects in images with covariance matrices patent June 2010
System for object recognition in colorized point clouds patent July 2013
System and method for exploiting segment co-occurrence relationships to identify object location in images patent July 2014
Intelligent control with hierarchical stacked neural networks patent April 2015
Devices for modulation of retinal stimulation and/or retinal signal processing and methods of use thereof patent October 2015
Methods of fabricating nanostructures and nanowires and devices fabricated therefrom patent-application November 2002
Alternatives to a table of criterion values in signal detection theory journal May 1986
Support-vector networks journal September 1995
ART neural networks for remote sensing: vegetation classification from Landsat TM and terrain data journal March 1997
LIBSVM: A library for support vector machines journal April 2011
Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ1 minimization journal February 2003
Classification of transient signals using sparse representations over adaptive dictionaries conference June 2011
Receptive fields and functional architecture of monkey striate cortex journal March 1968
Task-Driven Dictionary Learning journal April 2012
Sparse Representation for Color Image Restoration journal January 2008
Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position journal April 1980
A model of saliency-based visual attention for rapid scene analysis journal January 1998
Simplified neuron model as a principal component analyzer journal November 1982
Emergence of simple-cell receptive field properties by learning a sparse code for natural images journal June 1996
Trailblazing with Roadrunner journal July 2009
Spatial frequency selectivity of cells in macaque visual cortex journal January 1982
The orientation and direction selectivity of cells in macaque visual cortex journal January 1982
Hierarchical models of object recognition in cortex journal November 1999
Matching pursuits with time-frequency dictionaries journal January 1993
Large-scale functional models of visual cortex for remote sensing conference October 2009
Visualizing classification of natural video sequences using sparse, hierarchical models of cortex. journal May 2011
A feedforward architecture accounts for rapid categorization journal April 2007
Robust Object Recognition with Cortex-Like Mechanisms journal March 2007