Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

10

ICPR
2008
IEEE

favoriteEmaildiscussreport

114views Computer Vision» more ICPR 2008»

Novel image feature alphabets for object recognition

13 years 11 months ago

Novel image feature alphabets for object recognition

Download figment.cse.usf.edu

Most successful object recognition systems are based on a visual alphabet of quantised gradient orientations. Here, we introduce two richer image feature alphabets for use in object recognition. The two alphabets are evaluated using the PASCAL VOC challenge 2007 dataset. The results show that both alphabets perform as well as or better than the ’standard‘ gradient orientation based one.

Martin Lillholm, Lewis D. Griffin

Real-time Traffic

Alphabets | Computer Vision | Gradient Orientation | ICPR 2008 | Object Recognition |

claim paper

Related Content

» Incremental learning of object detectors using a visual shape alphabet

» A Novel Approach for Text Detection in Images Using Structural Features

» A genetic approach for building different alphabets for peptide and protein classification

» Object Recognition Using Frequency Domain Blur Invariant Features

» A Novel Null SpaceBased Kernel Discriminant Analysis for Face Recognition

» 3D Probabilistic Feature Point Model for Object Detection and Recognition

» Object Recognition with Features Inspired by Visual Cortex

» A Gesture Recognition System Using 3D Data

» Object Recognition as ManytoMany Feature Matching

Post Info
More Details (n/a)

Added	30 May 2010
Updated	30 May 2010
Type	Conference
Year	2008
Where	ICPR
Authors	Martin Lillholm, Lewis D. Griffin

Comments (0)