Sciweavers

24 search results - page 2 / 5
» Prototype Selection for Handwritten Connected Digits Classif...
Sort
View
ICDAR
2011
IEEE
12 years 4 months ago
Tuning between Exponential Functions and Zones for Membership Functions Selection in Voronoi-Based Zoning for Handwritten Charac
— In Handwritten Character Recognition, zoning is rigtly considered as one of the most effective feature extraction techniques. In the past, many zoning methods have been propose...
Sebastiano Impedovo, Giuseppe Pirlo
HIS
2004
13 years 6 months ago
Adaptive Boosting with Leader based Learners for Classification of Large Handwritten Data
Boosting is a general method for improving the accuracy of a learning algorithm. AdaBoost, short form for Adaptive Boosting method, consists of repeated use of a weak or a base le...
T. Ravindra Babu, M. Narasimha Murty, Vijay K. Agr...
OZCHI
2006
ACM
13 years 10 months ago
Saxaren: strengthening informal collaboration among geographically distributed teachers
For people working in situations with few colleagues around, information technology could be used for increased communication with colleagues at other places. One such group is te...
Kristina Groth, Sinna Lindquist, Cristian Bogdan, ...
NIPS
1998
13 years 5 months ago
Making Templates Rotationally Invariant. An Application to Rotated Digit Recognition
This paper describes a simple and efficient method to make template-based object classification invariant to in-plane rotations. The task is divided into two parts: orientation di...
Shumeet Baluja
CORR
2010
Springer
210views Education» more  CORR 2010»
12 years 11 months ago
Classification with Scattering Operators
A scattering vector is a local descriptor including multiscale and multi-direction co-occurrence information. It is computed with a cascade of wavelet decompositions and complex m...
Joan Bruna, Stéphane Mallat