𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Edge-backpropagation for noisy logo recognition

✍ Scribed by M. Gori; M. Maggini; S. Marinai; J.Q. Sheng; G. Soda

Publisher
Elsevier Science
Year
2003
Tongue
English
Weight
237 KB
Volume
36
Category
Article
ISSN
0031-3203

No coin nor oath required. For personal study only.

πŸ“œ SIMILAR VOLUMES

Noisy logo recognition using line segmen
Noisy logo recognition using line segment Hausdorff distance
✍ Jingying Chen; Maylor K. Leung; Yongsheng Gao πŸ“‚ Article πŸ“… 2003 πŸ› Elsevier Science 🌐 English βš– 540 KB

Logo recognition is of great interest in the document and shape analysis domain. In order to develop a recognition method that is robust to employ under adverse conditions such as di erent scale/orientation, broken curves, added noise and occlusion, a modiΓΏed line segment Hausdor distance is propose

Weight decay backpropagation for noisy d
Weight decay backpropagation for noisy data
✍ Amit Gupta; Siuwa M. Lam πŸ“‚ Article πŸ“… 1998 πŸ› Elsevier Science 🌐 English βš– 283 KB

We present a formal evaluation of the effect of weight decay training for backpropagation on noisy data sets. Weight decay training is suggested as an implementation for achieving a robust neural network which is insensitive to noise. We investigate the noisy situations of noisy training set-clean t

Nonlinear stretching for enhanced learni
Nonlinear stretching for enhanced learning of the backpropagation algorithm in target recognition
✍ Yi Ge; Soyoung S. Cha; Jiajun Zhang; Li Zhang; Anzhi He πŸ“‚ Article πŸ“… 1997 πŸ› John Wiley and Sons 🌐 English βš– 147 KB

## In spite of its relati¨ely slow learning speed, backpropaga-( ) tion BP is one of the most popular neural network training algorithms. Here, a method based on nonlinear stretching is presented that modifies the acti¨ation function in a BP algorithm to speed up the con¨ergence in

A fast algorithm for parallel model comb
A fast algorithm for parallel model combination for noisy speech recognition
✍ Tai-Hwei Hwang; Hsiao-Chuan Wang πŸ“‚ Article πŸ“… 2000 πŸ› Elsevier Science 🌐 English βš– 223 KB

Based on the log-normal assumption, parallel model combination (PMC) provides an effective method to adapt the cepstral means and variances of speech models for noisy speech recognition. In addition, the log-add method has been derived to adapt the mean by ignoring the cepstral variance during the p