Digit recognition with confidence

2011 ◽  
Author(s):  
George E. Sakr ◽  
Imad H. Elhajj
Keyword(s):  
Digit Recognition

DIGIT RECOGNITION USING TENSORFLOW TOOL

2017 ◽  
Vol 4 (3) ◽  
pp. 27
Author(s):  
RAJESH K.V.N. ◽  
RAMESH K.V.N ◽  
HYMAVATHI M ◽  
REDDY K. SYAM SUNDAR ◽  
◽  
...  
Keyword(s):  
Digit Recognition

Multi-Digit Recognition using Image Processing and Neural Network

2021 ◽  
Author(s):  
Anway Shirgaonkar ◽  
Neeraj Sahasrabudhe ◽  
Prathamesh Sandikar ◽  
Tapan Sawant ◽  
Shahid Sayyad ◽  
...  
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Digit Recognition

Energy-Efficient All-Spin BNN Using Voltage-Controlled Spin-Orbit Torque Device for Digit Recognition

2020 ◽  
pp. 1-8
Author(s):  
Sonal Shreya ◽  
Gaurav Verma ◽  
S. N. Piramanayagam ◽  
Brajesh Kumar Kaushik
Keyword(s):  
Energy Efficient ◽  
Spin Orbit ◽  
Digit Recognition

A Novel Sparse Weighted Least Squares Support Vector Classifier

2013 ◽  
Vol 842 ◽  
pp. 746-749
Author(s):  
Bo Yang ◽  
Liang Zhang
Keyword(s):  
Least Squares ◽  
Weighted Least Squares ◽  
Importance Measure ◽  
Support Vector ◽  
Comparative Experiment ◽  
Digit Recognition ◽  
Calculating Method ◽  
Imbalance Problem ◽  
Support Vector Classifier

A novel sparse weighted LSSVM classifier is proposed in this paper, which is based on Suykens weighted LSSVM. Unlike Suykens weighted LSSVM, the proposed weighted method is more suitable for classification. The distance between sample and classification border is used as the sample importance measure in our weighted method. Based on this importance measure, a new weight calculating function, using which can adjust the sparseness of weight, is designed. In order to solve the imbalance problem, a kind of normalization weights calculating method is proposed. Finally, the proposed method is used on digit recognition. Comparative experiment results show that the proposed sparse weighted LSSVM can improve the recognition correct rate effectively.

Sign in / Sign up

Export Citation Format

Share Document