M-HMOGA: A New Multi-Objective Feature Selection Algorithm for Handwritten Numeral Classification
The feature selection process is very important in the field of pattern recognition, which selects the informative features so as to reduce the curse of dimensionality, thus improving the overall classification accuracy. In this paper, a new feature selection approach named Memory-Based Histogram-Or...
Main Authors: | Guha Ritam, Ghosh Manosij, Singh Pawan Kumar, Sarkar Ram, Nasipuri Mita |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2019-06-01
|
Series: | Journal of Intelligent Systems |
Subjects: | |
Online Access: | https://doi.org/10.1515/jisys-2019-0064 |
Similar Items
-
Recognition of Handwritten Arabic and Hindi Numerals Using Convolutional Neural Networks
by: Amin Alqudah, et al.
Published: (2021-02-01) -
Word Extraction and Character Segmentation from Text Lines of Unconstrained Handwritten Bangla Document Images
by: Sarkar Ram, et al.
Published: (2011-11-01) -
Multiclass Recognition of Offline Handwritten Devanagari Characters using CNN
by: Mamta Bisht, et al.
Published: (2020-12-01) -
Development of a Two-Stage Segmentation-Based Word Searching Method for Handwritten Document Images
by: Malakar Samir, et al.
Published: (2018-07-01) -
Handwritten Devanagari Character Recognition Using Layer-Wise Training of Deep Convolutional Neural Networks and Adaptive Gradient Methods
by: Mahesh Jangid, et al.
Published: (2018-02-01)