Performance of Meta-Heuristic Techniques in Freeman Chain Code (FCC) Extraction for Handwritten Character Recognition

Nasien, Dewi; Haron, Habibollah; Yuhaniz, Siti Sophiayati; Azmi, Aini Najwa; Hassan, H.

doi:10.1166/asl.2014.5656

Cited by 2 publications

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

A Multi-Constrained Optimization Method for THz Backward Wave Oscillators

2022

View full text Add to dashboard Cite

The current design period for various backward wave oscillators (BWOs) is still at least several months. How to find the best structure parameters with an efficient and stable optimization method is a problem facing researchers in both scientific research and engineering work. In this paper, a non-randomized iterative optimization method is proposed. It applies orthogonal design methods to find local solutions that can provide optimal ‘gradient direction’ for several successive next iteration steps. An evaluation function is designed to distinguish the better ones from the local solutions in the multi-constrained optimization of such BWOs. Optimizations from different starting points are performed separately for a global optimal solution. Two BWOs at different frequency ranges are optimized using the proposed method. The validity and stability of the method are verified. It is believed that the method can provide the global optimum and shorten the design period of THz BWOs.

show abstract

A Multi-Constrained Optimization Method for THz Backward Wave Oscillators

2022

View full text Add to dashboard Cite

show abstract

New Mechanisms to Enhance the Performances of Arabic Text Recognition System

Amara¹,

Zidi

2017

Handbook of Research on Machine Learning Innovations and Trends

View full text Add to dashboard Cite

The recognition of a character begins with analyzing its form and extracting the features that will be exploited for the identification. Primitives can be described as a tool to distinguish an object of one class from another object of another class. It is necessary to define the significant primitives during the development of an optical character recognition system. Primitives are defined by experience or by intuition. Several primitives can be extracted while some are irrelevant or redundant. The size of vector primitives can be large if a large number of primitives are extracted including redundant and irrelevant features. As a result, the performance of the recognition system becomes poor, and as the number of features increases, so does the computing time. Feature selection, therefore, is required to ensure the selection of a subset of features that gives accurate recognition and has low computational overhead. We use feature selection techniques to improve the discrimination capacity of the Multilayer Perceptron Neural Networks (MLPNNs).

show abstract

Performance of Meta-Heuristic Techniques in Freeman Chain Code (FCC) Extraction for Handwritten Character Recognition

Cited by 2 publications

References 0 publications

A Multi-Constrained Optimization Method for THz Backward Wave Oscillators

A Multi-Constrained Optimization Method for THz Backward Wave Oscillators

New Mechanisms to Enhance the Performances of Arabic Text Recognition System

Contact Info

Product

Resources

About