Feature Selection Based on Evolution Strategy for Character Recognition

Benchaou, Soukaina; Nasri, M’barek; Melhaoui, Ouafae El

doi:10.1142/s0219467818500146

Cited by 10 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Remote sensing images contain rich spectral information, so traditional feature extraction methods cannot achieve good segmentation results. From the perspective of pattern recognition, the selection of typical features is the bottleneck to improve the recognition accuracy [19]. It is impossible to accurately classify all types of ground objects by only using a specific set of features.…”

Section: Introductionmentioning

confidence: 99%

Semantic Segmentation of Remote Sensing Image Based on Convolutional Neural Network and Mask Generation

Niu

2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

High-resolution remote sensing images usually contain complex semantic information and confusing targets, so their semantic segmentation is an important and challenging task. To resolve the problem of inadequate utilization of multilayer features by existing methods, a semantic segmentation method for remote sensing images based on convolutional neural network and mask generation is proposed. In this method, the boundary box is used as the initial foreground segmentation profile, and the edge information of the foreground object is obtained by using the multilayer feature of the convolutional neural network. In order to obtain the rough object segmentation mask, the general shape and position of the foreground object are estimated by using the high-level features in the process of layer-by-layer iteration. Then, based on the obtained rough mask, the mask is updated layer by layer using the neural network characteristics to obtain a more accurate mask. In order to solve the difficulty of deep neural network training and the problem of degeneration after convergence, a framework based on residual learning was adopted, which can simplify the training of those very deep networks and improve the accuracy of the network. For comparison with other advanced algorithms, the proposed algorithm was tested on the Potsdam and Vaihingen datasets. Experimental results show that, compared with other algorithms, the algorithm in this article can effectively improve the overall precision of semantic segmentation of high-resolution remote sensing images and shorten the overall training time and segmentation time.

show abstract

Section: Introductionmentioning

confidence: 99%

Semantic Segmentation of Remote Sensing Image Based on Convolutional Neural Network and Mask Generation

Niu

2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…The solution to the problems associated with different structures mentioned above local languages and their morphological structure requires an individual approach. On that account selection of the most effective features and their application is the main indicator for ensuring accuracy of a specific character and text recognition problems (Ali & Suresha, 2019;Benchaou et al, 2018;Cilia et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Parallel Solution of Features Subset Selection Process for Hand-Printed Character Recognition

Ismayilov¹,

Oil²,

Mammadov³

2019

AzJHPC

View full text Add to dashboard Cite

The existence of a huge amount of features for pattern recognition problems brings to the overloading of the training and exploitation steps of the recognition; also, highly correlated features affect the accuracy of the designed systems negatively. One of the most used ways for tackling this problem is the application of genetic algorithms for the solution of the binary optimization problems that appeared during the features subset selection process. In this paper was used parallel genetic algorithms for the selection of the most informative features in Azerbaijani hand-printed character recognition system by using opportunities of the distributed cluster computing. In this way after the given number of generations most appropriate features with the high recognition rate were selected from the features database.

show abstract

Performance Evaluation of Various Feature Selection Techniques for Offline Handwritten Gurumukhi Place Name Recognition

Kaur

Kumar

2021

Data Driven Approach Towards Disruptive Technologies

View full text Add to dashboard Cite

Feature Selection Based on Evolution Strategy for Character Recognition

Cited by 10 publications

References 9 publications

Semantic Segmentation of Remote Sensing Image Based on Convolutional Neural Network and Mask Generation

Semantic Segmentation of Remote Sensing Image Based on Convolutional Neural Network and Mask Generation

Parallel Solution of Features Subset Selection Process for Hand-Printed Character Recognition

Performance Evaluation of Various Feature Selection Techniques for Offline Handwritten Gurumukhi Place Name Recognition

Contact Info

Product

Resources

About