Sparse noise minimization in image classification using Genetic Algorithm and DenseNet

Mienye, ID; Kenneth Ainah, P; Emmanuel, ID; Esenogho, E

Abstract

Noise handling is a critical aspect of image processing, which can significantly affect the accuracy of classification and recognition algorithms. In this paper, we propose a technique for improved noise handling in sparse input feature maps where the noise signal is also sparse. The signal-noise relationship is formulated as an optimization problem which is solved by a genetic algorithm. The genetic algorithm is applied to optimize the setting of a non-convexity parameter which yields a more accurate image sparse matrix. The resulting feature map is then classified using a densely connected convolutional network (DenseNet). Lung computed tomography images were used for the experiments. The proposed approach achieves better performance when the classification results are compared with a case in which the input signal has not been denoised using the proposed approach.

Citation

Mienye, I., Kenneth Ainah, P., Emmanuel, I., & Esenogho, E. Sparse noise minimization in image classification using Genetic Algorithm and DenseNet. Presented at 2021 Conference on Information Communications Technology and Society (ICTAS), Durban, South Africa

• Presentation Conference Type: Other
• Conference Name: 2021 Conference on Information Communications Technology and Society (ICTAS)
• Conference Location: Durban, South Africa
• End Date: Mar 11, 2021
• Online Publication Date: Apr 6, 2021
• Publication Date: Mar 11, 2021
• Deposit Date: Apr 23, 2021
• Publicly Available Date: Apr 23, 2021
• Book Title: 2021 Conference on Information Communications Technology and Society (ICTAS)
• ISBN: 9781728180816-(online);-9781728180823-(print-on-demand)
• DOI: https://doi.org/10.1109/ictas50802.2021.9395014
• Publisher URL: https://doi.org/10.1109/ICTAS50802.2021.9395014
• Related Public URLs: https://ieeexplore.ieee.org/xpl/conhome/9394949/proceeding
• Additional Information: Additional Information : ** From Crossref proceedings articles via Jisc Publications Router **History: published 03-2021; Access Information : © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; Event Type : Conference