Laser Marks Classification for Retinal Images based on Convolutional Neural Network
Mustafa Ali Abuzaraida1, Osama Mohamed Elrajubi2
1Mustafa Ali Abuzaraida, Department of Computing, College of Arts and Sciences, Universiti Utara Malaysia, Sintok, Kedah, Malaysia.
2Osama Mohamed Elrajubi, Department of Telecommunications and Networks Information Technology, Misurata University, Misurata, Libya.
Manuscript received on 27 September 2019 | Revised Manuscript received on 09 November 2019 | Manuscript Published on 22 November 2019 | PP: 188-193 | Volume-8 Issue-6S3 September 2019 | Retrieval Number: F10300986S319/19©BEIESP | DOI: 10.35940/ijeat.F1030.0986S319
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Recently, deep learning approaches have been getting more attention in many research fields. Medical imaging field has been attracting widely by deep learning techniques. An example of this field categories are images segmentations, images registration, images classification and retrieval of images database. This paper is presenting a number of experiments to classify rental images using Convolutional Neural Networks (CNN). These images of retinal could contain laser marks which left by the action of the laser on the surface of the retina. (CNN) is defined as trainable multi-stages architecture composed of multiple stages. The inputs and outputs of each stage are a set of arrays which called the feature maps. For the outputs, every feature map is representing a unique feature which extracted from all the regions which located on the input. Basically, every stage is consisted of three layers which are: a filter bank, a non linearity, and a layer of feature pooling. However, the classic (CNN) is normally consisting of three or less number of layers. The results accuracy were appropriate of more than 90%. As a summary of this paper, a number of considerations are listed for possible improvements and future developments.
Keywords: Machine Learning, Image Processing, Deep Learning, Classification, Rental Images, Laser Marks.
Scope of the Article: Classification