Signed in as:
filler@godaddy.com
Signed in as:
filler@godaddy.com
In the field of image processing, I have completed several projects that I would like to share three of them with you. All of these projects were focusing on solving the issue of non-uniform illumination and low contrast images. This issue may cause huge problems in many sectors, such as biomedical, security, and marine science. This issue may occur in the x-ray, microscopic, MRI, underwater, and security camera (CCTV) images. Below I will take you in a short and brief tour of the three most recent projects of mine, to show you how I have used image processing to solve three different issues in the biomedical sector.
Non-uniform illumination and low contrast is an issue major issue for critical and sensitive images. Recently, researchers have shown an interest in solving this issue by proposing local contrast image enhancement methods to improve the contrast of certain regions of the non-uniform illumination and low contrast images. However, most techniques concentrate on developing a specific algorithm to separately enhance only two main regions of the image such as over-exposed and under-exposed regions. Those techniques faced several issues i.e., the pixels are wrongly classified and thus make the enhancement inefficient to solve non-uniform illumination issues as well as poor contrast. These techniques are not robust, and they are specifically designed to solve a specific problem at one time. Also, these techniques have the limitation of measuring the region determination accuracy. These limitations have motivated this study to propose a new technique to solve the above-mentioned problems. An Adaptive Local Exposure Based Region Determination (ALEBRD) method is proposed to determine the image into three specific regions based on the contrast distribution, namely under-exposed, over-exposed, and well-exposed regions. The results of the proposed ALEBRD method produced better region determination performance than the other state-of-the-art methods. This research aims to determine and separate each region individually as a pre-processing stage. The prominent result from this study can be essential for the enhancement process also it can be extended to be applied in further processing such as segmentation and feature extraction. This research also proposed a new novel method to measure the region determination accuracy named Region Determination Accuracy Measurement System (RDAMS). This research is published at Alexandria Engineering Journal, with the impact factor 6.626
“LOCAL NEIGHBOURHOOD IMAGE PROPERTIES FOR EXPOSURE REGION DETERMINATION METHOD IN NONUNIFORM ILLUMINATION IMAGES.”
This project is the most recent project that had been done with the co-operation with the Intelligent system and research team at the school of electrical and electronic engineering at University Science of Malaysia (USM). This study explains the importance of determining the different areas of illumination to the enhancement of nonuniform illumination images. Most determination methods divide the regions of nonuniform illumination images into bright and dark illuminated areas. There are three methods that divide the non-illumination image into three regions which are ALEBRD, Exposure 3R and Backlit. Based on these methods, Backlit and Exposure 3R focus on intensity level only to differentiate the area of illumination while ALEBRD evaluates the contrast of local neighbour based on the intensity. Due to insufficient pixels information since only the intensity is considered by the existing method, thus leading to the inaccurately determine areas. The proposed method addresses this problem by considering two other image attributes, namely, contrast and entropy. All the attributes are determined in the local area. The experimental results show that the proposed method qualitatively produced better results than the other techniques. Additionally, according to the survey results, experts agree and support that the proposed method is better that the current methods in terms of region determination capability. This research is published in April 2020 at IEEE ACCESS ISI journal with an impact factor of 4.098.
“ADAPTIVE FUZZY EXPOSURE LOCAL CONTRAST ENHANCEMENT FOR NON-UNIFORM ILLUMINATION IMAGES.”
This project is based on the results obtained for all three different types of image databases (i.e. standard, underwater and microscopic human sperm images), the two state-of-the-art methods (i.e. Exposure, and FIM) were unable to determine the image into three regions. The reason is both methods only provide a single threshold which can only divide the image into two regions only namely over-exposed and under-exposed. The other state- of-the-art region determination method (i.e. Backlit method) is able to determine the image into three regions. However, the output of the determined regions was lack of accuracy, which leads to miss-classification or over or underdetermine of those regions. On the other hand, the proposed ALEBRD method had successfully overcome the previous issues by providing the best region determination performance. With prominent results presented in this paper, the proposed region determination techniques could be extensively applied in enhancing digital images particularly those with non-uniform illumination issues. In addition, the proposed region determination technique could aid any segmentation process since it can significantly distinguish low contrast regions. This advantage will improve the accuracy of detection and diagnosis in various applications. This research is published in April 2020 at Computing and Visualisation Science ISI journal with the impact factor of 0.69.
ECZEMA BABY SOLUTIONS
This co-operation project with the University of Calgary aims to detect, extract and categorize the eczema stage on the baby skin using mobile application. This research project involved 550000 images for evaluating and classifying and used for training and testing the deep learning of the system.
EcZema Baby strives to make eczema care for children under 4 years more effective, convenient and integrated. EcZema Baby is a comprehensive mobile platform for caregivers of children with eczema, consisting of three interconnected tools that uses machine learning to provide immediate information on their baby’s skin condition, while providing a validated treatment plan.
UAV SURVEILLANCE DRONE
Personal project developed by myself by programming and commanding DJI Drone using Python Programming language and working on object detection and obstacles awareness.
This project is still in the development stage and I share work in my YouTube Channel as a tutorial short videos.
Abdullah Amer Mohammed Salih Jirjees
Copyright © 2024 Abdullah Amer Mohammed Salih Jirjees - All Rights Reserved.
Powered by GoDaddy Website Builder
We use cookies to analyze website traffic and optimize your website experience. By accepting our use of cookies, your data will be aggregated with all other user data.