Antipersonnel landmines represent a very serious hazard endangering the lives of many people living in armed conflict counties. The huge number of human lives lost due to this phenomenon has been a strong motivation for this research. Deep Learning (DL) is considered a very useful tool in object detection, image classification, face recognition and other computer vision activities. This paper focuses on DL for the problem of landmines recognition in order to identify its type based on shape features. This research work consists of several stages: gathering a new dataset of Anti-Personnel Mines (APMs) images for training and testing purposes, employing several augmentation strategies to boost the diversity of training data, applying four different Convolutional Neural Network (CNN) models namely VGG, ResNet, MiniGoogleNet and MobileNet, and evaluating their performances on APMs recognition. In conclusion, results indicate that MiniGoogleNet exceed all of other three models in recognizing APMs with the highest accuracy rate of 97%.
Hassan Ali Hassan Ebrahem, Abdelhamid Elwaer, Marwa Solla, Fatima Ben Lashihar, Hala Shaari, Rudwan A. Husain(7-2021)

The main purpose of this paper is to introduce some techniques to overcome 3D missing information visual artefacts problem, holes and blank regions between 3D integral images (holoscopic images) frames encountered with the computer generated 3D integral image, pixel-tracing styles is proposed to achieve a higher performance of generating 3D integral images in terms of execution time, Z-buffer and correct occlusion scheme is also introduced to overcome visual artefact. The methods are based on a 3D integral images ray-tracer containing 3D integral images parser, 3D integral camera model, a 3D integral images renderer and scene transformations. Consequently, fast sequences of 3D integral image frames for animations purposes are generated, experimental results show validation of the strategies to fill in the 3D missing pixels and test on different scenes, improvement in terms of execution time depends on the complexity of the scene is achieved.
Dr. Mahmoud Geat Eljadid, Prof. Amar Aggoun, Dr. Osama Hassan Youssef(1-2014)

3D integral imaging is a true 3D imaging technology. It offers the simplest form that is capable of recording and replaying the true light field 3D scene in the form of a planar intensity distribution, by employing microlens array. There is a new world health crisis threatening the humanity with the spread of Covid-19 (Coronavirus Disease-2019). The Covid-19 belongs to a family of viruses that may cause various symptoms such as pneumonia, fever, breathing difficulty, and lung infection. Real images of Covid-19 patients confirmed by computed tomography CT were used to segment areas of increased attenuation in the lungs, all compatible with ground glass opacities and consolidations. This paper describes a new method to generate an indicative Covid-19 3D integral image models. The method is based on a Multiprocessor Ray Tracing System including Philips viewer, 3D slicer software and unidirectional camera. Experimental results are extremely satisfactory and for the first time it is proved that 3D integral images Covid-19 models are generated through Multiprocessor ray tracing system in order to deep monitoring and visualization to could be aid diagnosis in the absence of RT-PCR kits as demonstrated. A new file format content is created as well.
Dr. Mahmoud Geat Eljadid(3-2022)