3D Integral Imaging (also referred to as 3D Holoscopic imaging) methodology uses the principle of “Fly’s eye” and hence allows natural viewing of objects (i.e. fatigue free viewing); 3D-holoscopic technology produces images that are true optical models. This technology is based on physical principles with duplication of light fields. In this paper, a new method of visualization medical 3D integral images is proposed. Digital Imaging and Communications in Medicine data images (DICOM) taken from CT, MRI, PET and US images that produced by 3D-Doctor software to generate medical 3D integral images visualization of anatomy without glass in natural light. The method is mainly based on multiprocessor ray tracing system as renderer. The medical 3D content is captured in real time with the content viewed by multiple viewers independently of their position, without the needs of 3D eyewear. Experimental results show validation of the new algorithm and demonstrated that medical 3D integral images content can be displayed on commercially available multi-view auto-stereoscopic display. Medical 3D integral images content is parsed into multiprocessor ray tracing system, consequently, short time of medical 3D integral images movie of such pelvis scene is generated and displayed on PC screen, LCD and Holovizio display.
Dr. Mahmoud Geat Mahmoud Eljadid, Prof. Amar Aggoun(5-2016)

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)

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%. arabic 9 English 69
Hassan Ali Hassan Ebrahem, Abdelhamid Elwaer, Marwa Solla, Fatima Ben Lashihar, Hala Shaari, Rudwan A. Husain(7-2021)