Optic disc (OD) detection is a main step while developing automated screening systems for diabetic retinopathy. We present in this paper a method to automatically detect the position of the OD in digital retinal fundus images. The method starts by normalizing luminosity and contrast through out the image using illumination equalization and adaptive histogram equalization methods respectively. The OD detection algorithm is based on matching the expected directional pattern of the retinal blood vessels. Hence, a simple matched filter is proposed to roughly match the direction of the vessels at the OD vicinity. The retinal vessels are segmented using a simple and standard 2-D Gaussian matched filter. Consequently, a vessels direction map of the segmented retinal vessels is obtained using the same segmentation algorithm. The segmented vessels are then thinned, and filtered using local intensity, to represent finally the OD-center candidates. The difference between the proposed matched filter resized into four different sizes, and the vessels' directions at the surrounding area of each of the OD-center candidates is measured. The minimum difference provides an estimate of the OD-center coordinates. The proposed method was evaluated using a subset of the STARE project's dataset, containing 81 fundus images of both normal and diseased retinas, and initially used by literature OD detection methods. The OD-center was detected correctly in 80 out of the 81 images (98.77%). In addition, the OD-center was detected correctly in all of the 40 images (100%) using the publicly available DRIVE dataset.

Breast cancer is the most widespread type of cancer among women. The diagnosis of breast cancer in its early stages is still a significant problem worldwide. The accurate classification and localization of breast mass help in the early detection of the disease, so in the last few years, a variety of CAD systems are developed to enhance breast cancer classification and localization accuracy, but most of them are fully based on handcrafted feature extraction techniques, which affect its efficiency. Currently, deep learning approaches are able to automatically learn a set of high-level features and consequently, they are achieving remarkable results in object classification and detection tasks. In this paper, the pre-trained ResNet-50 architecture and the Class Activation Map (CAM) technique are employed in breast cancer classification and localization respectively. CAM technique exploits the Convolutional Neural Network (CNN) classifiers with Global Average Pooling (GAP) layer for object localization without any supervised information about its location. According to the experimental results, the proposed approach achieved 96% Area under the Receiver Operating Characteristics (ROC) curve in the classification with 99.8% sensitivity and 82.1% specificity. Furthermore, it is able to localize 93.67% of the masses at an average of 0.122 false positives per image on the Digital Database for Screening Mammography (DDSM) data-set. It is worth noting that the pretrained CNN is able automatically to learn the most discriminative features in the mammogram, and then fulfills superior results in breast cancer classification (normal or mass). Additionally, CAM exhibits the concrete relation between the mass located in the mammogram and the discriminative features learned by the CNN.

An essential part in the construction of a mental picture of a situation is our ability to represent, assess and judge on the skill and competency level of a player, an agent, or any entity that makes decisions. Augmented with a suitable reasoning framework, this ability would allow us to diagnose the competency level of a player through real-time monitoring of their actions. The first key question to ask, is how to assess the skill level of a player from a sequence of actions. Putting it differently, if a strategy maps the objectives of an organization into actions, can we use the actions to assess the skill and competency level of a strategic-decision maker? While this question is traditionally answered through psychological and skill-assessment tests, the objective of the current work is to provide an automated, nonintrusive, passive method to evaluate the skill level of players.In this paper, we will present a framework whereby a computational environment is used to study and assess the competency of a decision maker. We use the game of GO to demonstrate the functionality of the environment. Hundreds of human-played GO games are analyzed in a computational environment. A combination of data mining and time-series analysis is developed to monitor and track the competency level of the human players. We then demonstrate that this methodology is successful in diagnosing problems for some players. The methodology is designed to both augment the construction of a situation awareness picture, as well as a training diagnosis tool.

With extensive applications of face recognition technologies, face anti-spoofing played an important role and has drawn a great attention in the security systems. This study represents a multi-spectral face anti-spoofing method working with both visible (VIS) and near-infrared (NIR) spectra imaging. Spectral imaging is the capture of images in multiple bands. Since these attacks are carried out at the sensor, operating in the visible range, a sensor operating in another band can give more cues regarding the artifact or disguise used to carry out the attack. Our experimental results of public datasets proved that the proposed algorithms gain promising results for different testing scenarios and that our methods can deal with different illuminations and both photo and screen spoofing.