In order to reduce the security risk of a commercial aircraft, passengers are not allowed to take certain items in their carry-on baggage. For this reason, human operators are trained to detect prohibited items using a manually controlled baggage screening process. In this paper, we propose the use of an automated method based on multiple Xray views to recognize certain regular objects with highly defined shapes and sizes. The method consists of two steps: 'monocular analysis', to obtain possible detections in each view of a sequence, and 'multiple view analysis', to recognize the objects of interest using matchings in all views. The search for matching candidates is efficiently performed using a lookup table that is computed off-line. In order to illustrate the effectiveness of the proposed method, experimental results on recognizing regular objects -clips, springs and razor blades-in pen cases are shown achieving around 93% accuracy for 120 objects. We believe that it would be possible to design an automated aid in a target detection task using the proposed algorithm.

No abstract

No abstract

Recently, X-rays have been adopted as the principal nondestructive testing method to identify flaws within an object that are undetectable to the naked eye. Automatic inspection using radiographic images has been made possible by incorporating image processing techniques into the process. In a previous work, we proposed a framework to detect flaws in aluminium castings using multiple views. The process consisted of flaw segmentation, matching and finally tracking the flaws along the image sequence. While the previous approach required effective segmentation and matching algorithms, this investigation focuses on a new detection approach. The proposed method combines, simultaneously, information gathered from multiple views of the scene; this does not require searching for correspondences or matching. By gathering all the projections from a 3D point, obtained from a sliding box in the 3D space, we train a classifier to learn to detect simulated flaws using all the evidence available. This paper describes our proposed method and presents its performance record in flaw detections using various classifiers. Our approach yields promising results: 94% of true positives detected with 95% sensitivity in real flaws. We conclude that simultaneously combining information from different points of view is a robust approach to flaw identification.

Within the last years, the classification of variable stars with Machine Learning has become a mainstream area of research. Recently, visualization of time series is attracting more attention in data science as a tool to visually help scientists to recognize significant patterns in complex dynamics. Within the Machine Learning literature, dictionary-based methods have been widely used to encode relevant parts of image data. These methods intrinsically assign a degree of importance to patches in pictures, according to their contribution in the image reconstruction. Inspired by dictionarybased techniques, we present an approach that naturally provides the visualization of salient parts in astronomical light curves, making the analogy between image patches and relevant pieces in time series. Our approach encodes the most meaningful patterns such that we can approximately reconstruct light curves by just using the encoded information. We test our method in light curves from the OGLE-III and StarLight databases. Our results show that the proposed model delivers an automatic and intuitive visualization of relevant light curve parts, such as local peaks and drops in magnitude.