Automated detection of regions of interest in cartridge case images using deep learning

This paper explores a deep-learning approach to evaluate the position of circular delimiters in cartridge case images. These delimiters define two regions of interest (ROI), corresponding to the breech face and the firing pin impressions, and are placed manually or by an image-processing algorithm. This positioning bears a significant impact on the performance of the image-matching algorithms for firearm identification, and an automated evaluation method would be beneficial to any computerized system. Our contribution consists in optimizing and training U-Net segmentation models from digital images of cartridge cases, intending to locate ROIs automatically. For the experiments, we used high-resolution 2D images from 1195 samples of cartridge cases fired by different 9MM firearms. Our results show that the segmentation models, trained on augmented data sets, exhibit a performance of 95.6% IoU (Intersection over Union) and 99.3% DC (Dice Coefficient) with a loss of 0.014 for the breech face images; and a performance of 95.9% IoU and 99.5% DC with a loss of 0.011 for the firing pin images. We observed that the natural shapes of predicted circles reduce the performance of segmentation models compared with perfect circles on ground truth masks suggesting that our method provide a more accurate segmentation of the real ROI shape. In practice, we believe that these results could be useful for firearms identification. In future work, the predictions may be used to evaluate the quality of delimiters on specimens in a database, or they could determine the region of interest on a cartridge case image.     

U.S. National Identity,Political Elites,and a Patriotic Press Following September 11

In the aftermath of the terrorist attacks on New York City and Washington, D.C. on September 11, 2001, U.S. government and military leaders often articulated distinctly pro-American themes in their public communications. We argue that this national identity discourse was at the heart of the U.S. government's attempt to unite the American public and to mobilize support for the ensuing "war on terrorism." With this perspective, we content analyzed Time and Newsweek newsmagazines for the five weeks following September 11 to identify potential communication strategies employed by government and military leaders to promote a sense of U.S. national identity. Findings suggest (a) that government and military officials consistently emphasized American core values and themes of U.S. strength and power while simultaneously demonizing the "enemy," and (b) that journalists closely paralleled these nationalist themes in their language.     

Do the Media Influence Foreign Aid Because or in Spite of the Bureaucracy? A Case Study of Belgian Aid Determinants

Bureaucrats are considered to play a determining role in how much media signals influence the allocation of foreign aid. As foreign aid decision-making is assumed to be a predominantly bureaucratic matter, bureaucratic responsiveness to media has often been concluded from the observation that foreign aid responds to media attention. Yet, studying this bureaucratic responsiveness directly has proven to be a challenging task due to the difficulties in quantitatively measuring bureaucratic activities. This study examines the different determinants of foreign aid in Belgium from 1995–2008 and addresses the question of bureaucratic responsiveness to media directly by isolating aid that is exclusively decided by the bureaucracy.     

基于深度学习的人体肋骨骨折智能检测技术

目的将人工智能中的深度学习技术应用到人体肋骨骨折识别,实现人体肋骨骨折智能检测,提高法医肋骨骨折诊断效率。方法采集3143例人体胸部X线数字影像(2602例用于训练,541例用于测试),标注肋骨骨折特征点,通过多层网络堆叠,分层、分级主动学习原始数据高度抽象的特征表述,并将此特征反馈至检测器进行骨折检测,输出骨折位置及相应置信度。结果基于深度学习的人体肋骨骨折检测准确率在90%以上。结论基于深度学习的人体肋骨骨折检测准确率较高,可用于辅助法医进行肋骨骨折识别诊断、检验鉴定等,本研究可为人体其他部位骨骼损伤智能检测提供参考。     

Global Television News and Foreign Policy: Debating the CNN Effect

This study investigates the origins and development of the cable news network (CNN) effect hypothesis. It reveals an ongoing debate among politicians, officials, and journalists who are involved in the political processes that this hypothesis attempts to explain, and also among scholars who have been studying it. Debates have been conducted both within and among these groups on the meaning and validity of the CNN effect, but none has contributed significantly to resolving the issue. On the contrary, these debates have presented contradicting statements that have only created confusion and misunderstanding. This study presents lessons from the decade-long effort to explore the CNN effect and projects a new agenda for more useful approaches towards different effects of global communication, apart from those covered by the present controversial hypothesis.     

ForensicNet: Modern convolutional neural network-based image forgery detection network

The advancements in Image editing techniques produce realistic-looking artificial images with ease. These images can easily circumvent the forensic systems making the authentication process more tedious and difficult. To overcome this problem, we introduce a modern convolutional neural network (CNN) named ForensicNet, inspired by the recent developments in computer vision. The three major contributions of our CNNs are inverted bottleneck, separate downsampling layers, and using depth-wise convolutions for mixing information in the spatial dimension. The inverted bottlenecks help improve accuracy and reduce network parameters/FLOPs. The separate downsampling layers help converge the network. The normalization layers also help stabilize training whenever the spatial resolution is changed. The depth-wise convolution is a grouped convolution where the number of groups and channels are the same. The experiments show that ForensicNet outperforms the state-of-the-art methods by a large margin.     

Identification of document paper using hybrid feature extraction

Document forgery is a significant issue in Korea, with around ten thousand cases reported every year. Analyzing paper plays a crucial role in examining questionable documents such as marketable securities and contracts, which can aid in solving criminal cases of document forgery. Paper analysis can also provide essential insights in other types of criminal cases, serving as an important clue for solving cases such as the source of a blackmail letter. The papermaking process generates distinct forming fabric marks and formations, which are critical features for paper classification. These characteristics are observable under transmitted light and are created by the forming fabric pattern and the distribution of pulp fibers, respectively. In this study, we propose a novel approach for paper identification based on hybrid features. This method combines texture features extracted from images converted using the gray-level co-occurrence matrix (GLCM) approach and a convolutional neural network (CNN), with another set of features extracted by the CNN using the same images as input. We applied the proposed method to classification tasks for seven major paper brands available in the Korean market, achieving an accuracy of 97.66%. The results confirm the applicability of this method for visually inspecting paper products and demonstrate its potential for assisting in solving criminal cases involving document forgery.