Search

Counterfeiting of banknotes is still a severe crime problem in many countries. One of the most significant issue for solving the crime is to classify the counterfeit types and identify the sources. Most of the current methods to classify counterfeit banknotes rely on manual examination that is time-consuming and labor-intensive. Moreover, these methods only detect surface features which can be easily imitated through advanced printing technology. In this study, an automated method based on optical coherence tomography (OCT) and machine-learning algorithms was proposed to classify different types of banknotes based on the internal features. A spectral-domain OCT (SD-OCT) system was employed for sub-surface imaging and quantitative assessment of banknotes. A total of 29 Chinese 100-Yuan banknotes were collected, in which 4 of them were real and 25 of them were counterfeiting by three different printing processes. Each banknote was imaged 10 times in 3 distinct regions, which resulted in a dataset of 290 samples. Each sample was characterized by extracting 2 A-scan (OCT signal intensity along depth) based features and 14B-scan (cross-sectional OCT images) based features. Several machine-learning models, including logistic regression (LR), support vector machines (SVM), K-nearest neighbor (KNN) and random forest (RF), were built and optimized as the classifiers that were trained using 203 samples and applied to predict 87 testing samples. The best performance was achieved by SVM classifier in which the sensitivity of 96.55% and specificity of 98.85% were obtained in discriminating between authentic and counterfeit banknotes, and the sensitivity of 94.67% and specificity of 98.22% were obtained in predicting the types of counterfeit banknotes. These classifiers were also evaluated using the receiver operating characteristic (ROC) curves. To the best of our knowledge, this is the first study where A-scan and B-scan derived features from OCT images have been used for the detection and classification of different types of counterfeit banknotes.

Based on Markov model, this paper analyzes a soft standby's reliability and safety in PUSH system for digital TV, which is constituted by two PUSH VOD severs working on master-slave mode. It illustrates 5 interesting rules that can guide us to design a more reliable and more secure system. We will see some key parameters that is positive correlated with the reliability may be negative correlated with the safety at the same time. What's more, it shows that using different algorithm for mutual checking can hold system's safety even though each algorithm may be not so efficient. Profit evaluations of such hot standby and advices to design are also given. 

Many DRM systems were created to protect content rights, but controversy never ends on the necessity. Doubters believe that the loss of user experience will be greater than profit gained. The key point to be solved, is not proposing a method, but proving the expected revenue is satisfactory. In this paper, a centralized home network content protection system firstly proposed. The management part and evaluation part is built on a special designed intelligent home gateway. It supports multiple domains and functions, and has flexible features. Then, profits of operator and user are both taken into consideration. Proposed content protection scheme is proved practical by game theory. Compared with previous systems, the system has many advantages. 

Face recognition is widely used in public security field. Surveillance video is a major source of probe faces for suspects search. For economic reasons, most social monitors are equipped with analog cameras. When Signals are displayed on PC, interlaced effect will appear. However, after the application of existing methods of de-interlacing, images would lose definition and identification rate would reduce. We proposed a novel sharpening method based on unsharp mask for preprocessing in face recognition. In this paper, we compared different methods of image sharpening. Then we showed the algorithm implementation under the framework of DirectShow. Proposed method makes significant improvement in image clarity and algorithm complexity.

With the internet's influence, an obvious trend can be seen that digital TV industry will embrace multi-screen and IP-based technology. Due to Chinese specific political environment, how to make sure the TV's contents controllable has become a key problem when the contents are accepted by more and more non-TV terminals like Android phones. In this paper, we focus on digital home network environment where Android terminals receive TV contents and display them with authorization. We introduce a new architecture for Android applications where an installed app works as a translator can run mobile code (Code that's loaded from server at runtime) through our defined android xml drama. What's more, we build an Android Digital Right Management (DRM) system referenced by China DRM Technical specification on that architecture. We show that DRM can effectively protect TV contents and mobile code can provide at least 2 benefits: first, it can protect some important code from exposure, second, it can keep the Android app's flexibility.