No abstract

Advancements in information and communication technologies have made it easier to forge printed documents these days. Forgery of printed document could have serious repercussions including financial losses, so maintaining the reliability of valuable documents is one that is timely and necessary. The document authentication approach in this study is one that involves tracing of the origin of a document through its contents. The approach explores viability of embedding certain information on printed documents for authentication purposes. Such information could be extracted from the content of documents, which can be divided into two: the context, which includes the text, figures and shapes and the visual attributes of the document, such as its color and design. In short, this study presents a practical and secure method to prevent the forgery of important documents. The proposed method makes use of the public key infrastructure (PKI) and Quick Response (QR) code and the cryptographic hash algorithm shows robustness to printing or scanning noise. The method also makes use of the unique tracking numbers such as device serial numbers, and timestamps enhance the security. To test the feasibility of the method several experiments were perform and the experimental results showed significant improvement in printed document authentication.

No abstract

No abstract

This paper presents a new approach to crime hotspot detection and monitoring. The approach consists of three phases' namely: video analysis, crime prediction and crime mapping. In video analysis, crime indicator events are modelled using statistical distribution of semantic concepts. In crime prediction, a neuro-fuzzy method is used to model indicator events. In crime mapping, kernel density estimation is used to detect crime hotspots. This approach is tested in a simulated platform using violent scene detection (VSD) 2014 dataset.