This paper presents a new technique for the automatic classification of audio signals into either speech or music signal. The classification is based on the most efficient five features extracted from the input signal. The correct classification ratio is always better than that using previous algorithms.

No abstract

No abstract

Abstract-The detection of moving objects in a frame sequence is an essential processing component for video surveillance. The main objective of this paper is to create a prototype system that can produce secure streams, ciphertext, for every pixel in the detected moving blobs, plaintext, at a much higher rate to be applicable for real time applications. This approach can be applied in security applications such as anti-theft systems and forensic investigation systems. It could potentially be of benefit to financial investment companies, the military and security forces in order to keep certain information encrypted that no one who does not know exactly how to decrypt will not be able to obtain this information. FPGAs have been used to process larger images at faster speed because of their configuration flexibility and high data processing speed. In this paper, FPGA-based architectures for the proposed privacy and authenticated surveillance system are presented. This design can process 768x576 frame sequence at a very high bit rate that reaches to 40M bit per second in a single FPGA chip, which is adequate for most real-time vision applications.

No abstract