Abstract-Traditional video forensics were just for complete video files, which aim at reconstructing the processing history of the video data and validating their origins or authenticity. They have obtained great achievements. However, we cannot always get complete video file in practice, sometime we only get part of it. In this paper, we came up with a method that can restore images of IDR frames from fragmented video files. After analyzing the format of MP4 and H.264/AVC Compression Standard, we proposed an algorithm to search for valid slices from fragment video files. With these slices, images of IDR frames can be restored by reconstructing sequence parameter set and picture parameter set. Test results show that images can be successfully restored in most cases except that FMO or data segmentation is adopted in the process of encoding.

To assist physicians to quickly find the required 3D model from the mass medical model, we propose a novel retrieval method, called DRFVT, which combines the characteristics of dimensionality reduction (DR) and feature vector transformation (FVT) method. The DR method reduces the dimensionality of feature vector; only the top M low frequency Discrete Fourier Transform coefficients are retained. The FVT method does the transformation of the original feature vector and generates a new feature vector to solve the problem of noise sensitivity. The experiment results demonstrate that the DRFVT method achieves more effective and efficient retrieval results than other proposed methods.

No abstract

No abstract

Since dozens years ago, various metaheuristic methods, such as genetic algorithm, ant colony algorithms, have been successfully applied to combinational optimization problem. However, as one of the members, ITO algorithm has only been employed in continuous optimization, it needs further design for combinational optimization problem. In this paper, a discrete ITO algorithm inspired by ITO stochastic process is proposed for travelling salesman problems (TSPs). Some key operators, such as move operator, wave operator, are redesigned to adapt to combinational optimization. Moreover, the performance of ITO algorithm in different parameter selections and the maintenance of population diversity information are also studied. By combining local search methods (such as 2-opt and LK-opt) with ITO algorithm, our computational results of the TSP problems show that ITO algorithm is currently one of the best-performing algorithms for these problems.