Showing papers by "Jeng-Shyang Pan published in 2003"

An efficient encoding algorithm for vector quantization based on subvector technique

Abstract: In this paper, a new and fast encoding algorithm for vector quantization is presented. This algorithm makes full use of two characteristics of a vector: the sum and the variance. A vector is separated into two subvectors: one is composed of the first half of vector components and the other consists of the remaining vector components. Three inequalities based on the sums and variances of a vector and its two subvectors components are introduced to reject those codewords that are impossible to be the nearest codeword, thereby saving a great deal of computational time, while introducing no extra distortion compared to the conventional full search algorithm. The simulation results show that the proposed algorithm is faster than the equal-average nearest neighbor search (ENNS), the improved ENNS, the equal-average equal-variance nearest neighbor search (EENNS) and the improved EENNS algorithms. Comparing with the improved EENNS algorithm, the proposed algorithm reduces the computational time and the number of distortion calculations by 2.4% to 6% and 20.5% to 26.8%, respectively. The average improvements of the computational time and the number of distortion calculations are 4% and 24.6% for the codebook sizes of 128 to 1024, respectively.

An embedding algorithm for multiple watermarks

Abstract: A new algorithm for embedding several watermarks into the same original source is proposed in this paper. Instead of conventional watermark embedding algorithms that embed one watermark in one specific domain, we propose algorithms for embedding multiple watermarks into different compression domains to protect the ownership of the original images. The proposed schemes for embedding and extraction in different domains vary from the existing methods reported in the literature. Simulation results show their robustness for surviving intentional attacks and, hence, their effectiveness in protecting copyrights. They are also easy to implement.

Parallel Ant Colony Systems

Abstract: In this paper a Parallel Ant Colony System (PACS) is developed. Three communication methods for updating the pheromone level between groups in PACS are proposed and work on the traveling salesman problem using our system is presented. Experimental results based on three well-known traveling salesman data sets demonstrate the proposed PACS is superior to the existing Ant Colony System (ACS) and Ant System (AS) with similar or better running times.

Progressive watermarking techniques with genetic algorithms

Abstract: An innovative watermarking scheme based on progressive transmission with genetic algorithms (GA) is proposed. We implement the watermarking embedding and extraction system in the discrete cosine transform (DCT) domain, and apply the JPEG spectral selection mode for progressive transmission. By employing GA with a proper fitness function into the watermarking system, both the watermark imperceptibility and watermark robustness requirements are considered and optimized. In addition, the embedded watermark can be partly extracted in the receiver side even when the watermarked image is being transmitted. Simulation results show both the robustness and the effectiveness of progressive transmission under different attacking schemes and different bandwidth variations.

A novel VQ-based watermarking scheme with genetic codebook partition

Abstract: A novel watermarking scheme based on vector quantisation (VQ) for digital still images is presented. This scheme begins with the procedure of partitioning the original codebook into two sub-codebooks. To achieve this, two strategies are proposed. The first one requires no complex algorithm and gives the users full freedom for partitioning. The second one is a genetic codebook partition procedure, which has the ability to improve the perfonmance of tile proposed watermarking scheme. After that, the information of codebook partition is served as a secret key and is used in the proposed watermarking scheme. In the embedding procedure, according to the watermark bit to be embedded a sub-codebook is chosen. The traditional VQ nearest codeword search is then performed to obtain the nearest codeword for the input vector. In the extracting procedure, the traditional VQ table lookup procedure is executed. With the same secret key, the hidden watermark bit can be determined by examining which same-codebook the corresponding codeword is belonging to. It is denaonstated that the proposed watermarking scheme provides better quality in watermarked images, stronger robustness under some common attacks, faster encoding time, and effective methods for partitioning codebooks.

Noise suppression for shape-gain vector quantization by index assignment using ant colony systems

Abstract: A pioneer work on index assignment using ant colony systems for shape-gain vector quantization is presented in this paper. SGVQ, descended from VQ, is well recognized as a highly efficient compression method, with which encoding speed is greatly improved without serious degradation in image quality. Our work focuses on the transmission of indices in noisy environment. In order to minimize the impact of channel noise, we use ant colony systems to find out a suitable index assignment. With our approach, channel distortion can be substantially reduced without incurring extra cost such as that in error-detection code and error-correction code.