Abstract
Digital radiological modalities in modern hospitals have led to the producing a variety of a vast amount of digital medical files. Therefore, for the medical image, the authenticity needs to ensure the image belongs to the correct patient, the integrity check to ensure the image has not been modified, and safe transfer are very big challenges. Digital watermarking is being used in broadcast and Internet monitoring, forensic tracking, copy protection, counterfeit deterrence, authentication, copyright communication and e-commerce applications. The basic idea behind digital watermarking is to embed a watermark signal into the host data with the purpose of copyright protection, access control, broadcast monitoring etc. Improvements in performance of watermarking schemes can be obtained by several methods. One way is to make use of computational intelligence techniques by considering image watermarking problem as an optimization problem. Particle swarm optimization is a relatively simple optimization technique, and it is easier to be understood compared with some other evolutionary computation methods. It is widely used in different fields including watermarking technologies. The global convergence of PSO cannot always be guaranteed because the diversity of population is decreased with evolution developed. To deal with this problem, concept of a global convergence guaranteed method called as Quantum behaved Particle Swarm Optimization (QPSO) was developed. Weighted QPSO (WQPSO) is introduced as an improved quantum-behaved particle swarm optimization algorithm. In this chapter we present a secure patient medical images and authentication scheme which enhances the security, confidentiality and integrity of medical images transmitted through the Internet. This chapter proposes a watermarking by invoking particle swarm optimization with its modifications(PSO-QPSO-WQPSO) technique in adaptive quantization index modulation and singular value decomposition in conjunction with discrete wavelet transform (DWT) and discrete cosine transform (DCT). The experimental results show that the proposed algorithm yields a watermark which is invisible to human eyes, robust against a wide variety of common attacks and reliable enough for tracing colluders.