Digital Image Processing

S. Sumathi ¹, R. Rani Hema Malini ²

Affiliations
1 Sri Sai Ram Engineering College, Chennai-44, Tamilnadu, IN
2 Electronics & Instrumentation Engineering Department, St. Peter's University, Chennai-54, Tamilnadu, IN

Abstract

Face recognition based on biometrics is one of the most hot and challengeable technologies. This paper proposes an efficient technique for identification of an individual. The person identification is done by face recognition using an average half face as a feature. Discrete Wavelet Transform (DWT) is used for feature extraction and Support Vector Machine (SVM) is proposed for classification. The proposed system consists of three phases: (i) Preprocessing, (ii) Feature extraction and (iii) Classification. The proposed method was tested using the cropped extended Yale database, where the images vary in illumination and expression. The experiment was demonstrated with various thresholds. Better results were obtained for a threshold of 0.5. The proposed system shows a high degree of success in identifying the individual with reduced computation time and memory storage saving of 31%.

Keywords

Average Half Face, Discrete Wavelet Transform, Face Recognition, Support Vector Machine.

Full Text

     

P. Surekha ¹, S. Sumathi ¹

Affiliations
1 Electrical and Electronics Engineering Department, PSG College of Technology, Coimbatore – 641 004, IN

Abstract

The increasing effect of illegal exploitation and imitation of digital images in the field of image processing has led to the urgent development in the growth of copyright protection methods. Digital watermarking has proved best in protecting illegal authentication of data. In this paper, we propose a hybrid digital image watermarking scheme based on computational intelligence paradigms like Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The watermark image is embedded into the host image using Discrete Wavelet Transform (DWT). During the extraction process, GA, and PSO are applied to improve the robustness, and fidelity of the watermarked image by evaluating the fitness function. The perceptual transparency and the robustness of the watermarked and the extracted images are evaluated by applying filtering attacks, additive noise, rotation, scaling and  JPEG compression attacks to the watermarked image. From the simulation results the performance of the Particle Swarm Optimization technique is proved best based on the computed robustness and transparency measures along with the evaluated parameters like elapsed time, computation time and fitness value. The performance of proposed scheme was evaluated with a set of 50 textures images taken from online resources of Tampere University of Technology, Finland and the entire algorithm for different stages was simulated using MATLAB R2008b.

Keywords

DWT, Genetic Algorithm, Particle Swarm Optimization, Robustness and Transparency.

Full Text

     

S. Sumathi ¹, M. Y. Sanavullah ²

Affiliations
1 Department of Electrical Engineering, V.M.K.V.Engineering College, Salem, IN
2 Department of Electrical Engineering, K. S. R. College of Technology, and Tiruchengodu, IN

Abstract

This paper presents an algorithm based on the discrete wavelet transform, for feature extraction from the ElectroCardioGraph (ECG) signal and recognition of abnormal heart beats. Wavelets provide simultaneous time and frequency information. The new algorithm detects the R waves as well as Premature Ventricular Contraction (PVC) waves in the ECG signal. The wavelet transform decomposes the ECG signal into a set of frequency band. By using wavelet decomposition, we reduced the amount of data necessary to be processed by the algorithm to less than ten percent of the original data. The adaptive threshold algorithm is implemented with a value greater than that of R waves and less than the value of PVC. For the standard 24 hour Massachusetts Institute of Technology/Beth Isrel Hospital (MIT-BIH) arrhythmia database, this algorithm correctly detects 99.4 percent of the QRS complexes.

Keywords

ECG, QRS Complex Detection, Premature Ventricular Contraction, Discrete Wavelet Transform, Cubic Spline Wavelet.

Full Text