Groupwise non-rigid image alignment is a difficult non-linear optimization problem involving many parameters and often large datasets. Previous methods have explored various metrics and optimization strategies. Good results have been previously achieved with simple metrics, requiring complex optimization, often with many unintuitive parameters that require careful tuning for each dataset. In this chapter, the problem is restructured to use a simpler, iterative optimization algorithm, with very few free parameters. The warps are refined using an iterative Levenberg-Marquardt minimization to the mean, based on updating the locations of a small number of points and incorporating a stiffness constraint. This optimization approach is eff

  Recently, biometric technologies are used widely due to their improved security that decreases cases of deception and theft. The biometric technologies use physical features and characters in the identification of individuals. The most common biometric technologies are: Iris, voice, fingerprint, handwriting and hand print. In this paper, two biometric recognition technologies are analyzed and compared, which are the iris and sound recognition techniques. The iris recognition technique recognizes persons by analyzing the main patterns in the iris structure, while the sound recognition technique identifies individuals depending on their unique voice characteristics or as called voice print. The comparison results show that the resul

Most includeding techniques of digital watermark even now working through the direct inclusion in the pixel without taking into account the level of compression (attack) that can go wrong, which makes digital watermark can be discarded easily. In this research, a method was proposed to overcome this problem, which is based on DCT (after image partitioned into non overlapped blocks with size 8×8 pixel), accompanied by a quantization method. The watermark (digital image) is embedded in DCT frequency domain seeking the blocks have highest standard deviation (the checking is only on the AC coefficients) within a predetermined threshold value, then the covered image will compressed (attacked) varying degrees of compression. The suggested met

     Lately, a growing interest has been emerging in age estimation from face images because of the wide range of potential implementations in law enforcement, security control, and human computer interactions. Nevertheless, in spite of the advances in age estimation, it is still a challenging issue. This is due to the fact that face aging process is not only set by distinct elements, such as genetic factors, but by extrinsic factors, such as lifestyle, expressions, and environment as well. This paper applied machine learning technique to intelligent age estimation from facial images using J48 classifier on FG_NET dataset. The proposed work consists of three phases; the first phase is image preprocessing which include

The prevalence of using the applications for the internet of things (IoT) in many human life fields such as economy, social life, and healthcare made IoT devices targets for many cyber-attacks. Besides, the resource limitation of IoT devices such as tiny battery power, small storage capacity, and low calculation speed made its security a big challenge for the researchers. Therefore, in this study, a new technique is proposed called intrusion detection system based on spike neural network and decision tree (IDS-SNNDT). In this method, the DT is used to select the optimal samples that will be hired as input to the SNN, while SNN utilized the non-leaky integrate neurons fire (NLIF) model in order to reduce latency and minimize devices

The prevalence of using the applications for the internet of things (IoT) in many human life fields such as economy, social life, and healthcare made IoT devices targets for many cyber-attacks. Besides, the resource limitation of IoT devices such as tiny battery power, small storage capacity, and low calculation speed made its security a big challenge for the researchers. Therefore, in this study, a new technique is proposed called intrusion detection system based on spike neural network and decision tree (IDS-SNNDT). In this method, the DT is used to select the optimal samples that will be hired as input to the SNN, while SNN utilized the non-leaky integrate neurons fire (NLIF) model in order to reduce latency and minimize devices

As a result of the significance of image compression in reducing the volume of data, the requirement for this compression permanently necessary; therefore, will be transferred more quickly using the communication channels and kept in less space in memory. In this study, an efficient compression system is suggested; it depends on using transform coding (Discrete Cosine Transform or bi-orthogonal (tap-9/7) wavelet transform) and LZW compression technique. The suggested scheme was applied to color and gray models then the transform coding is applied to decompose each color and gray sub-band individually. The quantization process is performed followed by LZW coding to compress the images. The suggested system was applied on a set of seven stand

The study aims to predict Total Dissolved Solids (TDS) as a water quality indicator parameter at spatial and temporal distribution of the Tigris River, Iraq by using Artificial Neural Network (ANN) model. This study was conducted on this river between Mosul and Amarah in Iraq on five positions stretching along the river for the period from 2001to 2011. In the ANNs model calibration, a computer program of multiple linear regressions is used to obtain a set of coefficient for a linear model. The input parameters of the ANNs model were the discharge of the Tigris River, the year, the month and the distance of the sampling stations from upstream of the river. The sensitivity analysis indicated that the distance and discharge

Aerial Robot Arms (ARAs) enable aerial drones to interact and influence objects in various environments. Traditional ARA controllers need the availability of a high-precision model to avoid high control chattering. Furthermore, in practical applications of aerial object manipulation, the payloads that ARAs can handle vary, depending on the nature of the task. The high uncertainties due to modeling errors and an unknown payload are inversely proportional to the stability of ARAs. To address the issue of stability, a new adaptive robust controller, based on the Radial Basis Function (RBF) neural network, is proposed. A three-tier approach is also followed. Firstly, a detailed new model for the ARA is derived using the Lagrange–d’A