Human has a duty to preserve the nature, preserving the plant is one of the examples. This research has an emphasis on ornamental plant that has functionality not only as ornament but also as medicine. Although in Indonesia, in general this plant is cultivated in front of the house; only few people know about its medicinal function. Considering this easiness to obtain and its medicinal function, this plant has to be an initial treatment or option towards full chemical-based medicines. This research proposes a system which able to identify properly ornamental plant from its leaf utilizing its shape or color features. Shape descriptor represented by Dyadic Wavelet Transformation and Zernike Complex Moment, and HSV-based color histogram as color descriptor. This research provides benefit of these three methods to solve various test aspects. It was obtained 81.77% of overall average-testing performance.

Video compression has become an essential component of broadcast and entertainment media. Motion Estimation and compensation techniques, which can eliminate temporal redundancy between adjacent frames effectively, have been widely applied to popular video compression coding standards such as MPEG-2, MPEG-4. Traditional fast block matching algorithms are easily trapped into the local minima resulting in degradation on video quality to some extent after decoding. In this paper various computing techniques are evaluated in video compression for achieving global optimal solution for motion estimation. Zero motion prejudgment is implemented for finding static macro blocks (MB) which do not need to perform remaining search thus reduces the computational cost. Adaptive Rood Pattern Search (ARPS) motion estimation algorithm is also adapted to reduce the motion vector overhead in frame prediction. The simulation results showed that the ARPS algorithm is very effective in reducing the computations overhead and achieves very good Peak Signal to Noise Ratio (PSNR) values. This method significantly reduces the computational complexity involved in the frame prediction and also least prediction error in all video sequences. Thus ARPS technique is more efficient than the conventional searching algorithms in video compression.

Desired segmentation of the image is a pivotal problem in image processing. Segmenting the left ventricle (LV) in magnetic resonance images (MRIs) is essential for evaluation of cardiac function. For the segmentation of cardiac MRI several methods have been proposed and implemented. Each of them has advantages and restrictions. A modified region-based active contour model was applied for segmentation of LV chamber. A new semi-automatic algorithm was suggested calculating the appropriate Balloon force according to mean intensity of the region of interest for each image. The database is included of 2,039 MR images collected from 18 children under 18. The results were compared with previous literatures according to two standards: Dice Metric (DM) and Point to Curve (P2C). The obtained segmentation results are better than previously reported values in several literatures. In this study different points were used in cardiac cycle and several slice levels and classified into three levels: Base, Mid. and Apex. The best results were obtained at end diastole (ED) in comparison with end systole (ES), and on base slice than other slices, because of LV bigger size in ED phase and base slice. With segmentation of LV MRI based on novel active contour and application of the suggested algorithm for balloon force calculation, the mean improvement of DM compared to Grosgeorge et al. is 19.6% in ED and 49.5% in ES phase. The mean improvement of P2C compared with the same literature respectively for ED and ES phase is 43.8% and 39.6%. 

Contemporary image processing based applications like medical diagnosis automation and analysis of satellite imagery include autonomous image segmentation as inevitable facility. The research done shows the efficiency of an adaptive evolutionary algorithm based on immune system dynamics for the task of autonomous image segmentation. The recognition dynamics of immune-kernels modeled with infinite Gaussian mixture models exhibit the capability to automatically determine appropriate number of segments in presence of noise. In addition, the model using representative density-kernel-parameters processes the information with much reduced space requirements. Experiments conducted with synthetic images as well as real images recorded assured convergence and optimal autonomous model estimation. The segmentation results tested in terms of PBM-index values have been found comparable to those of the Fuzzy C-Means (FCM) for the same number of segments as generated by our algorithm.

A Signal-Image fitted with a model function, embeds the property of the intensity-curvature content, which is defined through the math formulae merging together the signal intensity with the second order derivatives of the model function. This work presents one of the measures of the intensity-curvature content, which is called the Intensity-Curvature Functional along with qualitative results obtained with Magnetic Resonance Imaging (MRI) of the human brain and also with a sample contextual image. The Intensity-Curvature Functional is calculated in three dimensions while re-sampling the signal-image with the trivariate cubic Lagrange interpolation formula and also in two dimensions while re-sampling using the bivariate cubic Lagrange interpolation formula. The Intensity-Curvature Functional is defined as the ratio between the numerator called intensity-curvature term before interpolation and the denominator called intensity-curvature term after interpolation. The intensity-curvature term before interpolation is calculated through the multiplication between: (i) the signal intensity and (ii) the sum of the second order partial derivatives of the model function, both of them calculated at the grid point. The intensity-curvature term after interpolation is calculated through the multiplication between: (i) the signal intensity and (ii) the sum of second order partial derivatives of the model function, both of them calculated at the intra-pixel location chosen to re-sample the signal. Two most relevant properties are discernible through the Intensity-Curvature Functional. One property is the intensity-curvature content, and the other property is that the signal-image is re-imaged so to create a novel mapping of the original signal-image from which the Intensity-Curvature Functional is calculated. The novel mapping highlights and portraits the original image features under a different perspective.

Biometric based personal recognition is an efficient method for identifying a person. Recently, hand based biometric has become popular due to its various advantages such as high verification accuracy and high user acceptability. This paper proposes a hybrid model using an emerging hand based biometric trait known as Finger Back Knuckle Surface. This model is based on angular geometric analysis which is implemented on two different samples of Finger Back Knuckle Surface such as Finger Bend Knuckle Surface and Finger Intact Knuckle Surface for the extraction of knuckle feature information. The obtained feature information from both the surfaces is fused using feature information level fusion technique to authenticate the individuals. Experiments were conducted using newly created database for both Bend Knuckle and Intact Knuckle Surface. The results were promising in terms of accuracy, speed and computational complexity.

This paper demonstrates the significance of histogram processing of an image particularly the histogram equalization (HE). It is one of the widely used image enhancement technique. It has become a popular technique for contrast enhancement because the method is simple and effective. The basic idea of HE is to re-map the gray levels of an image. Here we propose two different techniques of Histogram Equalization namely, the global HE and local HE. The Histogram Equalization has been performed in the MATLAB environment. The merits and demerits of both techniques of Histogram Equalization have also been discussed. It is seen after exhaustive experimentation on a number of sample images that the proposed image enhancement techniques can be considered as an improvement over the inbuilt MATLAB function histeq.

Non-rigid image registration in extracting deformation map for two satellite images of the same region before and after earthquake occurrence based on measure of intensity dissimilarity C(Ir, T(If)) can play a significant role in post hazard analysis. In this paper, we have proposed a novel image transformation and regional segmentation of the same visualized region by assigning displacement label to change in intensity using Advanced Synthetic Aperture Radar (ASAR) satellite images. We used graph cut based non rigid registraion with a data term and a smoothness term for assigning markovianity between neighboring pixels. Displacement labels has been directly assigned from this data term for small intensity difference. Secondly, our data term imposes stricter penalty for intensity mismatches and hence yields higher registration accuracy.
Based on the satellite image analysis through image segmentation, it is found that the area of .997 km2 for the Honshu region was a maximum damage zone localized in the coastal belt of NE Japan fore-arc region. A further objective has been to correlate fractal analysis of seismic clustering behavior with image segmentation suggesting that increase in the fractal dimension coefficient is associated with the deviation of the pixel values that gives a metric of the devastation of the de-clustered region.