Two unsupervised classifiers for optimum multithreshold are presented; fast Otsu and k-means. The unparametric methods produce an efficient procedure to separate the regions (classes) by select optimum levels, either on the gray levels of image histogram (as Otsu classifier), or on the gray levels of image intensities(as k-mean classifier), which are represent threshold values of the classes. In order to compare between the experimental results of these classifiers, the computation time is recorded and the needed iterations for k-means classifier to converge with optimum classes centers. The variation in the recorded computation time for k-means classifier is discussed.

Wildfire risk has globally increased during the past few years due to several factors. An efficient and fast response to wildfires is extremely important to reduce the damaging effect on humans and wildlife. This work introduces a methodology for designing an efficient machine learning system to detect wildfires using satellite imagery. A convolutional neural network (CNN) model is optimized to reduce the required computational resources. Due to the limitations of images containing fire and seasonal variations, an image augmentation process is used to develop adequate training samples for the change in the forest’s visual features and the seasonal wind direction at the study area during the fire season. The selected CNN model (Mob

The research discusses the formal transformation in urban structure, all the cities around the world have undergone a series of formal transformations, resulting in radical transformations to their functions. And to calculate this transformation the descriptive analytical method was applied to this research. First, local urban management data and Landsat-9 visual data were used after processing by GIS. Then, the data were processed mathematically based on their engineering sequences. The aims of this research were as follows: to explore the formal transformations in cities, their dimensions and their consequences and impacts; to identify the underlying causes of their occurrence by deriving realistic results from trends in such degrees of t

Image Fusion Using A Convolutional Neural Network

In this paper, visible image watermarking algorithm based on biorthogonal wavelet
transform is proposed. The watermark (logo) of type binary image can be embedded in the
host gray image by using coefficients bands of the transformed host image by biorthogonal
transform domain. The logo image can be embedded in the top-left corner or spread over the
whole host image. A scaling value (α) in the frequency domain is introduced to control the
perception of the watermarked image. Experimental results show that this watermark
algorithm gives visible logo with and no losses in the recovery process of the original image,
the calculated PSNR values support that. Good robustness against attempt to remove the
watermark was s

Consider a simple graph   on vertices and edges together with a total  labeling . Then ρ is called total edge irregular labeling if there exists a one-to-one correspondence, say  defined by  for all  where  Also, the value  is said to be the edge weight of . The total edge irregularity strength of the graph G is indicated by  and is the least  for which G admits   edge irregular h-labeling.  In this article,   for some common graph families are examined. In addition, an open problem is solved affirmatively.

0