The deep learning algorithm has recently achieved a lot of success, especially in the field of computer vision. This research aims to describe the classification method applied to the dataset of multiple types of images (Synthetic Aperture Radar (SAR) images and non-SAR images). In such a classification, transfer learning was used followed by fine-tuning methods. Besides, pre-trained architectures were used on the known image database ImageNet. The model VGG16 was indeed used as a feature extractor and a new classifier was trained based on extracted features.The input data mainly focused on the dataset consist of five classes including the SAR images class (houses) and the non-SAR images classes (Cats, Dogs, Horses, and Humans). The Convolutional Neural Network (CNN) has been chosen as a better option for the training process because it produces a high accuracy. The final accuracy has reached 91.18% in five different classes. The results are discussed in terms of the probability of accuracy for each class in the image classification in percentage. Cats class got 99.6 %, while houses class got 100 %.Other types of classes were with an average score of 90 % and above.
The purpose of this work was to study the effects of the Nd:YAG laser on exposed dentinal
tubules of human extracted teeth using a scanning electron microscope (SEM). Eighty 2.5mm-thick
slices were cut at the cementoenamel junction from 20 extracted human teeth with an electric saw. A
diamond bur was used to remove the cementum layer to expose the dentinal tubules. Each slice was
sectioned into four equal quadrants and the specimens were randomly divided into four groups (A to D ).
Groups B to D were lased for 2 mins using an Nd:YAG laser at 6 pulses per second at energy outputs of
80 , 100 and 120 mJ. Group A served as control. Under SEM observation, nonlased specimens showed
numerous exposed dentinal tubules. SEM o
In the present work, a z-scan technique was used to study the nonlinear optical properties, represented by the nonlinear refractive index and nonlinear absorption coefficients of nanoparticles cadmium sulfide thin film. The sample was prepared by the chemical bath deposition method. Several testing were done including, x-ray, transmission and thickness of thin film. z-Scan experiment was performed at two wavelengths (1064 nm and 532 nm) and different energies. The results showed the effect of self-focusing in the material at higher intensities, which evaluated n2 to be (0.11-0.16) cm2/GW. The effect of two-photon absorption was studied, which evaluated β to be (24-106) cm/GW. In addition, the optical limiting behavior has been studied.
... Show MoreAbstract
In order to make an improvement associated with rotating biological contactor (RBC), a new design of biofilm reactor called as Rotating perforated disc biological contactor (RPBC) was developed in which the rotating discs are perforated. The transfer of oxygen from air to wastewater was investigated. Mass-transfer coefficient (KLa) in the liquid phase was determined by measuring the rate transfer of oxygen. A laboratory scale of (RPBC) consisted of a semicircular trough was used with a working capacity of 40 liters capacity of liquid. Synthetic wastewater was used as a liquid phase, while air was used as a gas phase.
The effects of m
... Show MoreGroupwise 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
... Show MoreThe computer vision branch of the artificial intelligence field is concerned with developing algorithms for analyzing video image content. Extracting edge information, which is the essential process in most pictorial pattern recognition problems. A new method of edge detection technique has been introduces in this research, for detecting boundaries.
Selection of typical lossy techniques for encoding edge video images are also discussed in this research. The concentration is devoted to discuss the Block-Truncation coding technique and Discrete Cosine Transform (DCT) coding technique. In order to reduce the volume of pictorial data which one may need to store or transmit,
... Show MoreMedical image segmentation is one of the most actively studied fields in the past few decades, as the development of modern imaging modalities such as magnetic resonance imaging (MRI) and computed tomography (CT), physicians and technicians nowadays have to process the increasing number and size of medical images. Therefore, efficient and accurate computational segmentation algorithms become necessary to extract the desired information from these large data sets. Moreover, sophisticated segmentation algorithms can help the physicians delineate better the anatomical structures presented in the input images, enhance the accuracy of medical diagnosis and facilitate the best treatment planning. Many of the proposed algorithms could perform w
... Show MoreIn this paper three techniques for image compression are implemented. The proposed techniques consist of three dimension (3-D) two level discrete wavelet transform (DWT), 3-D two level discrete multi-wavelet transform (DMWT) and 3-D two level hybrid (wavelet-multiwavelet transform) technique. Daubechies and Haar are used in discrete wavelet transform and Critically Sampled preprocessing is used in discrete multi-wavelet transform. The aim is to maintain to increase the compression ratio (CR) with respect to increase the level of the transformation in case of 3-D transformation, so, the compression ratio is measured for each level. To get a good compression, the image data properties, were measured, such as, image entropy (He), percent r
... Show MoreImage retrieval is used in searching for images from images database. In this paper, content – based image retrieval (CBIR) using four feature extraction techniques has been achieved. The four techniques are colored histogram features technique, properties features technique, gray level co- occurrence matrix (GLCM) statistical features technique and hybrid technique. The features are extracted from the data base images and query (test) images in order to find the similarity measure. The similarity-based matching is very important in CBIR, so, three types of similarity measure are used, normalized Mahalanobis distance, Euclidean distance and Manhattan distance. A comparison between them has been implemented. From the results, it is conclud
... Show More