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.
Identifying the total number of fruits on trees has long been of interest in agricultural crop estimation work. Yield prediction of fruits in practical environment is one of the hard and significant tasks to obtain better results in crop management system to achieve more productivity with regard to moderate cost. Utilized color vision in machine vision system to identify citrus fruits, and estimated yield information of the citrus grove in-real time. Fruit recognition algorithms based on color features to estimate the number of fruit. In the current research work, some low complexity and efficient image analysis approach was proposed to count yield fruits image in the natural scene. Semi automatic segmentation and yield calculation of fruit
... Show MoreOne of the significant stages in computer vision is image segmentation which is fundamental for different applications, for example, robot control and military target recognition, as well as image analysis of remote sensing applications. Studies have dealt with the process of improving the classification of all types of data, whether text or audio or images, one of the latest studies in which researchers have worked to build a simple, effective, and high-accuracy model capable of classifying emotions from speech data, while several studies dealt with improving textual grouping. In this study, we seek to improve the classification of image division using a novel approach depending on two methods used to segment the images. The first
... Show MoreThis paper presents the matrix completion problem for image denoising. Three problems based on matrix norm are performing: Spectral norm minimization problem (SNP), Nuclear norm minimization problem (NNP), and Weighted nuclear norm minimization problem (WNNP). In general, images representing by a matrix this matrix contains the information of the image, some information is irrelevant or unfavorable, so to overcome this unwanted information in the image matrix, information completion is used to comperes the matrix and remove this unwanted information. The unwanted information is handled by defining {0,1}-operator under some threshold. Applying this operator on a given ma
... Show MoreWe explore the transform coefficients of fractal and exploit new method to improve the compression capabilities of these schemes. In most of the standard encoder/ decoder systems the quantization/ de-quantization managed as a separate step, here we introduce new way (method) to work (managed) simultaneously. Additional compression is achieved by this method with high image quality as you will see later.
Building a system to identify individuals through their speech recording can find its application in diverse areas, such as telephone shopping, voice mail and security control. However, building such systems is a tricky task because of the vast range of differences in the human voice. Thus, selecting strong features becomes very crucial for the recognition system. Therefore, a speaker recognition system based on new spin-image descriptors (SISR) is proposed in this paper. In the proposed system, circular windows (spins) are extracted from the frequency domain of the spectrogram image of the sound, and then a run length matrix is built for each spin, to work as a base for feature extraction tasks. Five different descriptors are generated fro
... Show MoreSoftware Defined Network (SDN) is a new technology that separate the control plane from the data plane. SDN provides a choice in automation and programmability faster than traditional network. It supports the Quality of Service (QoS) for video surveillance application. One of most significant issues in video surveillance is how to find the best path for routing the packets between the source (IP cameras) and destination (monitoring center). The video surveillance system requires fast transmission and reliable delivery and high QoS. To improve the QoS and to achieve the optimal path, the SDN architecture is used in this paper. In addition, different routing algorithms are used with different steps. First, we eva
... Show MoreThis work involves the calculation of the cooling load in Iraqi building constructions taking in account the effect of the convective heat transfer inside the buildings. ASHRAE assumptions are compared with the Fisher and Pedersen model of estimation of internal convective heat transfer coefficient when the high rate of ventilation from ceiling inlet configuration is used. Theoretical calculation of cooling load using the Radiant Time Series Method (RTSM) is implemented on the actual tested spaces. Also the theoretical calculated cooling loads are experimentally compared by measuring the cooling load in these tested spaces. The comparison appears that using the modified Fisher and Pedersen model when large ventilation ra
... Show More