This study focusses on the effect of using ICA transform on the classification accuracy of satellite images using the maximum likelihood classifier. The study area represents an agricultural area north of the capital Baghdad - Iraq, as it was captured by the Landsat 8 satellite on 12 January 2021, where the bands of the OLI sensor were used. A field visit was made to a variety of classes that represent the landcover of the study area and the geographical location of these classes was recorded. Gaussian, Kurtosis, and LogCosh kernels were used to perform the ICA transform of the OLI Landsat 8 image. Different training sets were made for each of the ICA and Landsat 8 images separately that used in the classification phase, and used to calculate the classification accuracy. Statistical analysis for the result of the classification of each scene is presented for each class .The study showed that the ICA transform makes the satellite image significantly increases the classification accuracy, as well as that the Gaussian kernel gives the highest classification accuracy than other kernels.
This research is based on the idea of showing the extent to which the public relies on satellite channels as sources for news of the demonstrations in Iraq .This was the essence of the problem for which the researcher set several goals, including knowing the public’s confidence in the news of these satellite channels and comparing them with others. The researcher chose an available intended sample of (117) respondents in Baghdad - Karkh and Rusafa by adopting the survey method and applying a questionnaire form and the theory of media dependence for the period from 15/11/2019 to 1/1/2021 . By using statistical methods, the researcher reached many results, the most important of which are: Satellite channels are a source for 79% of the pu
... Show MoreArabic text categorization for pattern recognitions is challenging. We propose for the first time a novel holistic method based on clustering for classifying Arabic writer. The categorization is accomplished stage-wise. Firstly, these document images are sectioned into lines, words, and characters. Secondly, their structural and statistical features are obtained from sectioned portions. Thirdly, F-Measure is used to evaluate the performance of the extracted features and their combination in different linkage methods for each distance measures and different numbers of groups. Finally, experiments are conducted on the standard KHATT dataset of Arabic handwritten text comprised of varying samples from 1000 writers. The results in the generatio
... Show MoreAccurate emotion categorization is an important and challenging task in computer vision and image processing fields. Facial emotion recognition system implies three important stages: Prep-processing and face area allocation, feature extraction and classification. In this study a new system based on geometric features (distances and angles) set derived from the basic facial components such as eyes, eyebrows and mouth using analytical geometry calculations. For classification stage feed forward neural network classifier is used. For evaluation purpose the Standard database "JAFFE" have been used as test material; it holds face samples for seven basic emotions. The results of conducted tests indicate that the use of suggested distances, angles
... Show MoreIn recent years, with the rapid development of the current classification system in digital content identification, automatic classification of images has become the most challenging task in the field of computer vision. As can be seen, vision is quite challenging for a system to automatically understand and analyze images, as compared to the vision of humans. Some research papers have been done to address the issue in the low-level current classification system, but the output was restricted only to basic image features. However, similarly, the approaches fail to accurately classify images. For the results expected in this field, such as computer vision, this study proposes a deep learning approach that utilizes a deep learning algorithm.
... Show MoreThe game of volleyball requires the formation of new motor responses, which in turn requires special physical characteristics in the performance of that skill, and the correct and accurate performance during the performance of the skills of passing from the top and smash serve in volleyball cannot be developed or improved without a good level of accuracy and what is required to perform the movements in terms of responses to the defense and attack movements. Therefore, the researchers decided to identify the type of relationship between the motor response speed with the performance accuracy of the skills of passing from the top and the smash serve in volleyball. The research aims to: 1. Identifying the motor response speed of fourth-stage s
... Show More