With the rapid development of smart devices, people's lives have become easier, especially for visually disabled or special-needs people. The new achievements in the fields of machine learning and deep learning let people identify and recognise the surrounding environment. In this study, the efficiency and high performance of deep learning architecture are used to build an image classification system in both indoor and outdoor environments. The proposed methodology starts with collecting two datasets (indoor and outdoor) from different separate datasets. In the second step, the collected dataset is split into training, validation, and test sets. The pre-trained GoogleNet and MobileNet-V2 models are trained using the indoor and outdoor sets, resulting in four trained models. The test sets are used to evaluate the trained models using many evaluation metrics (accuracy, TPR, FNR, PPR, FDR). Results of Google Net model indicate the high performance of the designed models with 99.34% and 99.76% accuracies for indoor and outdoor datasets, respectively. For Mobile Net models, the result accuracies are 99.27% and 99.68% for indoor and outdoor sets, respectively. The proposed methodology is compared with similar ones in the field of object recognition and image classification, and the comparative study proves the transcendence of the propsed system.
Automatic license plate recognition (ALPR) used for many applications especially in security applications, including border control. However, more accurate and language-independent techniques are still needed. This work provides a new approach to identifying Arabic license plates in different formats, colors, and even including English characters. Numbers, characters, and layouts with either 1-line or 2-line layouts are presented. For the test, we intend to use Iraqi license plates as there is a wide range of license plate styles written in Arabic, Kurdish, and English/Arabic languages, each different in style and color. This variety makes it difficult for recent traditional license plate recognition systems and algorithms to recogn
... Show MoreProtecting information sent through insecure internet channels is a significant challenge facing researchers. In this paper, we present a novel method for image data encryption that combines chaotic maps with linear feedback shift registers in two stages. In the first stage, the image is divided into two parts. Then, the locations of the pixels of each part are redistributed through the random numbers key, which is generated using linear feedback shift registers. The second stage includes segmenting the image into the three primary colors red, green, and blue (RGB); then, the data for each color is encrypted through one of three keys that are generated using three-dimensional chaotic maps. Many statistical tests (entropy, peak signa
... Show MoreOptical Mark Recognition (OMR) is the technology of electronically extracting intended data from marked fields, such as squareand bubbles fields, on printed forms. OMR technology is particularly useful for applications in which large numbers of hand-filled forms need to be processed quickly and with a great degree of accuracy. The technique is particularly popular with schools and universities for the reading in of multiple choice exam papers. This paper proposed OMRbased on Modify Multi-Connect Architecture (MMCA) associative memory, its work in two phases: training phase and recognition phase. The proposed method was also able to detect more than one or no selected choice. Among 800 test samples with 8 types of grid answer sheets and tota
... Show MoreThis study aims to identify the amount of the effect of the ability to learn the individuals within the organization on the accumulation of intellectual capital and the role it plays in improving the performance of the organization, and to achieve that, the researcher designed a questionnaire to collect data and information from the surveyed respondents and analyzed using SPSS software, the study concluded after testing hypotheses to have a direct impact between the capacity for organizational learning and the accumulation of intellectual capital, which in turn affects the accumulation of intellectual capital as a positive and direct impact on the performance of the organization, al
... Show MoreSupport vector machine (SVM) is a popular supervised learning algorithm based on margin maximization. It has a high training cost and does not scale well to a large number of data points. We propose a multiresolution algorithm MRH-SVM that trains SVM on a hierarchical data aggregation structure, which also serves as a common data input to other learning algorithms. The proposed algorithm learns SVM models using high-level data aggregates and only visits data aggregates at more detailed levels where support vectors reside. In addition to performance improvements, the algorithm has advantages such as the ability to handle data streams and datasets with imbalanced classes. Experimental results show significant performance improvements in compa
... Show MoreCopper Telluride Thin films of thickness 700nm and 900nm, prepared thin films using thermal evaporation on cleaned Si substrates kept at 300K under the vacuum about (4x10-5 ) mbar. The XRD analysis and (AFM) measurements use to study structure properties. The sensitivity (S) of the fabricated sensors to NO2 and H2 was measured at room temperature. The experimental relationship between S and thickness of the sensitive film was investigated, and higher S values were recorded for thicker sensors. Results showed that the best sensitivity was attributed to the Cu2Te film of 900 nm thickness at the H2 gas.