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 recognize all these license plate types using the same algorithm. In this work, a new method has been proposed to efficiently recognize all these types of license plates. This has been done by utilizing a series of algorithms for preprocessing and recognition with new identification strategies. The results show that the system recognized license plate numbers with higher accuracy, reaching up to 97.85%. However, the method field to detect license plates when there are some high deformations in plate numbers or when they are partially covered with mud, which makes it difficult to distinguish numbers.
Artificial intelligence (AI) is entering many fields of life nowadays. One of these fields is biometric authentication. Palm print recognition is considered a fundamental aspect of biometric identification systems due to the inherent stability, reliability, and uniqueness of palm print features, coupled with their non-invasive nature. In this paper, we develop an approach to identify individuals from palm print image recognition using Orange software in which a hybrid of AI methods: Deep Learning (DL) and traditional Machine Learning (ML) methods are used to enhance the overall performance metrics. The system comprises of three stages: pre-processing, feature extraction, and feature classification or matching. The SqueezeNet deep le
... Show MoreArtificial intelligence (AI) is entering many fields of life nowadays. One of these fields is biometric authentication. Palm print recognition is considered a fundamental aspect of biometric identification systems due to the inherent stability, reliability, and uniqueness of palm print features, coupled with their non-invasive nature. In this paper, we develop an approach to identify individuals from palm print image recognition using Orange software in which a hybrid of AI methods: Deep Learning (DL) and traditional Machine Learning (ML) methods are used to enhance the overall performance metrics. The system comprises of three stages: pre-processing, feature extraction, and feature classification or matching. The SqueezeNet deep le
... Show MoreThe variety of clean energy sources has risen, involving many resources, although their fundamental principles remain consistent in terms of energy generation and pollution reduction. The using of hydropower system for energy production also has a dynamic impact in which it utilizes to harness the water for the purpose of energy production. As it is important to overcome the problem of accidents in the highway and rural areas in the case of server rainfall and flood by implementation a smart system that used for energy production. This paper aims to develop a controlled hydropower system installed in the drainage sinks allocated in highway roads used for producing. The proposed system consists of storage unit represented by pipes used for t
... Show More
Experimental investigation of the influence of inserting the metal foam to the solar chimney to induce natural ventilation are described and analyzed in this work. To carry out the experimental test, two identical solar chimneys (without insertion of metal foam and with insertion of metal foam) are designed and placed facing south with dimensions of length× width× air gap (2 m× 1 m× 0.2 m). Four incline angles are tested (20o,30o,45o,60o) for each chimney in Baghdad climate condition (33.3o latitude, 44.4o longitude) on October, November, December 2018. The solar chimney performance is investigated by experimentally recording absorber pl
... Show More