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.
Recently, all over the world mechanism of cloud computing is widely acceptable and used by most of the enterprise businesses in order increase their productivity. However there are still some concerns about the security provided by the cloud environment are raises. Thus in this our research project, we are discussing over the cloud computing paradigm evolvement for the large business applications like CRM as well as introducing the new framework for the secure cloud computing using the method of IT auditing. In this case our approach is basically directed towards the establishment of the cloud computing framework for the CRM applications with the use of checklists by following the data flow of the CRM application and its lifecycle. Those ch
... Show MoreIn this work Nano crystalline (Cu2S) thin films pure and doped 3% Al with a thickness of 400±20 nm was precipitated by thermic steaming technicality on glass substrate beneath a vacuum of ~ 2 × 10− 6 mbar at R.T to survey the influence of doping and annealing after doping at 573 K for one hour on its structural, electrical and visual properties. Structural properties of these movies are attainment using X-ray variation (XRD) which showed Cu2S phase with polycrystalline in nature and forming hexagonal temple ,with the distinguish trend along the (220) grade, varying crystallites size from (42.1-62.06) nm after doping and annealing. AFM investigations of these films show that increase average grain size from 105.05 nm to 146.54 nm
... Show MoreDiode laser technology is well established for biomedicine applications which demand high-power pulse-wave. They are extensively utilized from medical imaging and testing to surgical therapies and the latest aesthetic processes. For medical therapeutic practices, diode lasers have become the ideal laser source for this particular purpose. In the last previous years, semiconductor laser technology has evolved to produce high-repetitions rate near-infrared pulsed lasers diodes that are dependable, low-cost, portable, and small-weight, about few grams. In this paper, we review the recent development and demonstration of diode laser devices for biomedical applications recorded in the latest years taking into account the power, wavelength, and p
... Show MoreDocument analysis of images snapped by camera is a growing challenge. These photos are often poor-quality compound images, composed of various objects and text; this makes automatic analysis complicated. OCR is one of the image processing techniques which is used to perform automatic identification of texts. Existing image processing techniques need to manage many parameters in order to clearly recognize the text in such pictures. Segmentation is regarded one of these essential parameters. This paper discusses the accuracy of segmentation process and its effect over the recognition process. According to the proposed method, the images were firstly filtered using the wiener filter then the active contour algorithm could b
... Show MoreOver the past few years, ear biometrics has attracted a lot of attention. It is a trusted biometric for the identification and recognition of humans due to its consistent shape and rich texture variation. The ear presents an attractive solution since it is visible, ear images are easily captured, and the ear structure remains relatively stable over time. In this paper, a comprehensive review of prior research was conducted to establish the efficacy of utilizing ear features for individual identification through the employment of both manually-crafted features and deep-learning approaches. The objective of this model is to present the accuracy rate of person identification systems based on either manually-crafted features such as D
... Show MoreThe area of character recognition has received a considerable attention by researchers all over the world during the last three decades. However, this research explores best sets of feature extraction techniques and studies the accuracy of well-known classifiers for Arabic numeral using the Statistical styles in two methods and making comparison study between them. First method Linear Discriminant function that is yield results with accuracy as high as 90% of original grouped cases correctly classified. In the second method, we proposed algorithm, The results show the efficiency of the proposed algorithms, where it is found to achieve recognition accuracy of 92.9% and 91.4%. This is providing efficiency more than the first method.
Recognizing speech emotions is an important subject in pattern recognition. This work is about studying the effect of extracting the minimum possible number of features on the speech emotion recognition (SER) system. In this paper, three experiments performed to reach the best way that gives good accuracy. The first one extracting only three features: zero crossing rate (ZCR), mean, and standard deviation (SD) from emotional speech samples, the second one extracting only the first 12 Mel frequency cepstral coefficient (MFCC) features, and the last experiment applying feature fusion between the mentioned features. In all experiments, the features are classified using five types of classification techniques, which are the Random Forest (RF),
... Show MoreMethods of speech recognition have been the subject of several studies over the past decade. Speech recognition has been one of the most exciting areas of the signal processing. Mixed transform is a useful tool for speech signal processing; it is developed for its abilities of improvement in feature extraction. Speech recognition includes three important stages, preprocessing, feature extraction, and classification. Recognition accuracy is so affected by the features extraction stage; therefore different models of mixed transform for feature extraction were proposed. The properties of the recorded isolated word will be 1-D, which achieve the conversion of each 1-D word into a 2-D form. The second step of the word recognizer requires, the
... Show More