One study whose importance has significantly grown in recent years is lip-reading, particularly with the widespread of using deep learning techniques. Lip reading is essential for speech recognition in noisy environments or for those with hearing impairments. It refers to recognizing spoken sentences using visual information acquired from lip movements. Also, the lip area, especially for males, suffers from several problems, such as the mouth area containing the mustache and beard, which may cover the lip area. This paper proposes an automatic lip-reading system to recognize and classify short English sentences spoken by speakers using deep learning networks. The input video extracts frames and each frame is passed to the Viola-Jones to detect the face area. Then 68 landmarks of the facial area are determined, and the landmarks from 48 to 68 represent the lip area extracted based on building a binary mask. Then, the contrast is enhanced to improve the quality of the lip image by applying contrast adjustment. Finally, sentences are classified using two deep learning models, the first is AlexNet, and the second is VGG-16 Net. The database consists of 39 participants (32 males and 7 females). Each participant repeats the short sentences five times. The outcomes demonstrate the accuracy rate of AlexNet is 90.00%, whereas the accuracy rate for VGG-16 Net is 82.34%. We concluded that AlexNet performs better for classifying short sentences than VGG-16 Net.
This research include design and implementation of an Iraqi cities database using spatial data structure for storing data in two or more dimension called k-d tree .The proposed system should allow records to be inserted, deleted and searched by name or coordinate. All the programming of the proposed system written using Delphi ver. 7 and performed on personal computer (Intel core i3).
An assembled pulsed Nd:YAG laser-robot system for spot welding similar and dissimilar metals is presented in this paper. The study evaluates the performance of this system through investigating the possibility and accuracy of executing laser spot welding of 0.2 mm in thickness stainless steel grade AISI302 to 0.5 mm in thickness low carbon steel grade AISI1008. The influence of laser beam parameters (peak power, pulse energy, pulse duration, repetition rate, and focal plane position on the final gained best results are evaluated. Enhancement of the experimental results was carried by a computational simulation using ANSYS FLUENT 6.3 package code.
Computer vision seeks to mimic the human visual system and plays an essential role in artificial intelligence. It is based on different signal reprocessing techniques; therefore, developing efficient techniques becomes essential to achieving fast and reliable processing. Various signal preprocessing operations have been used for computer vision, including smoothing techniques, signal analyzing, resizing, sharpening, and enhancement, to reduce reluctant falsifications, segmentation, and image feature improvement. For example, to reduce the noise in a disturbed signal, smoothing kernels can be effectively used. This is achievedby convolving the distributed signal with smoothing kernels. In addition, orthogonal moments (OMs) are a cruc
... Show MoreThe aim of this research is to develop qualitative workouts based on certain sensory perceptions for the development of offensive basketball abilities and to determine their impact on female pupils. Several findings, based on the au-thor's extensive expertise instructing basketball materials and our closeness to the sample, revealed deficits in some sensory perceptions “in the game of basketball”, which impair the accuracy of passing the ball to the best team-mate. It also affects the pace of dribbling and the difficulty of selecting the op-timal moment and distance to fire. Therefore, the researcher designs qualita-tive activities based on many sensory experiences, including distance, speed, force, and direction shift. In addition, the
... Show MoreThe current research aims to prepare a proposed Programmebased sensory integration theory for remediating some developmental learning disabilities among children, researchers prepared a Programme based on sensory integration through reviewing studies related to the research topic that can be practicedby some active teaching strategies (cooperative learning, peer learning, Role-playing, and educational stories). The Finalformat consists of(39) training sessions.
The purpose of this resesrh know (the effectiveness of cooperative lerarning implementation of floral material for calligraphy and ornamentation) To achieve the aim of the research scholar put the two zeros hypotheses: in light of the findings of the present research the researcher concluded a number of conclusions, including: -
1 - Sum strategy helps the learner to be positive in all the information and regulations, monitoring and evaluation during the learning process.
2 - This strategy helps the learner to use information and knowledge and their use in various educational positions, and to achieve better education to increase its ability to develop thinking skills and positive trends towards the article.
In light of this, the
The aim of this research to study.
The dimensions of organizational learning have been defined(learning dynamics, individuals empowerment, knowledge management and technology application) as well as the dimensions of learning organization have been defined (culture values, knowledge transfer, communication and employee characteristics), Asset completion questionnaire was used to collect data of this research from a purposely sample represent forty employees who works in Iraqi Planning Ministry at different positions. The research divided to four parts :
The first to the research methodology, the second to the theoretical review o
... Show MoreAbstract: The aim of the current research is to identify (the relationship between deep understanding skills and mathematical modeling among fifth grade students) the research sample consisted of (411) male and female students of the fifth grade of biology distributed over the General Directorates of Education in Baghdad / Al-Rusafa / 2 / and Al-Karkh / 1 /, and two research tools were built: 1- A test of deep understanding skills, consisting of (20) test items and a scale for two skills. 2- The second test consists of (24) test items distributed among (18) essay items and (6) objective items. The psychometric properties of validity, stability, discriminatory strength, and effectiveness of alternatives were verified for the two tests fo
... Show MoreBackground/Objectives: The purpose of this study was to classify Alzheimer’s disease (AD) patients from Normal Control (NC) patients using Magnetic Resonance Imaging (MRI). Methods/Statistical analysis: The performance evolution is carried out for 346 MR images from Alzheimer's Neuroimaging Initiative (ADNI) dataset. The classifier Deep Belief Network (DBN) is used for the function of classification. The network is trained using a sample training set, and the weights produced are then used to check the system's recognition capability. Findings: As a result, this paper presented a novel method of automated classification system for AD determination. The suggested method offers good performance of the experiments carried out show that the
... Show MoreBackground: Deep vein thrombosis is a multi causal disease and its one of most common venous disorder, but only one quarter of the patients who have signs and symptoms of a clot in the vein actually have thrombosis and need treatment .The disease can be difficult to diagnose. Venous ultrasound in combination with clinical finding is accurate for venous thromboembolism, its costly because a large number of patients with suspicious signs and symptoms. Venography still the gold standard for venous thromboembolism but it is invasive. The D-dimer increasingly is being seen as valuable tool rolling out venous thromboembolism and sparing low risk patients for further workup.Objectives: this study has designed the role of D-dimer to confirm diag
... Show More