Audio-visual detection and recognition system is thought to become the most promising methods for many applications includes surveillance, speech recognition, eavesdropping devices, intelligence operations, etc. In the recent field of human recognition, the majority of the research be- coming performed presently is focused on the reidentification of various body images taken by several cameras or its focuses on recognized audio-only. However, in some cases these traditional methods can- not be useful when used alone such as in indoor surveillance systems, that are installed close to the ceiling and capture images right from above in a downwards direction and in some cases people don't look straight the cameras or it cannot be added in some area such as W.C. or sleeping room. Thus, its commonly difficult to identify any movement or breakthrough process, on the other hand when need to pursue suspect when enter a building or party to identify his location and/or listen to his speech only and isolate it from other voices or noises, the other. Hence, the use of the hybrid combination technique is very effective. In this work, we proposed a multimodal human recognition approach that utilizes both the face and audio and is based upon a deep convolutional neural network (CNN). Mainly, to solve the challenge of not capturing part of the body, final results of recognizing via separate CNNs of VGG Face16 and ResNet50 are joined together depending on the score-level combination by Weighted Sum rule to enhance recognition performance. The results show that the proposed system success to recognise each person from his voice and/or his face captured. In addition, the system can separate the person voice and isolate it from noisy environment and determine the existence of desired person.
Three-dimensional (3D) image and medical image processing, which are considered big data analysis, have attracted significant attention during the last few years. To this end, efficient 3D object recognition techniques could be beneficial to such image and medical image processing. However, to date, most of the proposed methods for 3D object recognition experience major challenges in terms of high computational complexity. This is attributed to the fact that the computational complexity and execution time are increased when the dimensions of the object are increased, which is the case in 3D object recognition. Therefore, finding an efficient method for obtaining high recognition accuracy with low computational complexity is essentia
... Show More
(12)
(13)
As a result of recent developments in highway research as well as the increased use of vehicles, there has been a significant interest paid to the most current, effective, and precise Intelligent Transportation System (ITS). In the field of computer vision or digital image processing, the identification of specific objects in an image plays a crucial role in the creation of a comprehensive image. There is a challenge associated with Vehicle License Plate Recognition (VLPR) because of the variation in viewpoints, multiple formats, and non-uniform lighting conditions at the time of acquisition of the image, shape, and color, in addition, the difficulties like poor image resolution, blurry image, poor lighting, and low contrast, these
... Show More
The speech recognition system has been widely used by many researchers using different
methods to fulfill a fast and accurate system. Speech signal recognition is a typical
classification problem, which generally includes two main parts: feature extraction and
classification. In this paper, a new approach to achieve speech recognition task is proposed by
using transformation techniques for feature extraction methods; namely, slantlet transform
(SLT), discrete wavelet transforms (DWT) type Daubechies Db1 and Db4. Furthermore, a
modified artificial neural network (ANN) with dynamic time warping (DTW) algorithm is
developed to train a speech recognition system to be used for classification and recognition
purposes. T
(2)
(1)
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 se
... Show More
(6)
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 More
(6)
(3)
Finger vein recognition and user identification is a relatively recent biometric recognition technology with a broad variety of applications, and biometric authentication is extensively employed in the information age. As one of the most essential authentication technologies available today, finger vein recognition captures our attention owing to its high level of security, dependability, and track record of performance. Embedded convolutional neural networks are based on the early or intermediate fusing of input. In early fusion, pictures are categorized according to their location in the input space. In this study, we employ a highly optimized network and late fusion rather than early fusion to create a Fusion convolutional neural network
... Show MoreNumeral recognition is considered an essential preliminary step for optical character recognition, document understanding, and others. Although several handwritten numeral recognition algorithms have been proposed so far, achieving adequate recognition accuracy and execution time remain challenging to date. In particular, recognition accuracy depends on the features extraction mechanism. As such, a fast and robust numeral recognition method is essential, which meets the desired accuracy by extracting the features efficiently while maintaining fast implementation time. Furthermore, to date most of the existing studies are focused on evaluating their methods based on clean environments, thus limiting understanding of their potential a
... Show More
(37)
(36)
This study deals with the orthographic processing ability of homophones
which can account for variance in word recognition and production skills due to
phonological processing. The study aims at: A)Investigating whether the students
can recognize correct usage and spelling comprehension of different homophones
by using appropriate word that overlapped in both phonology and orthography.
B)Assessing spelling production word association to the written form of the
homophone in the sentence comprehension task. To achieve these aims, two tests
have been conducted and distributed on 50 students at first stage at the College of
Education(Ibn-Rushd) for the academic year 2010-2011. The two tests are exposed
to a jury of
The interests toward developing accurate automatic face emotion recognition methodologies are growing vastly, and it is still one of an ever growing research field in the region of computer vision, artificial intelligent and automation. However, there is a challenge to build an automated system which equals human ability to recognize facial emotion because of the lack of an effective facial feature descriptor and the difficulty of choosing proper classification method. In this paper, a geometric based feature vector has been proposed. For the classification purpose, three different types of classification methods are tested: statistical, artificial neural network (NN) and Support Vector Machine (SVM). A modified K-Means clustering algorithm
... Show More
(2)