Emotion recognition has important applications in human-computer interaction. Various sources such as facial expressions and speech have been considered for interpreting human emotions. The aim of this paper is to develop an emotion recognition system from facial expressions and speech using a hybrid of machine-learning algorithms in order to enhance the overall performance of human computer communication. For facial emotion recognition, a deep convolutional neural network is used for feature extraction and classification, whereas for speech emotion recognition, the zero-crossing rate, mean, standard deviation and mel frequency cepstral coefficient features are extracted. The extracted features are then fed to a random forest classifier. In addition, a bi-modal system for recognising emotions from facial expressions and speech signals is presented. This is important since one modality may not provide sufficient information or may not be available for any reason beyond operator control. To perform this, decision-level fusion is performed using a novel way for weighting according to the proportions of facial and speech impressions. The results show an average accuracy of 93.22 %.
Image pattern classification is considered a significant step for image and video processing.Although various image pattern algorithms have been proposed so far that achieved adequate classification,achieving higher accuracy while reducing the computation time remains challenging to date. A robust imagepattern classification method is essential to obtain the desired accuracy. This method can be accuratelyclassify image blocks into plain, edge, and texture (PET) using an efficient feature extraction mechanism.Moreover, to date, most of the existing studies are focused on evaluating their methods based on specificorthogonal moments, which limits the understanding of their potential application to various DiscreteOrthogonal Moments (DOMs). The
... Show MoreIn this work we present a technique to extract the heart contours from noisy echocardiograph images. Our technique is based on improving the image before applying contours detection to reduce heavy noise and get better image quality. To perform that, we combine many pre-processing techniques (filtering, morphological operations, and contrast adjustment) to avoid unclear edges and enhance low contrast of echocardiograph images, after implementing these techniques we can get legible detection for heart boundaries and valves movement by traditional edge detection methods.
In this research a proposed technique is used to enhance the frame difference technique performance for extracting moving objects in video file. One of the most effective factors in performance dropping is noise existence, which may cause incorrect moving objects identification. Therefore it was necessary to find a way to diminish this noise effect. Traditional Average and Median spatial filters can be used to handle such situations. But here in this work the focus is on utilizing spectral domain through using Fourier and Wavelet transformations in order to decrease this noise effect. Experiments and statistical features (Entropy, Standard deviation) proved that these transformations can stand to overcome such problems in an elegant way.
... Show MoreIn this paper, a fast lossless image compression method is introduced for compressing medical images, it is based on splitting the image blocks according to its nature along with using the polynomial approximation to decompose image signal followed by applying run length coding on the residue part of the image, which represents the error caused by applying polynomial approximation. Then, Huffman coding is applied as a last stage to encode the polynomial coefficients and run length coding. The test results indicate that the suggested method can lead to promising performance.
Hand gestures are currently considered one of the most accurate ways to communicate in many applications, such as sign language, controlling robots, the virtual world, smart homes, and the field of video games. Several techniques are used to detect and classify hand gestures, for instance using gloves that contain several sensors or depending on computer vision. In this work, computer vision is utilized instead of using gloves to control the robot's movement. That is because gloves need complicated electrical connections that limit user mobility, sensors may be costly to replace, and gloves can spread skin illnesses between users. Based on computer vision, the MediaPipe (MP) method is used. This method is a modern method that is discover
... Show MoreThis work aims to develop a secure lightweight cipher algorithm for constrained devices. A secure communication among constrained devices is a critical issue during the data transmission from the client to the server devices. Lightweight cipher algorithms are defined as a secure solution for constrained devices that require low computational functions and small memory. In contrast, most lightweight algorithms suffer from the trade-off between complexity and speed in order to produce robust cipher algorithm. The PRESENT cipher has been successfully experimented on as a lightweight cryptography algorithm, which transcends other ciphers in terms of its computational processing that required low complexity operations. The mathematical model of
... Show MoreThere has been a great deal of research into the considerable challenge of managing of traffic at road junctions; its application to vehicular ad hoc network (VANET) has proved to be of great interest in the developed world. Dynamic topology is one of the vital challenges facing VANET; as a result, routing of packets to their destination successfully and efficiently is a non-simplistic undertaking. This paper presents a MDORA, an efficient and uncomplicated algorithm enabling intelligent wireless vehicular communications. MDORA is a robust routing algorithm that facilitates reliable routing through communication between vehicles. As a position-based routing technique, the MDORA algorithm, vehicles' precise locations are used to establish th
... Show MoreThe internet is a basic source of information for many specialities and uses. Such information includes sensitive data whose retrieval has been one of the basic functions of the internet. In order to protect the information from falling into the hands of an intruder, a VPN has been established. Through VPN, data privacy and security can be provided. Two main technologies of VPN are to be discussed; IPSec and Open VPN. The complexity of IPSec makes the OpenVPN the best due to the latter’s portability and flexibility to use in many operating systems. In the LAN, VPN can be implemented through Open VPN to establish a double privacy layer(privacy inside privacy). The specific subnet will be used in this paper. The key and certificate will
... Show More