Hameed R. Farhan - Academia.edu (original) (raw)
Uploads
Papers by Hameed R. Farhan
International Journal of Electrical and Computer Engineering (IJECE), 2019
Face recognition and gender classification are vital topics in the field of computer graphic and ... more Face recognition and gender classification are vital topics in the field of computer graphic and pattern recognition. We utilized ideas from two growing ideas in computer vision, which are biological landmarks and quasi-landmarks (dense mesh) to propose a novel approach to compare their performance in face recognition and gender classification. The experimental work is conducted on FRRGv2 dataset and acquired 98% and 94% face recognition accuracies using the quasi and biological landmarks respectively. The gender classification accuracies are 92% for quasi-landmarks and 90% for biological landmarks.
International Journal of Electrical and Computer Engineering, 2019
Face recognition and gender classification are vital topics in the field of computer graphic and ... more Face recognition and gender classification are vital topics in the field of computer graphic and pattern recognition. We utilized ideas from two growing ideas in computer vision, which are biological landmarks and quasi-landmarks (dense mesh) to propose a novel approach to compare their performance in face recognition and gender classification. The experimental work is conducted on FRRGv2 dataset and acquired 98% and 94% face recognition accuracies using the quasi and biological landmarks respectively. The gender classification accuracies are 92% for quasi-landmarks and 90% for biological landmarks.
IOP Conference Series: Materials Science and Engineering, 2020
In this paper, a crossed dipole antenna based on Pyrex Glass substrate is proposed for dual bands... more In this paper, a crossed dipole antenna based on Pyrex Glass substrate is proposed for dual bands, GSM 900 MHz and Wi-Fi 2.4 GHz. Each dipole is placed on a side of the substrate with the antennas oriented perpendicular to each other. Both antennas participate in an omnidirectional radiation pattern in perpendicular planes to form a radiation pattern similar to the isotropic. The realised gain for each dipole and the total radiation efficiency are 1.46 dB and 88% respectively. The glass substrate provides a reduction in the antenna size of about 36% compared with typical individual elements in free space.
IOP Conference Series: Materials Science and Engineering, 2020
The problem of preventing unauthorised persons from accessing specific places has become an inter... more The problem of preventing unauthorised persons from accessing specific places has become an interesting research field. This study proposes a warning system to alarm the owner about any unauthorised attempt to access a secure gate. In the proposed system, the classic alarm circuits that use 555 timers or operational amplifiers are replaced with a simpler and more reliable electronic circuit that includes a small microcontroller chip known as a Programmable Intelligent Computer (PIC). The PIC is programmed to perform sense any touch and produce an alarm signal (buzzer sound), or to send a text message and/or phone call. Implementation of the system demonstrates the superiority of PIC-based circuit over rudimentary electronic circuits in terms of cost, size, complexity, reliability, and system updates.
AIP Conference Proceedings, 2019
Face recognition (FR) has received an important concern in our contemporary life, especially in c... more Face recognition (FR) has received an important concern in our contemporary life, especially in control and security applications. This work proposes a novel method for tackling the problem of FR using the minimum number of states (i.e. one state) of continuous Hidden Markov Model (HMM). The contribution of the proposed method can be viewed in the use of continuous one-state HMM, which has not yet been used in other approaches. Furthermore, the concept that early adopted, regarding the relationship between facial regions and number of states, is invalidated, accordingly. The implementation of this method can be summarized as follows: i) filtering the face image using a median filter, ii) reduction of additional noise and image size using multiple level of discrete wavelet transform (DWT), iii) training the outcomes of the DWT using one-state HMM of continuous output density with one Gaussian mixture coefficient, and iv) recognizing images for validation. The advantage of using continuous output densities appears in conducting noisy images, such that the proposed method highly reduces the effect of noise. The simulation results present that the recognition rate is about 100% despite the presence of 25% and 50% of impulsive noise densities on the images of the ORL and Yale databases, respectively.
This paper presents fast and robust face recognition (FR) system based on Discrete Wavelet Transf... more This paper presents fast and robust face recognition (FR) system based on Discrete Wavelet Transform (DWT) and states reduction of Hidden Markov Model (HMM). The robustness of the system against the noise is supported by using a type of order statistic filter called median filter. The noise reduction by median filter is a typical pre-processing step, which greatly improves the performance of the system. A high reduction in image size is achieved by using the 3rd level of DWT. Besides the reduction in image size, DWT reduces the impact of noise resulting during image capturing or image sending. An ergodic HMM, with only three states, is used to train a set of images for each person using Baum-Welch algorithm, whereas Viterbi algorithm is used for testing process. The computational complexity and the memory consumption of the system indicate competitively high reduction compared with other approaches. Experimental results show that the proposed work achieves 100% recognition rate on ORL face database, despite the presence of Salt and Pepper noise up to 0.1 noise density.
—Face recognition has become an important subject in modern life, especially in security and surv... more —Face recognition has become an important subject in modern life, especially in security and surveillance applications. This work introduces a face recognition method, which is characterized by high-speed, low-complexity, and high-efficiency in a noisy environment. The performance of this method is greatly improved by using a median filter, such that each image is filtered to eliminate the influence of noise and light illumination. Multiple levels of discrete wavelet transform are applied to the filtered image to reduce size and eliminate further noise. Subsequently, the resultant image is scanned using a window with a predefined overlap in raster fashion to construct a sequence of observation vectors used as the basis of a model. The model consists of two states of a continuous hidden Markov model, a unique model in the face recognition field that has not yet been used by other researchers, which interprets the novelty and low complexity of the method. In spite of the presence of 0.15, 0.4, and 0.25 measurement values of impulse noise density in images stored in the ORL, Yale, and EURECOM Kinect face databases, respectively, the proposed work has achieved a recognition rate of 100%. I. INTRODUCTION Face recognition has recently received considerable attention due to its important applications in many areas and fields such as credit card verification, security, and surveillance. The advantage of face recognition over other biometric techniques is the mechanism to recognize persons, which is frequently performed without requiring that the person have physical contact with the device, e.g. use of palm or fingers. The face image can be captured by a camera without informing the target person, especially in the case of criminal surveillance and apprehension. The methods introduced to recognize faces vary relative to the procedure used for feature extraction and type of classifier used. The artificial neural network [1], principle component analysis (PCA) [2], independent component analysis [3], linear discriminant analysis (LDA) [4], support vector machine [5] and K-nearest neighbour [6] are the most widely used methods. In addition, the hidden Markov model (HMM) [7] has been successfully used in face recognition during the last two decades. The advantage of applying HMM to face recognition is the flexibility of the selection of training models, such that it is easy to add or remove individuals. There is no need for retraining the overall system; however, a model with updated images must be retrained. For dimensionality reduction, a particular feature extraction method is applied to form a sequence of observation vectors to model faces. Thereafter, for each individual, one HMM model is constructed by training a specified set of images for that individual. The training process depends on the estimation of the HMM parameters [8], such that the process is iterated several times before it converges. In the testing process, the algorithm computes the probability of the observations of unknown face image calibrated with the parameters derived from the training. The unknown face belongs to the person whose model computes the highest probability. The disadvantages of using more states of the HMM are: high computational complexities, large memory requirements, and low processing speed. The proposed work addresses the unfavourable features by using only two states of the HMM.
This paper presents a fast face recognition (FR) method using only three states of Hidden Markov ... more This paper presents a fast face recognition (FR) method using only three states of Hidden Markov Model (HMM), where the number of states is a major effective factor in computational complexity. Most of the researchers believe that each state represents one facial region, so they used five states or more according to the number of facial regions. In this work, a different idea has been proven, where the number of states is independent of the number of facial regions. The image is resized to 56x56, and order-statistic filters are used to improve the preprocessing operations and thereby reducing the influence of the illumination and noise. Up to three coefficients of Singular Value Decomposition (SVD) are utilized to describe overlapped blocks of size 5x56. Experimental results show that the proposed work manages to achieve 100% recognition rate on ORL face database using the maximum variance and two coefficients of SVD and can, therefore, be considered as the fastest face recognition type.
International Journal of Electrical and Computer Engineering (IJECE), 2019
Face recognition and gender classification are vital topics in the field of computer graphic and ... more Face recognition and gender classification are vital topics in the field of computer graphic and pattern recognition. We utilized ideas from two growing ideas in computer vision, which are biological landmarks and quasi-landmarks (dense mesh) to propose a novel approach to compare their performance in face recognition and gender classification. The experimental work is conducted on FRRGv2 dataset and acquired 98% and 94% face recognition accuracies using the quasi and biological landmarks respectively. The gender classification accuracies are 92% for quasi-landmarks and 90% for biological landmarks.
International Journal of Electrical and Computer Engineering, 2019
Face recognition and gender classification are vital topics in the field of computer graphic and ... more Face recognition and gender classification are vital topics in the field of computer graphic and pattern recognition. We utilized ideas from two growing ideas in computer vision, which are biological landmarks and quasi-landmarks (dense mesh) to propose a novel approach to compare their performance in face recognition and gender classification. The experimental work is conducted on FRRGv2 dataset and acquired 98% and 94% face recognition accuracies using the quasi and biological landmarks respectively. The gender classification accuracies are 92% for quasi-landmarks and 90% for biological landmarks.
IOP Conference Series: Materials Science and Engineering, 2020
In this paper, a crossed dipole antenna based on Pyrex Glass substrate is proposed for dual bands... more In this paper, a crossed dipole antenna based on Pyrex Glass substrate is proposed for dual bands, GSM 900 MHz and Wi-Fi 2.4 GHz. Each dipole is placed on a side of the substrate with the antennas oriented perpendicular to each other. Both antennas participate in an omnidirectional radiation pattern in perpendicular planes to form a radiation pattern similar to the isotropic. The realised gain for each dipole and the total radiation efficiency are 1.46 dB and 88% respectively. The glass substrate provides a reduction in the antenna size of about 36% compared with typical individual elements in free space.
IOP Conference Series: Materials Science and Engineering, 2020
The problem of preventing unauthorised persons from accessing specific places has become an inter... more The problem of preventing unauthorised persons from accessing specific places has become an interesting research field. This study proposes a warning system to alarm the owner about any unauthorised attempt to access a secure gate. In the proposed system, the classic alarm circuits that use 555 timers or operational amplifiers are replaced with a simpler and more reliable electronic circuit that includes a small microcontroller chip known as a Programmable Intelligent Computer (PIC). The PIC is programmed to perform sense any touch and produce an alarm signal (buzzer sound), or to send a text message and/or phone call. Implementation of the system demonstrates the superiority of PIC-based circuit over rudimentary electronic circuits in terms of cost, size, complexity, reliability, and system updates.
AIP Conference Proceedings, 2019
Face recognition (FR) has received an important concern in our contemporary life, especially in c... more Face recognition (FR) has received an important concern in our contemporary life, especially in control and security applications. This work proposes a novel method for tackling the problem of FR using the minimum number of states (i.e. one state) of continuous Hidden Markov Model (HMM). The contribution of the proposed method can be viewed in the use of continuous one-state HMM, which has not yet been used in other approaches. Furthermore, the concept that early adopted, regarding the relationship between facial regions and number of states, is invalidated, accordingly. The implementation of this method can be summarized as follows: i) filtering the face image using a median filter, ii) reduction of additional noise and image size using multiple level of discrete wavelet transform (DWT), iii) training the outcomes of the DWT using one-state HMM of continuous output density with one Gaussian mixture coefficient, and iv) recognizing images for validation. The advantage of using continuous output densities appears in conducting noisy images, such that the proposed method highly reduces the effect of noise. The simulation results present that the recognition rate is about 100% despite the presence of 25% and 50% of impulsive noise densities on the images of the ORL and Yale databases, respectively.
This paper presents fast and robust face recognition (FR) system based on Discrete Wavelet Transf... more This paper presents fast and robust face recognition (FR) system based on Discrete Wavelet Transform (DWT) and states reduction of Hidden Markov Model (HMM). The robustness of the system against the noise is supported by using a type of order statistic filter called median filter. The noise reduction by median filter is a typical pre-processing step, which greatly improves the performance of the system. A high reduction in image size is achieved by using the 3rd level of DWT. Besides the reduction in image size, DWT reduces the impact of noise resulting during image capturing or image sending. An ergodic HMM, with only three states, is used to train a set of images for each person using Baum-Welch algorithm, whereas Viterbi algorithm is used for testing process. The computational complexity and the memory consumption of the system indicate competitively high reduction compared with other approaches. Experimental results show that the proposed work achieves 100% recognition rate on ORL face database, despite the presence of Salt and Pepper noise up to 0.1 noise density.
—Face recognition has become an important subject in modern life, especially in security and surv... more —Face recognition has become an important subject in modern life, especially in security and surveillance applications. This work introduces a face recognition method, which is characterized by high-speed, low-complexity, and high-efficiency in a noisy environment. The performance of this method is greatly improved by using a median filter, such that each image is filtered to eliminate the influence of noise and light illumination. Multiple levels of discrete wavelet transform are applied to the filtered image to reduce size and eliminate further noise. Subsequently, the resultant image is scanned using a window with a predefined overlap in raster fashion to construct a sequence of observation vectors used as the basis of a model. The model consists of two states of a continuous hidden Markov model, a unique model in the face recognition field that has not yet been used by other researchers, which interprets the novelty and low complexity of the method. In spite of the presence of 0.15, 0.4, and 0.25 measurement values of impulse noise density in images stored in the ORL, Yale, and EURECOM Kinect face databases, respectively, the proposed work has achieved a recognition rate of 100%. I. INTRODUCTION Face recognition has recently received considerable attention due to its important applications in many areas and fields such as credit card verification, security, and surveillance. The advantage of face recognition over other biometric techniques is the mechanism to recognize persons, which is frequently performed without requiring that the person have physical contact with the device, e.g. use of palm or fingers. The face image can be captured by a camera without informing the target person, especially in the case of criminal surveillance and apprehension. The methods introduced to recognize faces vary relative to the procedure used for feature extraction and type of classifier used. The artificial neural network [1], principle component analysis (PCA) [2], independent component analysis [3], linear discriminant analysis (LDA) [4], support vector machine [5] and K-nearest neighbour [6] are the most widely used methods. In addition, the hidden Markov model (HMM) [7] has been successfully used in face recognition during the last two decades. The advantage of applying HMM to face recognition is the flexibility of the selection of training models, such that it is easy to add or remove individuals. There is no need for retraining the overall system; however, a model with updated images must be retrained. For dimensionality reduction, a particular feature extraction method is applied to form a sequence of observation vectors to model faces. Thereafter, for each individual, one HMM model is constructed by training a specified set of images for that individual. The training process depends on the estimation of the HMM parameters [8], such that the process is iterated several times before it converges. In the testing process, the algorithm computes the probability of the observations of unknown face image calibrated with the parameters derived from the training. The unknown face belongs to the person whose model computes the highest probability. The disadvantages of using more states of the HMM are: high computational complexities, large memory requirements, and low processing speed. The proposed work addresses the unfavourable features by using only two states of the HMM.
This paper presents a fast face recognition (FR) method using only three states of Hidden Markov ... more This paper presents a fast face recognition (FR) method using only three states of Hidden Markov Model (HMM), where the number of states is a major effective factor in computational complexity. Most of the researchers believe that each state represents one facial region, so they used five states or more according to the number of facial regions. In this work, a different idea has been proven, where the number of states is independent of the number of facial regions. The image is resized to 56x56, and order-statistic filters are used to improve the preprocessing operations and thereby reducing the influence of the illumination and noise. Up to three coefficients of Singular Value Decomposition (SVD) are utilized to describe overlapped blocks of size 5x56. Experimental results show that the proposed work manages to achieve 100% recognition rate on ORL face database using the maximum variance and two coefficients of SVD and can, therefore, be considered as the fastest face recognition type.