International Journal of Image, Graphics and Signal Processing @ijigsp
Journal articles - International Journal of Image, Graphics and Signal Processing
All articles: 1207
Scientific article
The wastage of electrical power cannot be over-emphasized in FCT College of Education, Zuba-Abuja as many lighting bulbs, street-lights, electrical fans are always ON even when not in use. The college community is characterized by electrical power wastage. However, the motivation for this research was to curtail the electrical power wastage and reduce the high cost of electricity. This research was designed to control ON and OFF time of any electrical appliance connected to its output and could as well be used as a digital clock. The objective of this research was to control the ON and OFF time of air conditioning. The design included a microcontroller (ATMEGA328) that was programmed to achieve the timing operation. The Light Emitting Diode (LED) displayed the ton (Time ON) and the t0ff (Time OFF); four keys set the hour and the minutes; and the relay was activated whenever the time set elapsed, causing the air conditioning to be energized/dis-energized automatically. A time of 3:19 was set to test the ON switching. An air conditioning connected to the developed system was activated at exactly 3:19. Also, a time of 5:57 was set to de-activate the already ON electric bulb. The electric bulb was switched OFF at exactly 5:57. The developed switching system was tested and satisfactorily switched ON and OFF air conditioning as desired and pre-set by the user.
Free
A video based vehicle detection, counting and classification system
Scientific article
Traffic Analysis has been a problem that city planners have dealt with for years. Smarter ways are being developed to analyze traffic and streamline the process. Analysis of traffic may account for the number of vehicles in an area per some arbitrary time period and the class of vehicles. People have designed such mechanism for decades now but most of them involve use of sensors to detect the vehicles i.e. a couple of proximity sensors to calculate the direction of the moving vehicle and to keep the vehicle count. Even though over the time these systems have matured and are highly effective, they are not very budget friendly. The problem is such systems require maintenance and periodic calibration. Therefore, this study has purposed a vision based vehicle counting and classification system. The system involves capturing of frames from the video to perform background subtraction in order detect and count the vehicles using Gaussian Mixture Model (GMM) background subtraction then it classifies the vehicles by comparing the contour areas to the assumed values. The substantial contribution of the work is the comparison of two classification methods. Classification has been implemented using Contour Comparison (CC) as well as Bag of Features (BoF) and Support Vector Machine (SVM) method.
Free
ADCT-based Robust Methodology for Image Steganography
Scientific article
Steganography is an important area of research in recent years involving a number of applications. It is the science of embedding information into the cover image viz., text, video, and image (payload) without causing statistically significant modification to the cover image. The modern secure image steganography presents a challenging task of transferring the embedded information to the destination without being detected.In this paper, a DCT based robust methodology has been designed. The cover image is segmented into 8*8 blocks and DCT is applied on the image. The text to be hidden is embedded in the diagonal elements of the blocks by substituting a random variable in place of the bits of the text to be embedded. It is observed that the proposed algorithm is more robust with better CER & Normalized coefficient.
Free
ANN Approach for Classification of Different Origin Fabric Images
Scientific article
This paper focuses on classification of varieties of plants’, animals’ and minerals’ origin fabric materials from images. The morphological operations, namely, erosion and dilation are used. ANN classifier is used to predict the classification rates and the rates of 89%, 87% and 88% are obtained for plants’, animals’ and minerals’ origin fabric images respectively. The overall classification rate of 88% is obtained.
Free
Scientific article
The field of fraud identification is reaching a very high proportion in the society, thus leading to an increase in the need for fingerprint-based identification. This paper presents ASIC implementation of fingerprint recognition based on Overlap-add method and Integer Wavelet Transforms. In overlap-add method, the present output overlaps the next output and in the integer to integer wavelet, low component at 2nd level decomposition is taken as approximate integer value. The implementation presents an analysis for speed, area and power dissipation between the two algorithms and other methods.
Free
Accelerating Cross-correlation Applications via Parallel Computing
Scientific article
Software dealing with large-scale signal processing takes long time even on modern hardware. Cross-correlation applications are mostly algorithms rather than data-intensive (that is, they are more CPU-bound than I/O-bound). Parallel implementation of the cross-correlation execution over the local network, or in some cases over a Wide Area Network (WAN), helps reducing the processing time. The aim of this paper is to discuss the possibility of distributing the cross-correlation computational process over the available PCs in the local network. Moreover, the algorithm portion that is sent to a remote PC, within the LAN, will be redistributed over the available CPU cores on that computer yielding to maximum utilization of all available cores in the local area network. The load balancing problem will be addressed as well.
Free
Scientific article
Medical imaging appliances play a pivotal role in preventive medicine as the industry combat to low patient expense and acquire early disease estimation using nonintrusive methods. There are proprietary software packages which provide fast development for designing image processing algorithms. Another trend is to use open source softwares. With the advancement of VLSI (Very Large Scale Integration) technology, hardware implementation has also become an alternative. Proprietary hardwares provide flexibility, efficient power and timing constraints whereas open source hardwares provide optimum quality and cost constraints. The Present study is useful for image architects, researchers, biologists to learn various proprietary and open sources softwares as well as hardwares utilized for distinct applications of the healthcare industry.
Free
Accuracy Improvement in Palmprint Authentication System
Scientific article
Biometric authentication has been emerged as a reliable means to control a person's access to physical and virtual places. Despite the various efforts made on biometrics, accuracy of the authentication/identification is the main concern and it has to be completely investigated. The paper presents critical analysis of the matching score values in such a manner that system accuracy is increased. Min Max Threshold Range (MMTR) technique is proposed that provides two levels of authentication and increase in accuracy is observed. The methodology of increase in accuracy is observed on various feature extraction methods.
Free
Achieving Robustness in Face Recognition by Effective Feature Acquisition
Scientific article
In the past few decades, face recognition has been a widely researched topic, since it is a robust means of authentication. Extraction of features from the face images during face recognition is a very challenging task. Hence, proper selection of appropriate feature extraction algorithms is vital in this regard. Many robust feature extraction techniques do exist. But their proper selection and combination also plays an utmost role. In this study, 2D face recognition was achieved using the combination of local binary pattern (LBP), principal component analysis (PCA) and Support Vector Machines (SVM). Along with retaining most of the information, PCA is used to reduce multidimensional data to lower dimensions. LBP was mainly used to tackle the problems arising due to expressions. As the facial expression changes, the effect gets prevalent on the rest of the organs of the face. Similarly, the intensity of the corresponding pixels of images also changes. Hence, this study aims to overcome these challenges by applying PCA and LBP algorithms on face images to increase the recognition rate. SVM was used to perform classification on these datasets. This hybrid approach of using LBP and PCA in conjunction increased the recognition rate (RR) and decreased the false match rate. Therefore, this method was found to be more suitable for real-time applications.
Free
Acne Types Prediction Using Acne Images based on Modified Link Net-B7 and HR-Net Algorithm
Scientific article
Acne is a persistent skin disorder that typically affects children in the age range of 12 to 25. Both inflammatory and non-inflammatory skin diseases can coexist with various types of acne, such as papules, pustules, nodules, cysts, blackheads, and whiteheads. In recent times, the study of acne has been carried out conventionally, with a manual approach for determining the ROI. As a result, the patient's face will be physically counted and marked with the acne that was found in the ROI. This manual method could result in incorrect identification and diagnosis of acne. Moreover, it is still difficult to determine the type of acne related to another. The necessity for patients to visit a dermatologist is growing despite the difficulties in identifying acne manually. For a patient, waiting for the dermatologist to become available is challenging. Thus, an automated application for recognizing acne types is needed, as it may help these individuals. In order to address these problems, a dataset containing images of skin diseases is created. Lanczos resampling, which is frequently used to shift or enhance a digital signal's sampling rate by a fraction of the sampling interval, is employed in the preprocessing of the skin disease data. Subsequently, the pre-processed images are segmented using the Modified Link Net-B7 in order to eliminate noise and correctly categorize images of acne with the segmented skin images. After the model has been trained and validated, the Acne type prediction is forecast using the HR-Net algorithm. The performance metrics for this developed model are FPR, FOR, NPV, kappa, error, accuracy, precision, sensitivity, specificity, f1-score, kappa, training time, testing time, and execution time. Performance metrics values of 95.17%, 94.10%, 92.33%, 96.34%, 93.15%, 85.74%, 4.83%, 4%, 6%, 95%, 7.7%, 1492, 23 and 1515 have been reached for the proposed approach. Therefore, compared to the existing models, Acne type prediction using the different types of Acne disease images based on modified Link Net-B7 and HR-Net algorithm performs better.
Free
Acoustic Modeling of Bangla Words using Deep Belief Network
Scientific article
Recently, speech recognition (SR) has drawn a great attraction to the research community due to its importance in human-computer interaction bearing scopes in many important tasks. In a SR system, acoustic modelling (AM) is crucial one which contains statistical representation of every distinct sound that makes up the word. A number of prominent SR methods are available for English and Russian languages with Deep Belief Network (DBN) and other techniques with respect to other major languages such as Bangla. This paper investigates acoustic modeling of Bangla words using DBN combined with HMM for Bangla SR. In this study, Mel Frequency Cepstral Coefficients (MFCCs) is used to accurately represent the shape of the vocal tract that manifests itself in the envelope of the short time power spectrum. Then DBN is trained with these feature vectors to calculate each of the phoneme states. Later on enhanced gradient is used to slightly adjust the model parameters to make it more accurate. In addition, performance on training RBMs improved by using adaptive learning, weight decay and momentum factor. Total 840 utterances (20 utterances for each of 42 speakers) of the words are used in this study. The proposed method is shown satisfactory recognition accuracy and outperformed other prominent existing methods.
Free
Acoustic Signal Based Fault Detection in Motorcycles – A Comparative Study of Classifiers
Scientific article
The sound patterns generated by the vehicles give a clue of the health conditions. The paper presents the fault detection of motorcycles based on the acoustic signals. Simple temporal and spectral features are used as input to four types of classifiers, namely, dynamic time warping (DTW), artificial neural network (ANN), k-nearest neighbor (k-NN) and support vector machine (SVM), for a suitability study in automatic fault detection. Amongst these classifiers the k-NN is found to be simple and suitable for this work. The overall classification accuracy exhibited by k-NN classifier is over 90%. The work finds applications in automatic surveillance, detection of non-compliance with traffic rules, identification of unlawful mixture of fuel, detection of over-aged vehicles on road, vehicle fault diagnosis and the like.
Free
Acoustic Signal based Traffic Density State Estimation using SVM
Scientific article
Based on the information present in cumulative acoustic signal acquired from a roadside-installed single microphone, this paper considers the problem of vehicular traffic density state estimation. The occurrence and mixture weightings of traffic noise signals (Tyre, Engine, Air Turbulence, Exhaust, and Honks etc) are determined by the prevalent traffic density conditions on the road segment. In this work, we extract the short-term spectral envelope features of the cumulative acoustic signals using MFCC (Mel-Frequency Cepstral Coefficients). Support Vector Machines (SVM) is used as classifier is used to model the traffic density state as Low (40 Km/h and above), Medium (20-40 Km/h), and Heavy (0-20 Km/h). For the developing geographies where the traffic is non-lane driven and chaotic, other techniques (magnetic loop detectors) are inapplicable. SVM classifier with different kernels are used to classify the acoustic signal segments spanning duration of 20–40 s, which results in average classification accuracy of 96.67% for Quadratic kernel function and 98.33% for polynomial kernel function, when entire frames are considered for classification.
Free
Adaptive Image Enhancement Using Image Properties and Clustering
Scientific article
Image Enhancement is the method of improving the visibility of given image. Image Properties are used for the analysis of Quality of the given image. Various image Properties considered to improve the quality of the image. The Classification or grouping of images can be made by applying unsupervised image Classification algorithm. In our proposed method, various image properties are studied and an Adaptive K-means Clustering method is applied for Fractal image with Entropy Properties. The images are to enhanced on the basis of its grouping automatically. The resulted Classification can be acceptable by the user since the grouping is made on the type of the image i.e., Good Visible, Moderate and Blur images.
Free
Adaptive Modulation and Coding with Channel State Information in OFDM for WiMAX
Scientific article
WiMAX is a broadband wireless communication system which provides fixed as well as mobility services. The mobile-WiMAX offers a special feature that has adopted an adaptive modulation and coding (AMC) in OFDM to provide higher data rates and error free transmission. AMC technique employs the channel state information (CSI) to efficiently utilize the channel and maximize the throughput with better spectral efficiency. In this paper, LSE, MMSE, LMMSE, Low rank (Lr)-LMMSE channel estimators are integrated with the physical layer. The performance of estimation algorithms is analyzed in terms of BER, SNR, MSE and throughput. Simulation results proved that increment in modulation scheme size causes to improvement in throughput along with BER value. There is a trade-off among modulation size, BER value and throughput.
Free
Adaptive Quantization Index Modulation Audio Watermarking based on Fuzzy Inference System
Scientific article
Many of the adaptive watermarking schemes reported in the literature consider only local audio signal properties. Many schemes require complex computation along with manual parameter settings. In this paper, we propose a novel, fuzzy, adaptive audio watermarking algorithm based on both global and local audio signal properties. The algorithm performs well for dynamic range of audio signals without requiring manual initial parameter selection. Here, mean value of energy (MVE) and variance of spectral flux (VSF) of a given audio signal constitutes global components, while the energy of each audio frame acts as local component. The Quantization Index Modulation (QIM) step size Δ is made adaptive to both the global and local features. The global component automates the initial selection of Δ using the fuzzy inference system while the local component controls the variation in it based on the energy of individual audio frame. Hence Δ adaptively controls the strength of watermark to meet both the robustness and inaudibility requirements, making the system independent of audio nature. Experimental results reveal that our adaptive scheme outperforms other fixed step sized QIM schemes and adaptive schemes and is highly robust against general attacks.
Free
Adaptive Remote Sensing Texture Compression on GPU
Scientific article
Considering the properties of remote sensing texture such as strong randomness and weak local correlation, a novel adaptive compression method based on vector quantizer is presented and implemented on GPU. Utilizing the property of Human Visual System (HVS), a new similarity measurement function is designed instead of using Euclid distance. Correlated threshold between blocks can be obtained adaptively according to the property of different images without artificial auxiliary. Furthermore, a self-adaptive threshold adjustment during the compression is designed to improve the reconstruct quality. Experiments show that the method can handle various resolution images adaptively. It can achieve satisfied compression rate and reconstruct quality at the same time. Index is coded to further increase the compression rate. The coding way is designed to guarantee accessing the index randomly too. Furthermore, the compression and decompression process is speed up with the usage of GPU, on account of their parallelism.
Free
Adaptive Signal Processing for Improvement of Convergence Characteristics of FIR Filter
Scientific article
When the length of the filter and consequently the number of filter coefficients increase, the design of the filter becomes complex and therefore the popular NLMS algorithm has been replaced with MMax NLMS algorithm. But its performance in terms of convergence characteristics reduces to an extent though the filter design becomes very easy i.e., convergence occurs at a later stage taking too much computational time for the processing of the signal. In this paper, a proposal for improving the convergence characteristics is made without compromising the performance of the design and affecting the tap-selection process of the MMax NLMS algorithm. With the introduction of the concept of variable step-size for the filter coefficients, loss in the performance due to MMax NLMS algorithm can be effectively lowered and the convergence is better achieved in the filter deign.
Free
Adjustive reciprocal whale optimization algorithm for wrapper attribute selection and classification
Scientific article
One of the most difficult challenges in machine learning is the data attribute selection process. The main disadvantages of the classical optimization algorithms based attribute selection are local optima stagnation and slow convergence speed. This makes bio¬-inspired optimization algorithm a reliable alternative to alleviate these drawbacks. Whale optimization algorithm (WOA) is a recent bio-inspired algorithm, which is competitive to other swarm based algorithms. In this paper, a modified WOA algorithm is proposed to enhance the basic WOA performance. Furthermore, a wrapper attribute selection algorithm is proposed by integrating information gain as a preprocessing initialization phase. Experimental results based on twenty mathematical optimization functions demonstrate the stability and effectiveness of the modified WOA when compared to the basic WOA and the other three well-known algorithms. In addition, experimental results on nine UCI datasets show the ability of the novel wrapper attribute selection algorithm in selecting the most informative attributes for classification tasks.
Free
Advanced control of switching ignition by smart helmet
Scientific article
The impact of Accident effect, a lot of human livelihoods and their career, due to the negligence of wearing the helmets on a daily basis in India. To end this suffering, we have a social responsibility development projects. The motorcycle driver without wearing the helmet can be killed if it hit or crash and bring his life in danger. Wearing a helmet reduces the possibility of danger of life. In India, for example, wearing a helmet is mandatory in the law and the drivers need to follow it. Similar rules are in many countries. Therefore, this project is designed to improve motorcycle safety and make motorcyclist compulsory for wearing it. As you can see, we have a lot to think about it. It is a type that is used in the driver's helmet to drive a bike safely. The aim of this paper is to protect the driver life and decrease the death rate at road accident by making the helmet. It uses a hands-free kit and advances feature like compulsory of wearing helmet and theft security. Bluetooth wireless communication module (2.4 GHz band transceiver) can be used for transmission between the transmitter and the receiver. The driver needs to wear a helmet otherwise a helmet automatically keeps the engine OFF. If rider wears the helmet, ignition will be automatically ON. In the sensor, we transmit information to the wireless communication module, which is connected to the bike. This system is one of the devices built in the helmet; the second devices are inside the bike. Monitor recognizes the power devices with a Force-sensing resistor (FSR). Wireless data receiver, encoder, and a transmitter are used to communicate helmet with the bike. AT mega controller in both devices used as a CPU. It is one of the most advanced electronic projects for the Road Safety Systems.
Free
