Статьи журнала - International Journal of Image, Graphics and Signal Processing
Все статьи: 1110
DNA 3D Self-assembly Algorithmic Model to Solve Maximum Clique Problem
Статья научная
Self-assembly reveals the essence of DNA computing, DNA self-assembly is thought to be the best way to make DNA computing transform into computer chip. This paper introduce a method of DNA 3D self-assembly algorithm to solve the Maximum Clique Problem. Firstly, we introduce a non-deterministic algorithm. Then, according to the algorithm we design the types of DNA tiles which the computation needs. Lastly, we demonstrate the self-assembly process and the experimental methods which could get the final result. The computation time is linear, and the number of the distinctive tile types is constant.
Бесплатно
Статья научная
The main disadvantage of the classical direct torque control is high torque and flux ripples. This is due to hysteresis comparators suffer from a variable switching frequency and a high torque ripple. Besides, a hybrid strategy; Direct Torque Control with Space Vector Modulation (DTC -SVM) is established using Interval Type-2 Fuzzy Logic Controller (IT2FLC) for enhancing control performance parameters to reducing torque and flux ripple. In this work, a IT2FLC is applied to the DTC-SVM of Double Stator Induction Machine (DSIM). Simulation results are shown to present the robustness and efficiency of the recommended control strategy.
Бесплатно
DYNAMIC JOINT LOAD TRANSFER EFFICIENCY OF RIGID PAVEMENT
Статья научная
the mechanistic analysis presented in this paper is only the beginning of new approach for understanding the real joint load transfer capability on airport and highway concrete pavements. It gives up the two major assumptions those have been popularly adopted by hundreds of published papers: the load is transferred under a wheel with zero speed and with fixed position. The real load transfer in field is always under wheels with non-zero speed and with varied position at any moment. The objective of this study focuses on quantifying the dynamic effects of a moving wheel while it is crossing a joint on a pavement. The analysis is conducted using a model of two-slab system on Kelvin foundation under a moving wheel with variable speed v, different pavement damping Cs, foundation reaction modulus k and foundation damping Ck. The dynamic joint load transfer efficiency is temporarily and empirically defined by the peak strain ratio LTE(S) on the two sides of a joint. The primary findings include: (1) The higher speed of a moving wheel leads to the higher LTE(S);(2) The larger the pavement damping Cs leads to the higher LTE(S);(3) The numerical ratio c(=LTE(S)dynamic/ LTE(S)static) varies in the range 1 to 2 mainly depending on speed v and damping Cs;(4) The LTE(S)dynamic is not sensitive to foundation reaction modulus k and foundation damping Ck. Further researches are needed for appropriate applications of the new model in practice.
Бесплатно
Data Content Weighing for Subjective versus Objective Picture Quality Assessment of Natural Pictures
Статья научная
Estimating the visual quality of picture is a real challenge for various picture and video frame applications. The aim is to evaluate the quality of picture automatically in both subjective (human visual frame work) and objectively. The quality of picture is evaluated by comparing precision and closeness of a picture with reference or error free picture. The quality estimation can be done to achieve consistency in desired quality of picture with help of modeling remarkable physiological, psycho visual components framework and picture fidelity measure methods. In this article, the picture quality is evaluated by analyzing loss of picture information of the distortion system using differing noise models and examine the relationship between picture data, visual quality and error metric. The quality of picture & video frame assessment is really important that, every human can judge the visual quality of natural picture. The subjective quality of picture is assessed by using structural similarity metric, objective quality of picture is computed by root means squared error, mean squared error and peak signal to noise ratio and data content in picture is weighted through entropy.
Бесплатно
Статья научная
Deep learning (DL) architectures are becoming increasingly popular in modern traffic systems and self-driven vehicles owing to their high efficiency and accuracy. Emerging technological advancements and the availability of large databases have made a favorable impact on such improvements. In this study, we present a traffic sign recognition system based on novel DL architectures, trained and tested on a locally collected traffic sign database. Our approach includes two stages; traffic sign identification from live video feed, and classification of each sign. The sign identification model was implemented with YOLO architecture and the classification model was implemented with Xception architecture. The input video feed for these models were collected using dashboard camera recordings. The classification model has been trained with the German Traffic Sign Recognition Benchmark dataset as well for comparison. Final accuracy of classification for the local dataset was 96.05% while the standard dataset has given an accuracy of 92.11%. The final model is a combination of the detection and classification algorithms and it is able to successfully detect and classify traffic signs from an input video feed within an average detection time of 4.5fps
Бесплатно
Deep-ShrimpNet fostered Lung Cancer Classification from CT Images
Статья научная
Lung cancer affects the majority of people, due to genetic changes in lung tissues. Several existing methods on lung cancer detection are utilized with machine learning, but it does not accurately classify the lung cancer and also it takes high computation time. To overwhelm these issues, Deep-ShrimpNet fostered Lung cancer classification from CT images (LCC-Deep-ShrimpNet) is proposed. Initially, the input lung CT images are taken from IQ-OTH/NCCD Lung Cancer Dataset. Then the input lung CT images are pre-processed using Kernel co-relation method. Then these pre-processed lung CT images are given to Bayesian fuzzy clustering for extracting lung nodule region. Then the extracted lung nodule region is given into Deep-ShrimpNet classifier for representing features and classifying the lung CT images as normal (Healthy), Benign, and Malignant. The proposed LCC-Deep-ShrimpNet method is activated in python. The performance of the proposed LCC-Deep-ShrimpNet method attains 26.26%, 16.9%, 12.67%, 21.52% and 24.05% high accuracy, 68.86%, 59.57%, 57%, 62.72% and 65.69% low error rate and 60.76%, 53.67%, 68.58%, 59% and 56.61% low computation time compared with the existing methods.
Бесплатно
Denoising Self-Distillation Masked Autoencoder for Self-Supervised Learning
Статья научная
Self-supervised learning has emerged as an effective paradigm for learning universal feature representations from vast amounts of unlabeled data. It’s remarkable success in recent years has been demonstrated in both natural language processing and computer vision domains. Serving as a cornerstone of the development of large-scale models, self-supervised learning has propelled the advancement of machine intelligence to new heights. In this paper, we draw inspiration from Siamese Networks and Masked Autoencoders to propose a denoising self-distilling Masked Autoencoder model for Self-supervised learning. The model is composed of a Masked Autoencoder and a teacher network, which work together to restore input image blocks corrupted by random Gaussian noise. Our objective function incorporates both pixel-level loss and high-level feature loss, allowing the model to extract complex semantic features. We evaluated our proposed method on three benchmark datasets, namely Cifar-10, Cifar-100, and STL-10, and compared it with classical self-supervised learning techniques. The experimental results demonstrate that our pre-trained model achieves a slightly superior fine-tuning performance on the STL-10 dataset, surpassing MAE by 0.1%. Overall, our method yields comparable experimental results when compared to other masked image modeling methods. The rationale behind our designed architecture is validated through ablation experiments. Our proposed method can serve as a complementary technique within the existing series of self-supervised learning approaches for masked image modeling, with the potential to be applied to larger datasets.
Бесплатно
Denoising and Enhancement of Medical Images Using Wavelets in LabVIEW
Статья научная
In this paper, we have proposed a novel image enhancement technique based on M band wavelets. The conventional image enhancement algorithms opt for contrast enhancement using equalization techniques. Contrast enhancement is one of the most important issues in image enhancement techniques. High difference in luminance reflected from two adjacent surfaces results in a good contrast image which makes the object more distinguishable from other objects in the background. Many a times owing to over contrast, minute details of the images are lost; which cannot be tolerated for biomedical images. Moreover, they don't account for the noise embedded in the images. Also denoising using conventional filters result in blurring of images. The proposed algorithm not only denoises the image by retaining the high frequency edges, but also increases the contrast and generates a high resolution image. Various parameters like MSE and PSNR are been taken into account for comparison of enhanced images generated from the proposed algorithm with that of the conventional techniques.
Бесплатно
Denoising of Noisy Pixels in Video by Neighborhood Correlation Filtering Algorithm
Статья научная
A fast filtering algorithm for color video based on Neighborhood Correlation Filtering is presented. By utilizing a 3 × 3 pixel template, the algorithm can discriminate and filter various patterns of noise spots or blocks. In contrast with many kinds of median filtering algorithm, which may cause image blurring, it has much higher edge preserving ability. Furthermore, this algorithm is able to synchronously reflect image quality via amount, location and density statistics. Filtering of detected pixels is done by NCF algorithm based on a noise adaptive mean absolute difference. The experiments show that the proposed method outperforms other state-of-the-art filters both visually and in terms of objective quality measures such as the mean absolute error (MAE), the peak-signal-to-noise ratio (PSNR) and the normalized color difference (NCD).
Бесплатно
Статья научная
Non-Small Cell Lung Cancer (NSCLC) represents a significant health challenge globally, with high mortality rates largely attributed to late-stage diagnosis. This paper details a novel approach for denoising computed tomography (CT) scans through 2-dimensional Fractional Fourier transform (2D-FrFT), which has been reported to be effective for time-frequency signal/image processing applications. To establish a foundation for the FrFT filtering of the original and corrupt dataset, a variable fractional-order image processing technique was used. Based on the derived pre-processing of CT scans, a classification model was developed with hand-crafted features and a 2-layer neural network to classify 4834 CT scans collected from the Lung Image Database Consortium image (LIDC-IDRI) dataset into classes of normal lungs and NSCLC infected lungs. This work presents an approach to improving the performance of NSCLC detection through a lightweight neural network that attains 1.00 accuracy, 1.00 sensitivity, and 1.00 AUC. An additional real-time lung cancer dataset from PGI Rohtak, Haryana, has been considered to validate the model and prove its performance against overfitting. The experimental analysis showed better results than the existing methods for both LIDC-IDRI and hospital datasets and could be a competent assistant to clinicians in detecting NSCLC.
Бесплатно
Density Based Script Identification of a Multilingual Document Image
Статья научная
Automatic Pattern Recognition field has witnessed enormous growth in the past few decades. Being an essential element of Pattern Recognition, Document Image Analysis is the procedure of analyzing a document image with the intention of working out the contents so that they can be manipulated as per the requirements at various levels. It involves various procedures like document classification, organizing, conversion, identification and many more. Since a document chiefly contains text, Script Identification has grown to be a very important area of this field. A Script comprises the text of a document or a manuscript. It is a scheme of written characters and symbols used to write a particular language. Languages are written using scripts, but script itself is made up of symbols. Every language has its own set of symbols used for writing it. Sometimes different languages are written using the same script, but with marginal modification. Script Identification has been performed for unilingual, bilingual and multilingual document images. But, negligible work has been reported for Kashmiri script. In this paper, we are analyzing and experimentally testing statistical approach for identification of Kashmiri script in a document image along with Roman, Devanagari & Urdu scripts. The identification is performed on offline machine-printed scripts and yields promising results.
Бесплатно
Depth and Intensity Gabor Features Based 3D Face Recognition Using Symbolic LDA and AdaBoost
Статья научная
In this paper, the objective is to investigate what contributions depth and intensity information make to the solution of face recognition problem when expression and pose variations are taken into account, and a novel system is proposed for combining depth and intensity information in order to improve face recognition performance. In the proposed approach, local features based on Gabor wavelets are extracted from depth and intensity images, which are obtained from 3D data after fine alignment. Then a novel hierarchical selecting scheme embedded in symbolic linear discriminant analysis (Symbolic LDA) with AdaBoost learning is proposed to select the most effective and robust features and to construct a strong classifier. Experiments are performed on the three datasets, namely, Texas 3D face database, Bhosphorus 3D face database and CASIA 3D face database, which contain face images with complex variations, including expressions, poses and longtime lapses between two scans. The experimental results demonstrate the enhanced effectiveness in the performance of the proposed method. Since most of the design processes are performed automatically, the proposed approach leads to a potential prototype design of an automatic face recognition system based on the combination of the depth and intensity information in face images.
Бесплатно
Depth based Occlusion Detection and Localization from 3D Face Image
Статья научная
In this paper, authors have proposed two novel techniques for occlusion detection and then localization of the occluded section from a given 3D face image if occlusion is present. For both of these methods, at first, the 2.5D or range face images are created from input 3D face images. Then for detecting the occluded faces, two approaches have been followed, namely: block based and threshold based. These two methods have been investigated individually on Bosphorus database for localization of occluded portion. Bosphorus database consists of different types of occlusions, which have been considered during our research work. If 2D and 3D images are compared then 3D images provide more reliable, accurate, valid information within digitized data. In case of 2D images each point, named as pixel, is represented by a single value. One byte for gray scale and three byte for color images in a 2D grid whereas in case of 3D, there is no concept of 2D grid. Each point is represented by three values, namely X, Y and Z. The 'Z' value in X-Y plane does not contain the reflected light energy like 2D images. The facial surface's depth data is included in Z's point set. The threshold or cutoff based technique can detect the occluded faces with the accuracy 91.79% and second approach i.e. block based approach can successfully detect the same with the success rate of 99.71%. The accuracy of the proposed occlusion detection scheme has been measured as a qualitative parameter based on subjective fidelity criteria.
Бесплатно
Статья научная
Nowadays, the use of Rehabilitation Robots for stroke patients has been growing rapidly. However, there was a limited scope of using such Rehabilitation Robots for patients suffer from an accidental physical fracture. Since the pain condition of such accidents needs a critical treatment, precise control of such robotic manipulators is mandatory. This paper presents the design and control of the Elbow-Forearm Rehabilitation Robot by considering the pain level of the patient. This design consists of the mechatronic design processes including mechanical design, controller design, and Virtual prototyping using ADAMS-MATLAB Co-simulation. The pain level is estimated using three parameters i.e the patient general condition, the muscle strain, and the duration of exercise from the beginning of rehabilitation. Based on these three input parameters, the manipulator's desired range of motion has been determined using the Fuzzy Logic System. The output of this fuzzy logic system would be an input to the main control system. ADAMS-MATLAB Co-simulation is carried out based on three reference inputs i.e Step, sinusoidal and the proposed fuzzy reference input. Using step input, we have discussed the step response characteristics of the developed system. The Co-simulation of the ADAMS dynamic model is realized with a 30 degree oscillating motion by providing a sinusoidal input. Finally, using the developed fuzzy reference input, we have done a Co-simulation of ADAMS plant. The simulation result demonstrates that the proposed PID controller with gains Kp=0.001 and Ki=0.01 yields 99.6% of accuracy in the tracking of the reference input as compared to the simulation without introducing controller which has an accuracy of 94.9%. The simulation also shows that derivative gain (Kd) of the PID controller has no effect on the system so that it is over damping system. From the above three simulation schemes, we can conclude that the Elbow-Forearm rehabilitation robot could be controlled as per the desired signal. Since this desired signal is developed from the pain level of the patient, we can say that the system is controlled as per the pain level of the patient.
Бесплатно
Design and Development of PC Based Data Acquisition System for Radiation Measurement
Статья научная
A PC based data acquisition was designed and developed using GM detector and a programmable microcontroller 16F876 of PIC family. This unit was calibrated with the standard Canberra Counter. It gave prompt response directly and has low power consumption. It was tested for gamma ray measurement to continuously monitor a radiological resulting from the natural and man-made sources that threat site security and human health. The system was simple to use, required no additional hardware and allows the selection of data. The collected data were easily being exported to a PC via parallel port. A "C" language program was developed to control the function of the entire system, using PCWH compiler.
Бесплатно
Design and Development of an Intelligent Home with Automated Environmental Control
Статья научная
Intelligent home automation has become more popular over the decade. Integration of automation in a home security, enhances its self-dependability. An intelligent home, integrated with various smart system modules can provide convenient and safe environment for the inhabitants and home appliances which can be easily controlled and monitored even from a remote distance. In this paper an intelligent home automation and environmental solution is proposed along with the architecture of integrated sensor modules. This proposed system is embedded with electronic lock driven with password verification and biometric finger print scanner. This sensing tools ensure the system to prevent unauthorized access. It is comprised with video recording of unauthorized person or intruder moving around the home or office premises. Moreover, PIR motion sensor, IR sensors would also work as safeguard by helping to capture image and Skype video calling from the inside of home or office. User will also be able to monitor the present condition of the home or office by using Facebook post of image and message status. The implemented system as a prototype for the justification and attestation of the proposals has been tested successfully. The observed data ensures that the system is working efficiently.
Бесплатно
Design and Implementation of Novel Multiplier using Barrel Shifters
Статья научная
The paper presents a design scheme to provide a faster implementation of multiplication of two signed or unsigned numbers. The proposed scheme uses modified booth's algorithm in conjunction with barrel shifters. It provides a uniform architecture which makes upgrading to a bigger multiplier much easier than other schemes. The verification of the proposed scheme is illustrated through implementation of 16x16 multiplier using ISIM simulator of Xilinx Design Suite ISE 14.2. The scheme is also mapped onto hardware using Xilinx Zynq 702 System on Chip. The performance is compared with existing schemes and it is found that the proposed scheme outperform in terms of delay.
Бесплатно
Design and Implementation of Optimal PID Controller Using PLC for Al-Tahady ESP
Статья научная
The electrostatic precipitator (ESP) is an extensively used system in metallurgical industries and the generation of power to decrease the release of dust in the flue gas. In the design of the Electrostatic precipitator unit, gas emission uniform distribution is expected to fulfil its best aggregation performance. Programming Logic Controller (PLC) is a controller for industrial process automation and self-monitoring. A lot of industries utilized PLC to automatically control the entire process with less involvement from the human and to evade errors. In this paper, A mathematical model for Electrostatic precipitator from physical parameters and analysis has been developed. The controller is built depending on this model using the basic principle of a well-known A Proportional Integral Derivative (PID) controller to control the high voltage of the Electrostatic precipitator (ESP) by adjusting the opening of voltage and current by applying analogue signals (4-20 mA) from output cards of the PLC. The simulation results paved the way to build a practical system. building the mathematical model by using the Identification Toolbox of MATLAB® Version 9.6. The system was built using Allen Bradley PLC. The effect of control parameters (PID) in the case of voltage or current has been studied to demonstrate the efficiency of the model for the precipitator and observer in the case of the control system for the Al-Tahady ESP. The PID controller was built and the best values for the Electrostatic Precipitator controller are (KP=2.3904, KI=3.5382, KD=0.3). PID controller reduces steady-state errors.
Бесплатно
Статья научная
This paper presents a design and implementation of Root Mean Square (RMS) measurement system based on fast discrete Wavelet using a dsPIC-type microcontroller. For data acquisition, two sensors have been used such as the voltage divider for sensing voltage and the Hall Effect sensor for sensing the current. The proposed method has the real-time calculation advantages and can be used in sinusoidal and non–sinusoidal electrical power systems. The results of calculations have been verified using MATLAB and Proteus ISIS simulations. It has been proved that the Wavelet transform measuring technique is more accurate as it takes in consideration all the harmonics in the analyzed signal and provides temporal information, which is absent in other transforms or not directly available in the Fourier transform.
Бесплатно
Design and Implementation of Speckle Noise Reduction Algorithm Using 2D Ultrasound Image
Статья научная
Ultrasound is mostly used for diagnosis to deal with the specific abnormality in human body. To observe the internal organs including liver, kidneys, pancreas, thyroid gland, ovaries etc. ultrasound can be used. In diagnostic applications, 2 to 18 MHz frequencies are used. The sound wave explorations occurred through soft tissue and fluids. It bounces back as echoes from denser surfaces and creates an image. While producing ultrasound images from echo signal speckle noise is induced in a multiplicative way. Thus, speckle becomes the key challenge for ultrasound imaging. Several speckle reducing linear, non-linear and anisotropic diffusion-based methods are implemented to preserve the sharp edges of ultrasound images. Those methods contain lake of smoothing and edge preservation. However, this research proposed a combined method of adaptive filter (wiener) and anisotropic diffusion (modified Perona Malik) for speckle reduction of 2D ultrasound images by retain the important anatomical features. A comparison of all the existing methods studied based on the simulated experiment. To test the methods liver, kidney, heart and pancreas noise free images are used. Then, speckle noise is manually added with distinguished variance in between 0.02 and 0.20. Quality metrics are used to test the performance and show the improvements of the proposed method. About 71.79% structure similarity (SSIM), 66.72% root mean square error (RMSE), 56.93% signal to noise ratio (SNR), and 62.30% computational time are improved on average compared with the other methods.
Бесплатно
