International Journal of Image, Graphics and Signal Processing @ijigsp
Journal articles - International Journal of Image, Graphics and Signal Processing
All articles: 1207
Self-supervised Model Based on Masked Autoencoders Advance CT Scans Classification
Scientific article
The coronavirus pandemic has been going on since the year 2019, and the trend is still not abating. Therefore, it is particularly important to classify medical CT scans to assist in medical diagnosis. At present, Supervised Deep Learning algorithms have made a great success in the classification task of medical CT scans, but medical image datasets often require professional image annotation, and many research datasets are not publicly available. To solve this problem, this paper is inspired by the self-supervised learning algorithm MAE and uses the MAE model pre-trained on ImageNet to perform transfer learning on CT Scans dataset. This method improves the generalization performance of the model and avoids the risk of overfitting on small datasets. Through extensive experiments on the COVID-CT dataset and the SARS-CoV-2 dataset, we compare the SSL-based method in this paper with other state-of-the-art supervised learning-based pretraining methods. Experimental results show that our method improves the generalization performance of the model more effectively and avoids the risk of overfitting on small datasets. The model achieved almost the same accuracy as supervised learning on both test datasets. Finally, ablation experiments aim to fully demonstrate the effectiveness of our method and how it works.
Free
Semantic Segmentation of Multispectral Satellite Images Using Residual Convolutional Networks
Scientific article
Satellite imagery is always used to study spatial geographies to find water, residential, farmland, and forest lands; which can be further used for township development and planning, landscape detection etc. Semantic segmentation and image classification are the two crucial procedures in determining the spatial geographies. In order to improve the generalization ability of semantic segmentation algorithms, a combined model of UNet_ResNet is used in this paper. The engineered model is a type of Convolutional Neural Networks using GeoGANs which detects semantic patches in neural networks with smaller sizes and regional characteristics within a certain spatial and pixel scale. However, it faces a semantic segmentation challenge of identifying roadways in metropolitan areas. The model shows an accuracy score from 93% to 97.3% for image classification and segmentation purposes which fares better than the implementation of various existing architectures.
Free
Semantic Segmentation of Tuberculosis Bacilli from Microscopic Sputum Smear Images Using TransUNet
Scientific article
According to the World Health Organization (WHO) touchstones of 2022, Tuberculosis is the second dominant disease after COVID-19. Around one-fourth of the comprehensive population is ascertained to have tuberculosis. Timely detection and prevention of tuberculosis is a must to overcome its harmful effects. The method most often used in ascertaining whether a patient has tuberculosis, is examining his or her sputum sample. In the process, the isolation of the bacilli is done manually, and hence it is prone to error. Segmentation illustrates and enlightens objects or particles within an image, thus extracting the Region of Interest (ROI). The contemplated study uses TransUNet architecture to segment tuberculosis bacilli from sputum images to increase diagnostic accuracy and performance. The attention mechanism used in the TransUNet model helps to identify the spatial hierarchies present in image. It is an extremely tough task for naive or traditional segmentation algorithms to deal with the inherent complexity of sputum images. Hence, this study introduces an approach to capture the intrinsic features and dependencies needed to segment mycobacterium or TB bacilli by leveraging the TransUNet model. The model achieved an average Dice Score of 92.795%, a mean Intersection over Union (IoU) of 88.845%, and a segmentation accuracy of 99.19% on the Mosaic and Ziehl-Neelsen datasets. These results surpassed several existing state-of-art methods like UNet, clustering and thresholding, depicting the superior capability of TransUNet in segmenting the TB bacilli. It deepens the potentiality of transformer-based CNN models, especially TransUNet, for improving the diagnosis of tuberculosis and supporting disease management.
Free
Semi-fragile Image Watermarking Algorithm Based on Region-Segmentation
Scientific article
In order to improve the invisibility and the robustness of semi-fragile watermarking, the paper first brings up the idea which embedding watermark based on the attacks’ characteristic, brings forward the region segmentation operator and the image-segmentation embedding method, puts forward the characteristic and its representation in DWT transform domain based on visual features model, and brings forward the quantized central limit theorem which applies to adjusting the coefficients in general transform domain. These all make semi-fragile watermarking embedded through dynamic quantization achieve the greatest robustness. It gives wavelet transform domain coefficient redressal operator and the best restoration probability of the pixel value adjusting in experiments when the images were under attack. It leads up to a better invisibility of carrier image, a better robustness to the image processing, such as JPEG compression, noise adding, filtering, and the larger amount of embedded information. What’s more, it can ascertain the position of vicious attack exactly.
Free
Scientific article
The study is devoted to the analysis of public sentiment towards Ukrainian political figures based on comments on social media, in particular, YouTube and Twitter. The work aims to identify differences in the perception of political leaders and to understand how the platform affects the tone of statements. The main research question is to determine how public opinion about politicians in Ukraine differs between YouTube and Twitter during the full-scale war. To do this, a corpus of comments and tweets from 2022 to 2023 was collected, which went through pre-processing stages (including cleaning up slang and spelling mistakes). The article presents the results of a comprehensive analysis of public opinion on five public figures of Ukraine (S. Prytula, P. Poroshenko, V. Zelensky, S. Sternenko, A. Yermak) based on data from the social networks YouTube and Twitter. For data collection, the YouTube Data API and the Apify platform were used, a corpus of Ukrainian-language comments and tweets was collected and processed, which went through the stages of purification, normalisation and lemmatisation, taking into account slang, surzhyk and spelling mistakes. The sentiment analysis model, built on the basis of multilingual-e5-base embeddings and the XGBClassifier algorithm, showed an accuracy of 89.4%, macro-F1 of 88.7%, and a weighted F1 of 89.1%. Sentiment distribution analysis revealed that, on average, 42% of messages were positive, 36% were negative, and 22% were neutral. Twitter had a higher share of negative statements (up to 40%), while YouTube had a predominance of positive sentiment (up to 47%). The results indicate differences in the perception of public figures on different platforms and confirm the effectiveness of the developed approach for the Ukrainian-speaking segment of social networks. The results indicate significant differences in sentiment distribution: comments on YouTube are more likely to be marked by emotional intensity and harshness. At the same time, Twitter exhibits a more concise but no less polarised discourse. One of the reasons for this difference may be the difference in the format of the platforms, their audience, and the speed of content distribution. Further research should take into account the impact of user demographic biases, as well as the activity of bots or coordinated campaigns that can change the perception of public opinion. The practical significance of the study lies in the fact that its results can be used by politicians, journalists, and public figures to better understand the mood of society, predict reactions to political events, and build more effective communication. At the same time, it is worth noting that there are limitations: automated sentiment analysis has difficulty detecting sarcasm, irony, or context-sensitive meanings, which can affect the Accuracy of the results. In addition, the study takes into account the ethical aspects of data collection and analysis: only publicly available comments were used, without interference in the private sphere of users. There are possible risks of abuse of such technologies, and the need for responsible application of the findings is emphasised.
Free
Serial digital color image watermarking using composite scheme
Scientific article
Digital watermarking is one of the ways to have Copyright protection for digital information. The digital watermarking scheme used for watermark embedding has to satisfy robustness property to ensure the security of the secret information hidden. The scheme presented here will support the above said statement significantly. We propose here the scheme as composition of both blind and non-blind digital watermarking technique in a process of serial watermarking. A secret binary image is embedded in the first cover image to get first watermarked image by using blind watermarking technique. Then this first watermarked image is again embedded into second cover image to get serial watermarked image using non-blind watermarking technique. To extract secret binary image, first non-blind watermark extraction technique and then blind watermark extraction techniques are used. From this composite approach and serial watermark embedding procedure, we achieved considerable fidelity and robustness against - Rotation, JPEG compression and for noises Salt & pepper, Gaussian, Speckle, Poisson and multiple noises.
Free
Shadow Image Processing of X-Ray Screening System for Aviation Security
Scientific article
The aviation security is an important component of aviation safety providing. One of the main goals of aviation security service is to detect dangerous and prohibited objects during passengers and baggage screening. For this purpose, aviation security personnel use various equipment: X-ray screening system, body-scans, metal detectors, moving ions detectors, explosive trace detectors. The X-ray screening system gives information on internal structure of baggage. The main disadvantage of X-ray screening system is rather high level of the false alarm probability. This requires developing new methods of image processing and recognition of dangerous and prohibited objects on the background of other objects. This article develops the principles of shadow image processing while screening the baggage using X-ray system to fix the mentioned disadvantage. The math equation for shadow image is obtained based on the laws of geometry and Beer-Lambert equation taking into account the chosen scanning technique. Based on this, the article is focused to the analysis of simple objects images and their application for complex objects recognition. The article discusses the example of handgun recognition using a new approach based on spectral analysis of developed shadow images. The results of the research can be used for improvement of algorithmic toolkit in aviation security automatic decision-making system while screening the baggage by X-ray equipment.
Free
Shape-Based Wound Localization in Diabetic Foot Ulcer Using Foot Thermograms
Scientific article
The early detection of diabetic ulcers using thermal imaging is an important aspect of non-invasive medical instrumentation. An accurate assessment of a diabetic foot ulcer (DFU) using a machine-based approach requires a crystal-clear region of interest (ROI) of the foot ulcer. Different shapes based on automatic contour determination after the segmentation procedure can act as a major guide for the purpose of appropriate localization of the ROI. The purpose of this paper is to present a novel shape-area-based analysis for precisely localizing the ROI from the patient’s foot. The novel data set, which is suitable for Indian healthcare settings, was created at PGIMER hospital Chandigarh with the support of specialized clinicians. A comparison of various cutting-edge segmentation techniques was carried out. The quantitative analysis concluded that the average area (AA) of ROI, derived from different shapes, was extremely close to the ground truth values and thus offered a better prospective to automatically examine the ulcer area.
Free
Signal propagation analysis at 28GHz and 73GHz millimeter wave bands for next generation networks
Scientific article
Fifth generation (5G) mobile networks demand large bandwidth with the explosive growth of data driven applications. This necessitates enormous amount of spectrum in the Millimeter wave (mmWave) bands to greatly enhance the communication capacity. The mmWave band offers the potential for high-bandwidth communication channels in cellular networks. Relative to conventional networks, dense mmWave networks can achieve both higher data rates and comparable coverage. The paper presents the performance analysis of mobile networks in terms of propagation path loss, coverage probability and data rates for different mm wave operating frequencies of 28GHz and 73GHz. A scenario of multi-users in a micro cell is considered in different environments i.e. rural, sub urban and urban regions and the performance parameters in each case are analyzed. Millimeter wave cellular networks at 28GHz offer less rain attenuation compared to 73GHz and is useful for next generation communications with enhanced data rates and coverage.
Free
Signature based Document Image Retrieval Using Multi-level DWT Features
Scientific article
Automatic signature extraction from document image and retrieval has a large number of applications such as in business offices, organizations, institutes and digital libraries. Hence it has attracted a lot of researchers from the field of document image analysis and processing. This paper proposes a method for automatic signature extraction and signature based document image retrieval using multi-level discrete wavelet transform features. Since the distance measures play a vital role in pattern analysis, classification and clustering, in this paper we also compared the results of retrieval using 7 distance metrics such as Euclidean, Canberra, City-block, Chebychev, Cosine, Hamming and Jaccard. Results obtained in this paper shows that city-block distance with multi-level DWT features outperforms the other 6 distance metrics used for comparison.
Free
Significance of source information for text dependent speaker verification
Scientific article
This work focuses on text dependent speaker verification system where a source feature specifically residual Mel frequency cepstral coefficients (RMFCC), has been extracted in addition to a vocal tract system feature namely Mel frequency cepstral coefficients (MFCC). The RMFCC features are derived from the LP residuals whereas MFCC features are derived from the cepstral analysis of the speech signal. Thus, these two features have different information about the speaker. A four cohort speaker’s set has been prepared using these two features and dynamic time warping (DTW) is used as the classifier. Performance comparison of the text dependent speaker verification model using MFCC and RMFCC features are enumerated. Experimental results shows that, using RMFCC feature alone do not give satisfactory results in comparison to MFCC. Also, the system’s performance obtained using the MFCC features, is not optimum. So, to improve the performance of the system, these two features are combined together using different combination algorithms. The proposed lowest ranking method yields good performance with an equal error rate (EER) of 7.50%. To further improve the efficiency of the system, the proposed method is combined along with the strength voting and weighted ranking method in the hierarchical combination method to obtain an EER of 3.75%.
Free
Silence Removal and Endpoint Detection of Speech Signal for Text Independent Speaker Identification
Scientific article
In this paper we propose a composite silence removal technique comprising of short time energy and statistical method. The performance of the proposed algorithm is compared with the Short Time Energy (STE) algorithm and the statistical method with varying Signal to Noise Ratio (SNR). In the presence of low SNR the performance of proposed algorithm is highly appreciable in compare to STE and statistical method. We have applied the proposed algorithm in the pre processing stage of speaker identification system. A comparison between the speaker identification rate including and excluding the silence removal technique shows around 20% increase in identification rate by the application of this proposed algorithm.
Free
Simplified Model for Fire Resistance Analysis on Steel Staggered-truss System under Lateral Force
Scientific article
In order to investigate the simplified method for the fire resistance analysis on the steel staggered-truss system (SSTS) under the lateral force, a three-dimensional (3-D) model, a plane cooperative (PC) model and a planar model are established by the finite element method respectively. The effect of slabs is considered in the models. The mechanical performances of SSTS at elevated temperature were analyzed and the interaction characteristics between the truss exposed to fire and its adjacent trusses are studied. The results obtained by the above different models were comparatively investigated to explore the applicability of different models for the analysis of SSTS under lateral force and high temperature. The results indicate that the adjacent trusses in SSTS under lateral force could keep good coordination at elevated temperature. When applied to the analysis for SSTS under lateral force at elevated temperature, the 3-D model is the best in accord with actual situation while it is complicated and the computation is time-consuming, and the planar model is simple and convenient while it may cause some considerable deviation, and the PC model could simulate the interactions between adjacent frame truss and the truss under fire effectively in the SSTS, whose result is in the propinquity of 3-D model and has an acceptable accuracy. The PC model without rigidly hinged bars (RHB) on the fire floor is recommended to analyze the fire response behaviors of staggered-steel truss system under lateral force.
Free
Simulation and Experiment of Projectile Penetrate into Steel Target Acceleration Signal Processing
Scientific article
For a comprehensive and objective understanding of the dynamic overload character of projectile penetrate into a steel target, using the simulating software ANSYS/LS-DYNA, adopting of the corresponding ammunition and target model, and the process of the ammunition penetrate the steel target was simulated and computed, the stress distribution map, mode and some results were got, using ball cartridge experiment, the original overload curves and high speed camera results were got. In this paper, the acceleration signals, which are obtained by the embedded high-overload electronic solid recorder at the experiment of armor-piercing bullet penetrating steel target, was done of wave filtering and integral analysis and so on in time domain, power spectrum was got through FFT in frequency-domain, as well as Wigner-Ville analysis and wavelet analysis in timefrequency. The characteristic signal when armor-piercing bullet penetrates steel target under certain conditions was obtained. Through signal processing and comprehensive analysis, a kind of signal processing method was provided to engineers, by which concerned parameters can be got.
Free
Scientific article
Carbon Nanotube Field Effect Transistors (CNTFETs) are being proposed as candidates for next-generation integrated circuit technology replacing conventional MOSFET devices. It is a suitable nanoelectronic device which is used for high speed and low power design applications which include analog and digital circuits. In this paper, a single wall carbon nanotube field effect transistor (SW-CNTFET) with a coaxial structure in the ballistic regime has been studied and its performance parameters discussed. Numerical simulations were performed based on Natori approach. The various device metrics in consideration are drive current (Ion), Ion/Ioff ratio, output conductance (gd), trans-conductance (gm), gain, carrier injection velocity, sub-threshold swing and drain induced barrier lowering (DIBL). In particular, the influences of gate oxide thickness on the short-channel effects are presented in detail. Also, the dependence of sub-threshold swing and DIBL on the gate control parameter has been discussed.
Free
Simultaneous Image Fusion and Denoising based on Multi-Scale Transform and Sparse Representation
Scientific article
Multi-scale transform (MST) and sparse representation (SR) techniques are used in an image representation model. Image fusion is used especially in medical, military and remote sensing areas for high resolution vision. In this paper an image fusion technique based on shearlet transformation and sparse representation is proposed to overcome the natural defects of both MST and SR based methods. The proposed method is also used in different transformations and SR for comparison purposes. This research also investigate denoising techniques with additive white Gaussian noise into source images and perform threshold for de-noised into the proposed method. The image quality assessments for the fused image are used for the performance of proposed method and compared with others.
Free
Sine Cosine Taylor Like Technique for Connected Component Detector by ICNN Simulation
Scientific article
Sine cosine Taylor like technique is employed to carry out connected component detector (CCD) simulation under improved cellular neural network (ICNN) architecture to yield better accuracy for hand written character and image recognition system. The principal simulation results reveal that this technique performs well in comparison with other techniques.
Free
Skin Color Segmentation in YCBCR Color Space with Adaptive Fuzzy Neural Network (Anfis)
Scientific article
In this paper, an efficient and accurate method for human color skin recognition in color images with different light intensity will proposed .first we transform inputted color image from RGB color space to YCBCR color space and then accurate and appropriate decision on that if it is in human color skin or not will be adopted according to YCBCR color space using fuzzy, adaptive fuzzy neural network(anfis) methods for each pixel of that image. In our proposed system adaptive fuzzy neural network(anfis) has less error and system worked more accurate and appropriative than prior methods.
Free
Scientific article
High utility item-sets mining(HUIM)is a special topic in frequent item-sets mining(FIM). It gives better insights for business growth by focusing on the utility of items in a transaction. HUIM is evolving as a powerful research area due to its vast applications in many fields. Data stream processing, meanwhile, is an interesting and challenging problem since, processing very fast generating a huge amount of data with limited resources strongly demands high-performance algorithms. This paper presents an innovative idea to extract the high utility item-sets (HUIs) from the dynamic data stream by applying sliding window control. Even though certain algorithms exist to solve the same problem, they allow redundant processing or reprocessing of data. To overcome this, the proposed algorithm used a trie like structure called Extended Global Utility Item-sets tree (EGUI-tree), which is flexible to store and retrieve the mined information instead of reprocessing. An experimental study on real-world datasets proved that EGUI-tree algorithm is faster than the state-of-the-art algorithms.
Free
Software Implementation of CCSDS Recommended Hyperspectral Lossless Image Compression
Scientific article
HyperSpectral Imagers (HySI) are used in the spacecraft or aircrafts to get minute characteristics of target element through capturing image in a large number of narrow and contiguous bands. HySI data represented as data cube with two dimensions representing spatial distribution and third dimension providing band information is huge in volume and challenging task to handle. Hence onboard compression becomes a necessary for optimal usage of onboard storage and downlink bandwidth. CCSDS recommended 123.0-B-1 standard[2] has been released with onboard compression scheme of hyperspectral data. The scheme is based on Fast Lossless algorithm and consists of two main functional blocks namely Predictor and Encoder. Predictor algorithm can be implemented in two modes 'Full Neighborhood Oriented' and 'Reduced Column Oriented'. Encoder algorithm also defines two options 'sample-adaptive' and 'block-adaptive'. We have developed a MATLAB based model implementing the compression scheme with all options defined by the standard. Decompression model is also developed for getting back actual data and end to end verification. Four sets of HySI data (AVIRIS, Hyperion, Chandrayan-1 and FTIS) have been applied as input to the developed model for evaluation of the model. Compression ratio achieved is between 2 to 3 and lossless compression is ensured for each set of data as Mean Square Error (MSE) is zero for all hyperspectral images. Also visual reconstruction of decompressed data matches with original ones. In this paper we have discussed algorithm implementation methodology and results.
Free
