Int. J. Image Graph.最新文献

{"title":"Image Matting: A Comprehensive Survey on Techniques, Comparative Analysis, Applications and Future Scope","authors":"D. C. Lepcha, Bhawna Goyal, Ayush Dogra","doi":"10.1142/s0219467823500110","DOIUrl":"https://doi.org/10.1142/s0219467823500110","url":null,"abstract":"In the era of rapid growth of technologies, image matting plays a key role in image and video editing along with image composition. In many significant real-world applications such as film production, it has been widely used for visual effects, virtual zoom, image translation, image editing and video editing. With recent advancements in digital cameras, both professionals and consumers have become increasingly involved in matting techniques to facilitate image editing activities. Image matting plays an important role to estimate alpha matte in the unknown region to distinguish foreground from the background region of an image using an input image and the corresponding trimap of an image which represents a foreground and unknown region. Numerous image matting techniques have been proposed recently to extract high-quality matte from image and video sequences. This paper illustrates a systematic overview of the current image and video matting techniques mostly emphasis on the current and advanced algorithms proposed recently. In general, image matting techniques have been categorized according to their underlying approaches, namely, sampling-based, propagation-based, combination of sampling and propagation-based and deep learning-based algorithms. The traditional image matting algorithms depend primarily on color information to predict alpha matte such as sampling-based, propagation-based or combination of sampling and propagation-based algorithms. However, these techniques mostly use low-level features and suffer from high-level background which tends to produce unwanted artifacts when color is same or semi-transparent in the foreground object. Image matting techniques based on deep learning have recently introduced to address the shortcomings of traditional algorithms. Rather than simply depending on the color information, it uses deep learning mechanism to estimate the alpha matte using an input image and the trimap of an image. A comprehensive survey on recent image matting algorithms and in-depth comparative analysis of these algorithms has been thoroughly discussed in this paper.","PeriodicalId":177479,"journal":{"name":"Int. J. Image Graph.","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129284146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Retinal Blood Vessel Extraction Using a New Enhancement Technique of Modified Convolution Filters and Sauvola Thresholding","authors":"Hadrians Kesuma Putra, B. Suprihatin","doi":"10.1142/s0219467823500067","DOIUrl":"https://doi.org/10.1142/s0219467823500067","url":null,"abstract":"The retinal blood vessels in humans are major components with different shapes and sizes. The extraction of the blood vessels from the retina is an important step to identify the type or nature of the pattern of the diseases in the retina. Furthermore, the retinal blood vessel was also used for diagnosis, detection, and classification. The most recent solution in this topic is to enable retinal image improvement or enhancement by a convolution filter and Sauvola threshold. In image enhancement, gamma correction is applied before filtering the retinal fundus. After that, the image should be transformed to a gray channel to enhance pictorial clarity using contrast-limited histogram equalization. For filter, this paper combines two convolution filters, namely sharpen and smooth filters. The Sauvola threshold, the morphology, and the medium filter are applied to extract blood vessels from the retinal image. This paper uses DRIVE and STARE datasets. The accuracies of the proposed method are 95.37% for DRIVE with a runtime of 1.77[Formula: see text]s and 95.17% for STARE with 2.05[Formula: see text]s runtime. Based on the result, it concludes that the proposed method is good enough to achieve average calculation parameters of a low time quality, quick, and significant.","PeriodicalId":177479,"journal":{"name":"Int. J. Image Graph.","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128799382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fusion-Based Semantic Segmentation Using Deep Learning Architecture in Case of Very Small Training Dataset","authors":"G. R. Padalkar, M. Khambete","doi":"10.1142/s0219467822500437","DOIUrl":"https://doi.org/10.1142/s0219467822500437","url":null,"abstract":"Semantic segmentation is a pre-processing step in computer vision-based applications. It is the task of assigning a predefined class label to every pixel of an image. Several supervised and unsupervised algorithms are available to classify pixels of an image into predefined object classes. The algorithms, such as random forest and SVM are used to obtain the semantic segmentation. Recently, convolutional neural network (CNN)-based architectures have become popular for the tasks of object detection, object recognition, and segmentation. These deep architectures perform semantic segmentation with far better accuracy than the algorithms that were used earlier. CNN-based deep learning architectures require a large dataset for training. In real life, some of the applications may not have sufficient good quality samples for training of deep learning architectures e.g. medical applications. Such a requirement initiated a need to have a technique of effective training of deep learning architecture in case of a very small dataset. Class imbalance is another challenge in the process of training deep learning architecture. Due to class imbalance, the classifier overclassifies classes with large samples. In this paper, the challenge of training a deep learning architecture with a small dataset and class imbalance is addressed by novel fusion-based semantic segmentation technique which improves segmentation of minor and major classes.","PeriodicalId":177479,"journal":{"name":"Int. J. Image Graph.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122701292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning with Data Science-Enabled Lung Cancer Diagnosis and Classification Using Computed Tomography Images","authors":"S. Kiran, Inderjeet Kaur, K. Thangaraj, V. Saveetha, R. Grace, N. Arulkumar","doi":"10.1142/s0219467822400022","DOIUrl":"https://doi.org/10.1142/s0219467822400022","url":null,"abstract":"In recent times, the healthcare industry has been generating a significant amount of data in distinct formats, such as electronic health records (EHR), clinical trials, genetic data, payments, scientific articles, wearables, and care management databases. Data science is useful for analysis (pattern recognition, hypothesis testing, risk valuation) and prediction. The major, primary usage of data science in the healthcare domain is in medical imaging. At the same time, lung cancer diagnosis has become a hot research topic, as automated disease detection poses numerous benefits. Although numerous approaches have existed in the literature for lung cancer diagnosis, the design of a novel model to automatically identify lung cancer is a challenging task. In this view, this paper designs an automated machine learning (ML) with data science-enabled lung cancer diagnosis and classification (MLDS-LCDC) using computed tomography (CT) images. The presented model initially employs Gaussian filtering (GF)-based pre-processing technique on the CT images collected from the lung cancer database. Besides, they are fed into the normalized cuts (Ncuts) technique where the nodule in the pre-processed image can be determined. Moreover, the oriented FAST and rotated BRIEF (ORB) technique is applied as a feature extractor. At last, sunflower optimization-based wavelet neural network (SFO-WNN) model is employed for the classification of lung cancer. In order to examine the diagnostic outcome of the MLDS-LCDC model, a set of experiments were carried out and the results are investigated in terms of different aspects. The resultant values demonstrated the effectiveness of the MLDS-LCDC model over the other state-of-the-art methods with the maximum sensitivity of 97.01%, specificity of 98.64%, and accuracy of 98.11%.","PeriodicalId":177479,"journal":{"name":"Int. J. Image Graph.","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122498734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Learning-Based Classification of Malignant and Benign Cells in Dermatoscopic Images via Transfer Learning Approach","authors":"V. Kumar, V. Mishra, Monika Arora","doi":"10.1142/s0219467822500413","DOIUrl":"https://doi.org/10.1142/s0219467822500413","url":null,"abstract":"The inhibition of healthy cells creating improper controlling process of the human body system indicates the occurrence of growth of cancerous cells. The cluster of such cells leads to the development of tumor. The observation of this type of abnormal skin pigmentation is done using an effective tool called Dermoscopy. However, these dermatoscopic images possess a great challenge for diagnosis. Considering the characteristics of dermatoscopic images, transfer learning is an appropriate approach of automatically classifying the images based on the respective categories. An automatic identification of skin cancer not only saves human life but also helps in detecting its growth at an earlier stage which saves medical practitioner’s effort and time. A newly predicted model has been proposed for classifying the skin cancer as benign or malignant by DCNN with transfer learning and its pre-trained models such as VGG 16, VGG 19, ResNet 50, ResNet 101, and Inception V3. The proposed methodology aims at examining the efficiency of pre-trained models and transfer learning approach for the classification tasks and opens new dimensions of research in the field of medicines using imaging technique which can be implementable in real-time applications.","PeriodicalId":177479,"journal":{"name":"Int. J. Image Graph.","volume":"275 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134280055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Thermal Blended Facial Expression Analysis and Recognition System Using Deformed Thermal Facial Areas","authors":"P. Saha, D. Bhattacharjee, B. K. De, M. Nasipuri","doi":"10.1142/s0219467822500498","DOIUrl":"https://doi.org/10.1142/s0219467822500498","url":null,"abstract":"There are many research works in visible as well as thermal facial expression analysis and recognition. Several facial expression databases have been designed in both modalities. However, little attention has been given for analyzing blended facial expressions in the thermal infrared spectrum. In this paper, we have introduced a Visual-Thermal Blended Facial Expression Database (VTBE) that contains visual and thermal face images with both basic and blended facial expressions. The database contains 12 posed blended facial expressions and spontaneous six basic facial expressions in both modalities. In this paper, we have proposed Deformed Thermal Facial Area (DTFA) in thermal expressive face image and make an analysis to differentiate between basic and blended expressions using DTFA. Here, the fusion of DTFA and Deformed Visual Facial Area (DVFA) has been proposed combining the features of both modalities and experiments and has been conducted on this new database. However, to show the effectiveness of our proposed approach, we have compared our method with state-of-the-art methods using USTC-NVIE database. Experiment results reveal that our approach is superior to state-of-the-art methods.","PeriodicalId":177479,"journal":{"name":"Int. J. Image Graph.","volume":"28 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113967944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Image Copy-Move Forgery Detection Using Combination of Scale-Invariant Feature Transform and Local Binary Pattern Features","authors":"Marziye Shahrokhi, Alireza Akoushideh, A. Shahbahrami","doi":"10.1142/s0219467822500486","DOIUrl":"https://doi.org/10.1142/s0219467822500486","url":null,"abstract":"Today, manipulating, storing, and sending digital images are simple and easy because of the development of digital imaging devices from hardware and software points of view. Digital images are used in different contexts of people’s lives such as news, forensics, and so on. Therefore, the reliability of received images is a question that often occupies the viewer’s mind and the authenticity of digital images is increasingly important. Detecting a forged image as a genuine one as well as detecting a genuine image as a forged one can sometimes have irreparable consequences. For example, an image that is available from the scene of a crime can lead to a wrong decision if it is detected incorrectly. In this paper, we propose a combination method to improve the accuracy of copy–move forgery detection (CMFD) reducing the false positive rate (FPR) based on texture attributes. The proposed method uses a combination of the scale-invariant feature transform (SIFT) and local binary pattern (LBP). Consideration of texture features around the keypoints detected by the SIFT algorithm can be effective to reduce the incorrect matches and improve the accuracy of CMFD. In addition, to find more and better keypoints some pre-processing methods have been proposed. This study was evaluated on the COVERAGE, GRIP, and MICC-F220 databases. Experimental results show that the proposed method without clustering or segmentation and only with simple matching operations, has been able to earn the true positive rates of 98.75%, 95.45%, and 87% on the GRIP, MICC-F220, and COVERAGE datasets, respectively. Also, the proposed method, with FPRs from 17.75% to 3.75% on the GRIP dataset, has been able to achieve the best results.","PeriodicalId":177479,"journal":{"name":"Int. J. Image Graph.","volume":"93 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126051051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning Techniques for Identifying Fetal Risk During Pregnancy","authors":"S. Ravikumar, E. Kannan","doi":"10.1142/s0219467822500450","DOIUrl":"https://doi.org/10.1142/s0219467822500450","url":null,"abstract":"Cardiotocography (CTG) is a biophysical method for assessing fetal condition that primarily relies on the recording and automated analysis of fetal heart activity. The quantitative description of the CTG signals is provided by computerized fetal monitoring systems. Even though effective conclusion generation methods for decision process support are still required to find out the fetal risk such as premature embryo, this proposed method and outcome data can confirm the assessment of the fetal state after birth. Low birth weight is quite possibly the main attribute that significantly depicts an unusual fetal result. These expectations are assessed in a constant experimental decision support system, providing valuable information that can be used to obtain additional information about the fetal state using machine learning techniques. The advancements in modern obstetric practice enabled the use of numerous reliable and robust machine learning approaches in classifying fetal heart rate signals. The Naïve Bayes (NB) classifier, support vector machine (SVM), decision trees (DT), and random forest (RF) are used in the proposed method. To assess these outcomes in the proposed method, some of the metrics such as precision, accuracy, F1 score, recall, sensitivity, logarithmic loss and mean absolute error have been taken. The above mentioned metrics will be helpful to predict the fetal risk.","PeriodicalId":177479,"journal":{"name":"Int. J. Image Graph.","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131967935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Firefly Algorithm Optimized Functional Link Artificial Neural Network for ISA-Radar Image Recognition","authors":"Asma Elyounsi, H. Tlijani, M. Bouhlel","doi":"10.1142/s0219467822500449","DOIUrl":"https://doi.org/10.1142/s0219467822500449","url":null,"abstract":"Traditional neural networks are very diverse and have been used during the last decades in the fields of data classification. These networks like MLP, back propagation neural networks (BPNN) and feed forward network have shown inability to scale with problem size and with the slow convergence rate. So in order to overcome these numbers of drawbacks, the use of higher order neural networks (HONNs) becomes the solution by adding input units along with a stronger functioning of other neural units in the network and transforms easily these input units to hidden layers. In this paper, a new metaheuristic method, Firefly (FFA), is applied to calculate the optimal weights of the Functional Link Artificial Neural Network (FLANN) by using the flashing behavior of fireflies in order to classify ISA-Radar target. The average classification result of FLANN-FFA which reached 96% shows the efficiency of the process compared to other tested methods.","PeriodicalId":177479,"journal":{"name":"Int. J. Image Graph.","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123791570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative Analysis of Different Data Replication Strategies in Cloud Environment","authors":"K. Sasikumar, B. Vijayakumar","doi":"10.1142/s0219467822500425","DOIUrl":"https://doi.org/10.1142/s0219467822500425","url":null,"abstract":"In this paper, we performed a comparative study of the different data replication strategies such as Adaptive Data Replication Strategy (ADRS), Dynamic Cost Aware Re-Replication and Rebalancing Strategy (DCR2S) and Efficient Placement Algorithm (EPA) in the cloud environment. The implementation of these three techniques is done in JAVA and the performance analysis is conducted to study the performance of those replication techniques by various parameters. The parameters used for the performance analysis of these three techniques are Load Variance, Response Time, Probability of File Availability, System Byte Effective Rate (SBER), Latency, and Fault Ratio. From the analysis, it is evaluated that by varying the number of file replicas, it shows deviations in the outcomes of these parameters. The comparative results were also analyzed.","PeriodicalId":177479,"journal":{"name":"Int. J. Image Graph.","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129564529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}