Multimedia Research最新文献_第3页

Secret Image Sharing and Steganography Using Haar Wavelet Transform 基于Haar小波变换的秘密图像共享与隐写

Multimedia Research Pub Date : 2019-04-05 DOI: 10.46253/j.mr.v2i2.a4

{"title":"Secret Image Sharing and Steganography Using Haar Wavelet Transform","authors":"","doi":"10.46253/j.mr.v2i2.a4","DOIUrl":"https://doi.org/10.46253/j.mr.v2i2.a4","url":null,"abstract":"Image steganography enables secure communication whether even intimating the enemy regarding the occurrence of communication. Steganography and cryptography play a vast role in rendering effective security for the secret data. However, when the presence of the secret message is revealed then, the secret message is disclosed, which is the major drawback of the existing strategies. Thus, the paper proposes an effective image sharing and steganography method using the Haar wavelet. There are two phases in this research: encoding and decoding phase. In the first phase, the encoding phase, where the secret message is embedded in the input image using the proposed Haar wavelet-based steganography, while in the decoding phase, the secret message is uncovered. In the decoding phase, the Lagrange's interpolation is applied that decodes the secret message from the stego or embedded image. The great significance of the method is that the greater degree of security is rendered against the security attacks and is a robust strategy for combining the secret sharing of messages and steganography. The analysis of the proposed method with respect to the existing methods is enabled using the 500 stego images acquired from the UCID database. The comparative analysis of the proposed method based on the metrics, such as Peak Signal-To-Noise Ratio (PSNR) and Structural Similarity (SSIM) index reveals that the proposed method acquired a maximal PSNR and SSIM of 57.142 dB and 0.9991, respectively.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114892253","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}

引用次数: 11

Fractional Rider and Multi-Kernel-Based Spherical SVM for Low Resolution Face Recognition 基于分数骑手和多核球面支持向量机的低分辨率人脸识别

Multimedia Research Pub Date : 2019-04-05 DOI: 10.46253/j.mr.v2i2.a5

Renjith Thomas

{"title":"Fractional Rider and Multi-Kernel-Based Spherical SVM for Low Resolution Face Recognition","authors":"Renjith Thomas","doi":"10.46253/j.mr.v2i2.a5","DOIUrl":"https://doi.org/10.46253/j.mr.v2i2.a5","url":null,"abstract":": Face recognition is a unique feature for recognizing the individual in the biometric system and is advantageous since face recognition is a non-contact process. However, biometric recognition is ineffective due to the low-resolution images, wanting the need for the effective recognition system. Accordingly, this research concentrates on developing an effective face recognition strategy using low and high-resolution images. Initially, the input low-resolution images are pre-processed for enhancing the image contrast and subjected to the generation of the high-resolution image. Then, the feature extraction using the GWTM process presents the texture features that facilitate effective recognition using the spherical Support Vector Machine (SVM) that works using the multiple kernel function. In the GWTM process, proposed fractional-ROA is engaged in the optimal fusion of the features acquired from the wavelet, Linear Binary Patterns (LBP), and Gabor filter. The analysis of the recognition method is initiated based on the metrics, such as False Alarm Rate (FAR), False Rejection Ratio (FRR), and accuracy. The proposed fractional-ROA-based face recognition acquires the maximal accuracy, and minimal FRR and FAR of 0.98, 0.0123, and 0.0017, respectively.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114373466","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}

引用次数: 9

Fuzzy Weighted Least Square Filter for Pansharpening in Satellite Images 卫星图像泛锐化的模糊加权最小二乘滤波

Multimedia Research Pub Date : 2019-01-04 DOI: 10.46253/j.mr.v2i1.a3

Jegatheeswari

引用次数: 9

Multiobjective Cost Function Based Digital Vide Watermarking Technique 基于多目标代价函数的数字视频水印技术

Multimedia Research Pub Date : 2019-01-04 DOI: 10.46253/j.mr.v2i1.a4

A. U. Wagdarikar

{"title":"Multiobjective Cost Function Based Digital Vide Watermarking Technique","authors":"A. U. Wagdarikar","doi":"10.46253/j.mr.v2i1.a4","DOIUrl":"https://doi.org/10.46253/j.mr.v2i1.a4","url":null,"abstract":": Video watermarking is a key process for copyright protection of digital data. In the video sequence, there is a huge quantity of data and these data are more susceptible to attacks. Hence, this paper intends to develop a novel video watermarking technique with the aid of multi-objective cost function. Initially, the keyframes are extracted from the input video sequence and these extracted video frames are subjected to wavelet transform for achieving the wavelet coefficients. Then, a multi-objective cost function is proposed with the help of multiple criteria like edge, brightness, the intensity of pixel, coverage, energy and frequency coefficient. The bit plane technique is utilized here to develop multiple binary images for the secret message by means of partitioning the secret messages. Further, with the aid of the multi-objective cost function, the message bit is embedded in the frame (wavelet coefficient). The embedded image is transmitted from the sender to the receiver via a communication channel and on the receiver side, the retrieval process takes place. The original image is retrieved in the receiver side with the help of a multi-objective cost function. Finally, a comparative analysis is accomplished between the proposed wavelet+Cost (wavelet transform based on a multi-objective cost function) and the existing models like wavelet model, Linear Significant Bit model (LSB) and LSB + cost model in terms of peak-to-signal noise ratio (PSNR) and correlation coefficients.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124741033","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}

引用次数: 9

Face Recognition using Active Appearance and Type-2 Fuzzy Classifier 基于主动外观和二类模糊分类器的人脸识别

Multimedia Research Pub Date : 2019-01-04 DOI: 10.46253/j.mr.v2i1.a1

引用次数: 11

An Approach for Speech Enhancement Using Deep Convolutional Neural Network 基于深度卷积神经网络的语音增强方法

Multimedia Research Pub Date : 2019-01-04 DOI: 10.46253/j.mr.v2i1.a5

引用次数: 34

Hybrid Optimization based DBN for Face Recognition using Low-Resolution Images 基于混合优化的DBN低分辨率人脸识别

Multimedia Research Pub Date : 2018-10-10 DOI: 10.46253/j.mr.v1i1.a5

Renjith Thomas

{"title":"Hybrid Optimization based DBN for Face Recognition using Low-Resolution Images","authors":"Renjith Thomas","doi":"10.46253/j.mr.v1i1.a5","DOIUrl":"https://doi.org/10.46253/j.mr.v1i1.a5","url":null,"abstract":"The recognition of faces has gained immense interest in image processing. The conventional face recognition techniques provide improved performance using the frontal images with high resolution. However, the major problem in face recognition is the Low-Resolution face images. To address this challenge, this paper proposes the face recognition system by integrating the Gabor Filter + Wavelet + Texture (GWTM) operator and the Deep Belief Network (DBN) to increase the classification performance, while deploying the low-resolution images. Initially, the input image is subjected to the preprocessing, and the low-resolution image is generated. Then, these low-resolution images employed kernel regression model for generating an image with high-resolution. Then, both the low-resolution and the high-resolution images are applied to the GWTM operator for extracting significant features. The result of the GWTM is provided to the fractional Bat algorithm for producing the intermediary images. Finally, the intermediary images are given to the DBN classifier for optimal face detection. The proposed method is analyzed with the existing methods using three evaluation measures, like the false acceptance rate (FAR), accuracy, and false rejection rate (FRR). Thus, the proposed method outperformed other methods with higher accuracy of 0.98, minimum FAR and FRR of 0.05.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133247184","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}

引用次数: 80

Edge-based Image Steganography using Edge Least Significant Bit (ELSB) Technique 基于边缘最小有效位(ELSB)技术的图像隐写

Multimedia Research Pub Date : 2018-10-10 DOI: 10.46253/j.mr.v1i1.a2

{"title":"Edge-based Image Steganography using Edge Least Significant Bit (ELSB) Technique","authors":"","doi":"10.46253/j.mr.v1i1.a2","DOIUrl":"https://doi.org/10.46253/j.mr.v1i1.a2","url":null,"abstract":"Image steganography is defined as a process of conceal a secret message into a larger media file. Medial files are ideal for steganography system since it has larger size and such media files are termed as audio, video and image. The advantage of steganography over cryptography is that the intended secret message does not attract attention to itself as an object of scrutiny. In this paper, the edge based image steganography system is developed using threshold selection and edge least significant bit technique. The main purpose of this system is to enhance the security and imperceptibility of the system. The proposed methodology constitutes of threshold selection, embedding process and extraction process. Initially, the edges are determined from the cover image by the edge detector. Here, the canny edge detection algorithm is utilized for edge selection with the aid of threshold selection. Thus, the edge pixels are obtained for the embedding process. Then, the secret message is entrenched into the edge pixel of the original image using the Edge Least Significant Bit (ELSB) technique which acquires the embedded image. At the receiver side, the secret message is retrieved from the watermarked image using ELSB technique. The experimental results are evaluated and performance is analysed with the parameters are Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR). The outcome of the proposed system attains the higher PSNR of 78dB which ensures the security of the image steganography method.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127157512","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}

引用次数: 10

Artifacts Removal in EEG Signal Using a NARX Model Based CS Learning Algorithm 基于NARX模型的脑电信号伪影去除

Multimedia Research Pub Date : 2018-10-10 DOI: 10.46253/j.mr.v1i1.a1

{"title":"Artifacts Removal in EEG Signal Using a NARX Model Based CS Learning Algorithm","authors":"","doi":"10.46253/j.mr.v1i1.a1","DOIUrl":"https://doi.org/10.46253/j.mr.v1i1.a1","url":null,"abstract":"An Electroencephalogram (EEG) signal is essential clinical tool for monitoring the neurological disorders. The electrical activity of the EEG signal is obtained by placing several electrodes on the brain scalp. However, the recorded signals are easily affected by various artifacts which reduce its clinical convenience. In order to remove the artifacts signal such as EOG, EMG and ECG, we have proposed, a new nonlinear autoregressive with exogenous input (NARX) filter in this paper. Then, the efficient learning algorithm of cuckoo search (CS) algorithm is proposed for the elimination of various artifacts from the reordered EEG signal. Here, the performance of the proposed model is analysed using signal to noise ratio (SNR) and root mean square error (RMSE) value. Finally, results shows the effectiveness of the proposed model by extracting the artifcats signal from the recorded signals based on the maximum signal to noise ratio and minimum root mean square error value. From the results, we can conclude that the proposed model obtained the maximum SNR rate as 47.54db compared to various existing artifacts removal models such as independent component analysis (ICA), Fast independent component analysis (FICA), neural network model (NN).","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126581238","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}

引用次数: 35

Multiple Feature Sets and SVM Classifier for the Detection of Diabetic Retinopathy Using Retinal Images 基于多特征集和SVM分类器的糖尿病视网膜病变视网膜图像检测

Multimedia Research Pub Date : 2018-10-10 DOI: 10.46253/j.mr.v1i1.a3

Ninu preetha N.S

{"title":"Multiple Feature Sets and SVM Classifier for the Detection of Diabetic Retinopathy Using Retinal Images","authors":"Ninu preetha N.S","doi":"10.46253/j.mr.v1i1.a3","DOIUrl":"https://doi.org/10.46253/j.mr.v1i1.a3","url":null,"abstract":"Diabetes Mellitus is one of the growing vitally fatal diseases that can affect the patient's sight and its most severe effect is on blood vessels inside the eye called diabetic retinopathy. Due to its significance, a design of an efficient classifier for the detection of Diabetes disease is one of the challenging tasks. In this paper, we have proposed SVM classifier for diagnosing the diabetics from retinal images using two features like optic disc and blood vessel. Initially, the Gaussian filter is used for performing the pre-processing phase. Once the noise free image is generated, the segmentation processed is applied for detecting the both optic disc and blood vessel areas. Then, the relevant features are extracted from the optic disc and blood vessel such as mean, variance, perimeter, diameter, maximum intensity and minimum intensity. Then, the diabetic images are classified from the input images using the proposed SVM classifier. Finally, the experimentation results of the proposed classification technique is carried out using the Stare database, which shows that the SVM classifier can be successfully classifies the diabetic images with better classification accuracy of 96%.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126980501","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}

引用次数: 23