Showing papers in "Multimedia Tools and Applications in 2018"

Deep residual learning for image steganalysis

Abstract: Image steganalysis is to discriminate innocent images and those suspected images with hidden messages. This task is very challenging for modern adaptive steganography, since modifications due to message hiding are extremely small. Recent studies show that Convolutional Neural Networks (CNN) have demonstrated superior performances than traditional steganalytic methods. Following this idea, we propose a novel CNN model for image steganalysis based on residual learning. The proposed Deep Residual learning based Network (DRN) shows two attractive properties than existing CNN based methods. First, the model usually contains a large number of network layers, which proves to be effective to capture the complex statistics of digital images. Second, the residual learning in DRN preserves the stego signal coming from secret messages, which is extremely beneficial for the discrimination of cover images and stego images. Comprehensive experiments on standard dataset show that the DRN model can detect the state of arts steganographic algorithms at a high accuracy. It also outperforms the classical rich model method and several recently proposed CNN based methods.

The skin cancer classification using deep convolutional neural network

Abstract: This paper addresses the demand for an intelligent and rapid classification system of skin cancer using contemporary highly-efficient deep convolutional neural network. In this paper, we mainly focus on the task of classifying the skin cancer using ECOC SVM, and deep convolutional neural network. RGB images of the skin cancers are collected from the Internet. Some collected images have noises such as other organs, and tools. These images are cropped to reduce the noise for better results. In this paper, an existing, and pre-trained AlexNet convolutional neural network model is used in extracting features. A ECOC SVM clasifier is utilized in classification the skin cancer. The results are obtained by executing a proposed algorithm with a total of 3753 images, which include four kinds of skin cancers images. The implementation result shows that maximum values of the average accuracy, sensitivity, and specificity are 95.1 (squamous cell carcinoma), 98.9 (actinic keratosis), 94.17 (squamous cell carcinoma), respectively. Minimum values of the average in these measures are 91.8 (basal cell carcinoma), 96.9 (Squamous cell carcinoma), and 90.74 (melanoma), respectively.

A proposed secure multiple watermarking technique based on DWT, DCT and SVD for application in medicine

Abstract: In this paper, an algorithm for multiple watermarking based on discrete wavelet transforms (DWT), discrete cosine transform (DCT) and singular value decomposition (SVD) has been proposed for healthcare applications. For identity authentication purpose, the proposed method uses three watermarks in the form of medical Lump image watermark, the doctor signature/identification code and diagnostic information of the patient as the text watermarks. In order to improve the robustness performance of the image watermark, Back Propagation Neural Network (BPNN) is applied to the extracted image watermark to reduce the noise effects on the watermarked image. The security of the image watermark is also enhanced by using Arnold transform before embedding into the cover. Further, the symptom and signature text watermarks are also encoded by lossless arithmetic compression technique and Hamming error correction code respectively. The compressed and encoded text watermark is then embedded into the cover image. Experimental results are obtained by varying the gain factor, different sizes of text watermarks and the different cover image modalities. The results are provided to illustrate that the proposed method is able to withstand a different of signal processing attacks and has been found to be giving excellent performance for robustness, imperceptibility, capacity and security simultaneously. The robustness performance of the method is also compared with other reported techniques. Finally, the visual quality of the watermarked image is evaluated by the subjective method also. This shows that the visual quality of the watermarked images is acceptable for diagnosis at different gain factors. Therefore the proposed method may find potential application in prevention of patient identity theft in healthcare applications.

Four-image encryption scheme based on quaternion Fresnel transform, chaos and computer generated hologram

Abstract: A novel four-image encryption scheme based on the quaternion Fresnel transforms (QFST), computer generated hologram and the two-dimensional (2D) Logistic-adjusted-Sine map (LASM) is presented. To treat the four images in a holistic manner, two types of the quaternion Fresnel transform (QFST) are defined and the corresponding calculation method for a quaternion matrix is derived. In the proposed method, the four original images, which are represented by quaternion algebra, are processed holistically in a vector manner by using QFST first. Then the input complex amplitude, which is constructed by the components of the QFST-transformed plaintext images, is encoded by Fresnel transform with two virtual independent random phase masks (RPM). In order to avoid sending entire RPMs to the receiver side for decryption, the RPMs are generated by utilizing 2D–LASM, which results that the amount of the key data is reduced dramatically. Subsequently, by using Burch’s method and the phase-shifting interferometry, the encrypted computer generated hologram is fabricated. To improve the security and weaken the correlation, the encrypted hologram is scrambled base on 2D–LASM. Experiments demonstrate the validity of the proposed image encryption technique.

Hybrid Recommendation System for Heart Disease Diagnosis based on Multiple Kernel Learning with Adaptive Neuro-Fuzzy Inference System

Abstract: Multiple Kernel Learning with Adaptive Neuro-Fuzzy Inference System (MKL with ANFIS) based deep learning method is proposed in this paper for heart disease diagnosis. The proposed MKL with ANFIS based deep learning method follows two-fold approach. MKL method is used to divide parameters between heart disease patients and normal individuals. The result obtained from the MKL method is given to the ANFIS classifier to classify the heart disease and healthy patients. Sensitivity, Specificity and Mean Square Error (MSE) are calculated to evaluate the proposed MKL with ANFIS method. The proposed MKL with ANFIS is also compared with various existing deep learning methods such as Least Square with Support Vector Machine (LS with SVM), General Discriminant Analysis and Least Square Support Vector Machine (GDA with LS-SVM), Principal Component Analysis with Adaptive Neuro-Fuzzy Inference System (PCA with ANFIS) and Latent Dirichlet Allocation with Adaptive Neuro-Fuzzy Inference System (LDA with ANFIS). The results from the proposed MKL with ANFIS method has produced high sensitivity (98%), high specificity (99%) and less Mean Square Error (0.01) for the for the KEGG Metabolic Reaction Network dataset.

A big data classification approach using LDA with an enhanced SVM method for ECG signals in cloud computing

Abstract: Electrocardiographic (ECG) signals often consist of unwanted noises and speckles. In order to remove the noises, various image processing filters are used in various studies. In this paper, FIR and IIR filters are initially used to remove the linear and nonlinear delay present in the input ECG signal. In addition, filters are used to remove unwanted frequency components from the input ECG signal. Linear Discriminant Analysis (LDA) is used to reduce the features present in the input ECG signal. Support Vector Machines (SVM) is widely used for pattern recognition. However, traditional SVM method does not applicable to compute different characteristics of the features of data sets. In this paper, we use SVM model with a weighted kernel function method to classify more features from the input ECG signal. SVM model with a weighted kernel function method is significantly identifies the Q wave, R wave and S wave in the input ECG signal to classify the heartbeat level such as Left Bundle Branch Block (LBBB), Right Bundle Branch Block (RBBB), Premature Ventricular Contraction (PVC) and Premature Atrial Contractions (PACs). The performance of the proposed Linear Discriminant Analysis (LDA) with enhanced kernel based Support Vector Machine (SVM) method is comparatively analyzed with other machine learning approaches such as Linear Discriminant Analysis (LDA) with multilayer perceptron (MLP), Linear Discriminant Analysis (LDA) with Support Vector Machine (SVM), and Principal Component Analysis (PCA) with Support Vector Machine (SVM). The calculated RMSE, MAPE, MAE, R2 and Q2 for the proposed Linear Discriminant Analysis (LDA) with enhanced kernel based Support Vector Machine (SVM) method is low when compared with other approaches such as LDA with MLP, and PCA with SVM and LDA with SVM. Finally, Sensitivity, Specificity and Mean Square Error (MSE) are calculated to prove the effectiveness of the proposed Linear Discriminant Analysis (LDA) with an enhanced kernel based Support Vector Machine (SVM) method.

Learning laparoscopic video shot classification for gynecological surgery

Abstract: Videos of endoscopic surgery are used for education of medical experts, analysis in medical research, and documentation for everyday clinical life. Hand-crafted image descriptors lack the capabilities of a semantic classification of surgical actions and video shots of anatomical structures. In this work, we investigate how well single-frame convolutional neural networks (CNN) for semantic shot classification in gynecologic surgery work. Together with medical experts, we manually annotate hours of raw endoscopic gynecologic surgery videos showing endometriosis treatment and myoma resection of over 100 patients. The cleaned ground truth dataset comprises 9 h of annotated video material (from 111 different recordings). We use the well-known CNN architectures AlexNet and GoogLeNet and train these architectures for both, surgical actions and anatomy, from scratch. Furthermore, we extract high-level features from AlexNet with weights from a pre-trained model from the Caffe model zoo and feed them to an SVM classifier. Our evaluation shows that we reach an average recall of .697 and .515 for classification of anatomical structures and surgical actions respectively using off-the-shelf CNN features. Using GoogLeNet, we achieve a mean recall of .782 and .617 for classification of anatomical structures and surgical actions respectively. With AlexNet the achieved recall is .615 for anatomical structures and .469 for surgical action classification respectively. The main conclusion of our work is that advances in general image classification methods transfer to the domain of endoscopic surgery videos in gynecology. This is relevant as this domain is different from natural images, e.g. it is distinguished by smoke, reflections, or a limited amount of colors.

Efficient transform-based texture image retrieval techniques under quantization effects

Abstract: With the great demand for storing and transmitting images as well as their managing, the retrieval of compressed images is a field of intensive research. While most of the works have been devoted to the case of losslessly encoded images (by extracting features from the unquantized transform coefficients), new studies have shown that lossy compression has a negative impact on the performance of conventional retrieval systems. In this work, we investigate three different quantization schemes and propose for each one an efficient retrieval approach. More precisely, the uniform quantizer, the moment preserving quantizer and the distribution preserving quantizer are considered. The inherent properties of each quantizer are then exploited to design an efficient retrieval strategy, and hence, to reduce the drop of retrieval performances resulting from the quantization effect. Experimental results, carried out on three standard texture databases and a color dataset, show the benefits which can be drawn from the proposed retrieval approaches.

Study of digital image processing techniques for leaf disease detection and classification

Abstract: In this paper, we address a comprehensive study on disease recognition and classification of plant leafs using image processing methods. The traditional manual visual quality inspection cannot be defined systematically as this method is unpredictable and inconsistent. Moreover, it involves a remarkable amount of expertise in the field of plant disease diagnostics (phytopathology) in addition to the disproportionate processing times. Hence, image processing has been applied for the recognition of plant diseases. The paper has been divided into two main categories viz. detection and classification of leafs. A comprehensive discussion on the diseases detection and classification performance is presented based on analysis of previously proposed state of art techniques particularly from 1997 to 2016. Finally, discussed and classify the challenges and some prospects for future improvements in this space.

Local neighborhood difference pattern: A new feature descriptor for natural and texture image retrieval

Abstract: A new image retrieval technique using local neighborhood difference pattern (LNDP) has been proposed for local features. The conventional local binary pattern (LBP) transforms every pixel of image into a binary pattern based on their relationship with neighboring pixels. The proposed feature descriptor differs from local binary pattern as it transforms the mutual relationship of all neighboring pixels in a binary pattern. Both LBP and LNDP are complementary to each other as they extract different information using local pixel intensity. In the proposed work, both LBP and LNDP features are combined to extract the most of the information that can be captured using local intensity differences. To prove the excellence of the proposed method, experiments have been conducted on four different databases of texture images and natural images. The performance has been observed using well-known evaluation measures, precision and recall and compared with some state-of-art local patterns. Comparison shows a significant improvement in the proposed method over existing methods.

Content-based processing and analysis of endoscopic images and videos: A survey

Abstract: In recent years, digital endoscopy has established as key technology for medical screenings and minimally invasive surgery. Since then, various research communities with manifold backgrounds have picked up on the idea of processing and automatically analyzing the inherently available video signal that is produced by the endoscopic camera. Proposed works mainly include image processing techniques, pattern recognition, machine learning methods and Computer Vision algorithms. While most contributions deal with real-time assistance at procedure time, the post-procedural processing of recorded videos is still in its infancy. Many post-processing problems are based on typical Multimedia methods like indexing, retrieval, summarization and video interaction, but have only been sparsely addressed so far for this domain. The goals of this survey are (1) to introduce this research field to a broader audience in the Multimedia community to stimulate further research, (2) to describe domain-specific characteristics of endoscopic videos that need to be addressed in a pre-processing step, and (3) to systematically bring together the very diverse research results for the first time to provide a broader overview of related research that is currently not perceived as belonging together.

Single slice based detection for Alzheimer's disease via wavelet entropy and multilayer perceptron trained by biogeography-based optimization

Abstract: Detection of Alzheimer's disease (AD) from magnetic resonance images can help neuroradiologists to make decision rapidly and avoid missing slight lesions in the brain. Currently, scholars have proposed several approaches to automatically detect AD. In this study, we aimed to develop a novel AD detection system with better performance than existing systems. 28 ADs and 98 HCs were selected from OASIS dataset. We used inter-class variance criterion to select single slice from the 3D volumetric data. Our classification system is based on three successful components: wavelet entropy, multilayer perceptron, and biogeography-base optimization. The statistical results of our method obtained an accuracy of 92.40 ± 0.83%, a sensitivity of 92.14 ± 4.39%, a specificity of 92.47 ± 1.23%. After comparison, we observed that our pathological brain detection system is superior to latest 6 other approaches.

A brief review on multi-task learning

Abstract: Multi-task learning (MTL), which optimizes multiple related learning tasks at the same time, has been widely used in various applications, including natural language processing, speech recognition, computer vision, multimedia data processing, biomedical imaging, socio-biological data analysis, multi-modality data analysis, etc. MTL sometimes is also referred to as joint learning, and is closely related to other machine learning subfields like multi-class learning, transfer learning, and learning with auxiliary tasks, to name a few. In this paper, we provide a brief review on this topic, discuss the motivation behind this machine learning method, compare various MTL algorithms, review MTL methods for incomplete data, and discuss its application in deep learning. We aim to provide the readers with a simple way to understand MTL without too many complicated equations, and to help the readers to apply MTL in their applications.

A recent survey on image watermarking techniques and its application in e-governance

Abstract: This survey presents a brief discussion of different aspects of digital image watermarking. Included in the present discussion are these general concepts: major characteristics of digital watermark, novel and recent applications of watermarking, different kinds of watermarking techniques and common watermark embedding and extraction process. In addition, recent state-of-art watermarking techniques, potential issues and available solutions are discussed in brief. Further, the performance summary of the various state-of-art watermarking techniques is presented in tabular format. This survey contribution will be useful for the researchers to implement efficient watermarking techniques for secure e-governance applications.

Single image shadow detection and removal based on feature fusion and multiple dictionary learning

Abstract: In recent years, the analysis of natural image has made great progress while the image of the intrinsic component analysis can solve many computer vision problems, such as the image shadow detection and removal. This paper presents the novel model, which integrates the feature fusion and the multiple dictionary learning. Traditional model can hardly handle the challenge of reserving the removal accuracy while keeping the low time consuming. Inspire by the compressive sensing theory, traditional single dictionary scenario is extended to the multiple condition. The human visual system is more sensitive to the high frequency part of the image, and the high frequency part expresses most of the semantic information of the image. At the same time, the high frequency characteristic of the high and low resolution image is adopted in the dictionary training, which can effectively recover the loss in the high resolution image with high frequency information. This paper presents the integration of compressive sensing model with feature extraction to construct the two-stage methodology. Therefore, the feature fusion algorithm is applied to the dictionary training procedure to finalize the robust model. Simulation results proves the effectiveness of the model, which outperforms compared with the other state-of-the-art algorithms.

Color image watermarking scheme based on quaternion Hadamard transform and Schur decomposition

Abstract: Based on quaternion Hadamard transform (QHT) and Schur decomposition, a novel color image watermarking scheme is presented. To consider the correlation between different color channels and the significant color information, a new color image processing tool termed as the quaternion Hadamard transform is proposed. Then an efficient method is designed to calculate the QHT of a color image which is represented by quaternion algebra, and the QHT is analyzed for color image watermarking subsequently. With QHT, the host color image is processed in a holistic manner. By use of Schur decomposition, the watermark is embedded into the host color image by modifying the Q matrix. To make the watermarking scheme resistant to geometric attacks, a geometric distortion detection method based upon quaternion Zernike moment is introduced. Thus, all the watermark embedding, the watermark extraction and the geometric distortion parameter estimation employ the color image holistically in the proposed watermarking scheme. By using the detection method, the watermark can be extracted from the geometric distorted color images. Experimental results show that the proposed color image watermarking is not only invisible but also robust against a wide variety of attacks, especially for color attacks and geometric distortions.

CNN-RNN: a large-scale hierarchical image classification framework

Abstract: Objects are often organized in a semantic hierarchy of categories, where fine-level categories are grouped into coarse-level categories according to their semantic relations. While previous works usually only classify objects into the leaf categories, we argue that generating hierarchical labels can actually describe how the leaf categories evolved from higher level coarse-grained categories, thus can provide a better understanding of the objects. In this paper, we propose to utilize the CNN-RNN framework to address the hierarchical image classification task. CNN allows us to obtain discriminative features for the input images, and RNN enables us to jointly optimize the classification of coarse and fine labels. This framework can not only generate hierarchical labels for images, but also improve the traditional leaf-level classification performance due to incorporating the hierarchical information. Moreover, this framework can be built on top of any CNN architecture which is primarily designed for leaf-level classification. Accordingly, we build a high performance network based on the CNN-RNN paradigm which outperforms the original CNN (wider-ResNet) and also the current state-of-the-art. In addition, we investigate how to utilize the CNN-RNN framework to improve the fine category classification when a fraction of the training data is only annotated with coarse labels. Experimental results demonstrate that CNN-RNN can use the coarse-labeled training data to improve the classification of fine categories, and in some cases it even surpasses the performance achieved by fully annotated training data. This reveals that, CNN-RNN can alleviate the challenge of specialized and expensive annotation of fine labels.

A multithreaded programming approach for multimedia big data: encryption system

Abstract: Multimedia is currently seen to dominate the internet network and the mobile network traffic; hence, it is seen as the largest Big data. Generally, the symmetric encryption algorithms are applied to the ‘big multimedia data’; however; these algorithms are thought as very slow. In our study, we developed and designed a resource-efficient encryption algorithm system which applies the multithreaded programming process for the encryption of the big multimedia data. This proposed system describes a multi-level encryption model which uses the Feistel Encryption Scheme, genetic algorithms and the Advanced Encryption Standard (AES). Our system has been assessed for actual medical-based big multimedia data and compared to the benchmarked encryption algorithms like the RC6, MARS, 3-DES, DES, and Blowfish with regards to the computational run time and its throughput for the encryption and decryption procedures. In addition, the multithreaded programming approach is adopted to implement the proposed encryption system in order to enhace the system effeciencey and porfermance. Furthermore, we also compared our system with its sequential version for showing its resource efficiency. Our results indicated that our system had the least run time and a higher throughput for the encryption and decryption processes in comparison to the already existing standard encryption algorithms. Also, our system could improve the computation run time by approximately 75% and its throughput was also increased by 4-times in comparison to its sequential version. For fulfilling the security objectives, our algorithm showed a better Avalanche Effect in comparison to the existing algorithms and therefore, could be included in any encryption/decryption process of a big plain multimedia data.

Seven-layer deep neural network based on sparse autoencoder for voxelwise detection of cerebral microbleed

Abstract: In order to detect the cerebral microbleed (CMB) voxels within brain, we used susceptibility weighted imaging to scan the subjects. Then, we used undersampling to solve the accuracy paradox caused from the imbalanced data between CMB voxels and non-CMB voxels. we developed a seven-layer deep neural network (DNN), which includes one input layer, four sparse autoencoder layers, one softmax layer, and one output layer. Our simulation showed this method achieved a sensitivity of 95.13%, a specificity of 93.33%, and an accuracy of 94.23%. The result is better than three state-of-the-art approaches.

End-to-end video background subtraction with 3d convolutional neural networks

Abstract: Background subtraction in videos is a highly challenging task by definition, as it lays on a pixel-wise classification level. Therefore, great attention to detail is essential. In this paper, we follow the success of Deep Learning in Computer Vision and present an end-to-end system for background subtraction in videos. Our model is able to track temporal changes in a video sequence by applying 3D convolutions to the most recent frames of the video. Thus, no background model is needed to be retained and updated. In addition, it can handle multiple scenes without further fine-tuning on each scene individually. We evaluate our system on the largest dataset for change detection, CDnet, with over 50 videos which span across 11 categories. Further evaluation is performed in the ESI dataset which features extreme and sudden illumination changes. Our model surpasses the state-of-the-art on both datasets according to the average ranking of the models over a wide range of metrics.

A chaotic color image encryption using integrated bit-level permutation

Abstract: In this paper, a color image encryption algorithm based on chaos has been proposed. We convert the color image into three bit-level images (R, G, B components) and combine them to one bit-level image. Then, only use bit-level permutation architecture based on chaotic system to encrypt the integrated image. When diffuse the position of the integrated binary image, the value of the gray pixel is changed as well, so this architecture can achieve similar security to permutation-diffusion architecture. Besides, this architecture makes the three color components affect each other, it can reduce the correlations between three components. Simulation results show that the algorithm can encrypt the color image effectively and resist various typical attacks.

Multi-objective whale optimization algorithm for content-based image retrieval

Abstract: In the recent years, there are massive digital images collections in many fields of our life, which led the technology to find methods to search and retrieve these images efficiently. The content-based is one of the popular methods used to retrieve images, which depends on the color, texture and shape descriptors to extract features from images. However, the performance of the content-based image retrieval methods depends on the size of features that are extracted from images and the classification accuracy. Therefore, this problem is considered as a multi-objective and there are several methods that used to manipulate it such as NSGA-II and NSMOPSO. However, these methods have drawbacks such as their time and space complexity are large since they used traditional non-dominated sorting methods. In this paper, a new non-dominated sorting based on multi-objective whale optimization algorithm is proposed for content-based image retrieval (NSMOWOA). The proposed method avoids the drawbacks in other non-dominated sorting multi-objective methods that have been used for content-based image retrieval through reducing the space and time complexity. The results of the NSMOWOA showed a good performance in content-based image retrieval problem in terms of recall and precision.

A novel region-based active contour model via local patch similarity measure for image segmentation

Abstract: It is always difficult to accurately segment images with intensity inhomogeneity because most of the representative local-based models only take into account rough local information and do not consider the spatial relationship between the central pixel and its neighborhood. In fact, the pixels on an image are closely correlated to their local neighborhood. Therefore, the spatial relationship of neighboring pixels is a crucial feature that can play a vital role in image segmentation. In this paper, we propose a novel region-based active contour model via local patch similarity measure for image segmentation. In the model, we make full use of the spatial constraints on local region-based models for controlling the amplitude of spatial neighborhood to the center pixel in the image domain. Specifically, we first construct a local patch similarity measure as the spatial constraint, which balances the noise suppression and the image details reservation. Second, we construct the novel model by integrating the patch similarity measure into a region-based active contour model. Finally, we add a regularization information term to the objective function to ensure the smoothness and stability of the curve evolution. Experimental results show that the model is better than other classical local region-based models.

One round cipher algorithm for multimedia IoT devices

Abstract: With the exponential growth in Internet-of-Things (IoT) devices, security and privacy issues have emerged as critical challenges that can potentially compromise their successful deployment in many data-sensitive applications. Hence, there is a pressing need to address these challenges, given that IoT systems suffer from different limitations, and IoT devices are constrained in terms of energy and computational power, which renders them extremely vulnerable to attacks. Traditional cryptographic algorithms use a static structure that requires several rounds of computations, which leads to significant overhead in terms of execution time and computational resources. Moreover, the problem is compounded when dealing with multimedia contents, since the associated algorithms have stringent QoS requirements. In this paper, we propose a lightweight cipher algorithm based on a dynamic structure with a single round that consists of simple operations, and that targets multimedia IoT. In this algorithm, a dynamic key is generated and then used to build two robust substitution tables, a dynamic permutation table, and two pseudo-random matrices. This dynamic cipher structure minimizes the number of rounds to a single one, while maintaining a high level of randomness and security. Moreover, the proposed cipher scheme is flexible as the dimensions of the input matrix can be selected to match the devices’ memory capacity. Extensive security tests demonstrated the robustness of the cipher against various kinds of attacks. The speed, simplicity and high-security level, in addition to low error propagation, make of this approach a good encryption candidate for multimedia IoT devices.

Fire smoke detection algorithm based on motion characteristic and convolutional neural networks

Abstract: It is a challenging task to recognize smoke from visual scenes due to large variations in the feature of color, texture, shapes, etc. The current detection algorithms are mainly based on single feature or fusion of multiple static features of smoke, which leads to low detection accuracy. To solve this problem, this paper proposes a smoke detection algorithm based on the motion characteristics of smoke and the convolutional neural networks (CNN). Firstly, a moving object detection algorithm based on background dynamic update and dark channel priori is proposed to detect the suspected smoke regions. Then, the features of suspected region is extracted automatically by CNN, on that the smoke identification is performed. Compared to previous work, our algorithm improves the detection accuracy, which can reach 99% in the testing sets. For the problem that the region of smoke is relatively small in the early stage of smoke generation, the strategy of implicit enlarging the suspected regions is proposed, which improves the timeliness of smoke detection. In addition a fine-tuning method is proposed to solve the problem of scarce of data in the training network. Also, the algorithm has good smoke detection performance by testing under various video scenes.

An overview of steganography techniques applied to the protection of biometric data

Abstract: Identification of persons by way of biometric features is an emerging phenomenon. Over the years, biometric recognition has received much attention due to its need for security. Amongst the many existing biometrics, fingerprints are considered to be one of the most practical ones. Techniques such as watermarking and steganography have been used in attempt to improve security of biometric data. Watermarking is the process of embedding information into a carrier file for the protection of ownership/copyright of music, video or image files, whilst steganography is the art of hiding information. This paper presents an overview of steganography techniques applied in the protection of biometric data in fingerprints. It is novel in that we also discuss the strengths and weaknesses of targeted and blind steganalysis strategies for breaking steganography techniques.

A plaintext-related image encryption algorithm based on chaos

Abstract: A symmetric key image cryptosystem based on the piecewise linear map is presented in this paper. In this cryptosystem, the encryption process and the decryption process are exactly same. They both include the same operations of plaintext-related scrambling once, diffusion twice and matrix rotating of 180 degrees four times. The length of secret key in the system is 64d where d is a positive integer. The proposed system can fight against the chosen/known plaintext attacks due to the using of plaintext-related scrambling. The simulate results and comparison analysis show that the proposed system has many merits such as high encryption/decryption speed, large key space, strong key sensitivity, strong plaintext sensitivity, strong cipher-text sensitivity, good statistical properties of cipher images, and large cipher-text information entropy. So the proposed system can be applied to actual communications.

Smart pathological brain detection by synthetic minority oversampling technique, extreme learning machine, and Jaya algorithm

Abstract: Pathological brain detection is an automated computer-aided diagnosis for brain images. This study provides a novel method to achieve this goal.We first used synthetic minority oversampling to balance the dataset. Then, our system was based on three components: wavelet packet Tsallis entropy, extreme learning machine, and Jaya algorithm. The 10 repetitions of K-fold cross validation showed our method achieved perfect classification on two small datasets, and achieved a sensitivity of 99.64 ± 0.52%, a specificity of 99.14 ± 1.93%, and an accuracy of 99.57 ± 0.57% over a 255-image dataset. Our method performs better than six state-of-the-art approaches. Besides, Jaya algorithm performs better than genetic algorithm, particle swarm optimization, and bat algorithm as ELM training method.

Visual analysis of geospatial habitat suitability model based on inverse distance weighting with paired comparison analysis

Abstract: Geospatial data analytical model is developed in this paper to model the spatial suitability of malaria outbreak in Vellore, Tamil Nadu, India In general, Disease control strategies are only the spatial information like landscape, weather and climate, but also spatially explicit information like socioeconomic variable, population density, behavior and natural habits of the people The spatial multi-criteria decision analysis approach combines the multi-criteria decision analysis and geographic information system (GIS) to model the spatially explicit and implicit information and to make a practical decision under different scenarios and different environment Malaria is one of the emerging diseases worldwide; the cause of malaria is weather & climate condition of the study area The climate condition is often called as spatially implicit information, traditional decision-making models do not use the spatially implicit information it most often uses spatially explicit information such as socio-economic, natural habits of the people There is need to develop an integrated approach that consists of spatially implicit and explicit information The proposed approach is used to identity an effective control strategy that prevents and control of malaria Inverse Distance Weighting (IDW) is a type of deterministic method used in this paper to assign the weight values based on the neighborhood locations ArcGIS software is used to develop the geospatial habitat suitability model

Dynamic graph learning for spectral feature selection

Abstract: Previous spectral feature selection methods generate the similarity graph via ignoring the negative effect of noise and redundancy of the original feature space, and ignoring the association between graph matrix learning and feature selection, so that easily producing suboptimal results. To address these issues, this paper joints graph learning and feature selection in a framework to obtain optimal selected performance. More specifically, we use the least square loss function and an l 2,1-norm regularization to remove the effect of noisy and redundancy features, and use the resulting local correlations among the features to dynamically learn a graph matrix from a low-dimensional space of original data. Experimental results on real data sets show that our method outperforms the state-of-the-art feature selection methods for classification tasks.