Showing papers in "Multimedia Tools and Applications in 2014"

An image encryption algorithm based on hyper-chaos and DNA sequence

Abstract: A novel image encryption algorithm making using of hyper-chaos and DNA sequence is presented here. A four-dimensional hyper-chaos system is used to generate the pseudo-random sequence, which is transformed into a biologic DNA sequence to diffuse the image blocks. A circular permutation is performed on the plain-image when it is in DNA status. Together with classical structure of permutation plus diffusion, the simulation results show that the proposed image encryption algorithm has a satisfactory performance. Moreover, our method can resist the known-plaintext and chosen-plaintext attacks with four parameters r i (i?=?1,2,3,4) dependent on the plain-image. These parameters generate different key streams for different plain-image even if the initial conditions are the same.

A simple, sensitive and secure image encryption algorithm based on hyper-chaotic system with only one round diffusion process

Abstract: Based on hyper-chaotic systems, a novel image encryption algorithm is introduced in this paper. The advantages of our proposed approach are that it can be realized easily in one round diffusion process and is computationally very simple while attaining high security level, high key sensitivity, high plaintext sensitivity and other properties simultaneously. The key stream generated by hyper-chaotic system is related to the original image. Moreover, to encrypt each pixel, we use the sum of pixels which are located after that pixel. The algorithm uses different summations when encrypting different input images (even with the same sequence based on hyper-chaotic system). This, in turn, will considerably enhance the cryptosystem resistance against known/chosen-plaintext and differential attacks. The change rate of the number of pixels in the cipher-image when only one pixel of the original image is modified (NPCR) and the Unified Average Changing Intensity (UACI) are already very high (NPCR?>?99.80233 % and UACI?>?33.55484 %). Also, experimental results such as key space analysis, histograms, correlation coefficients, information entropy, peak signal-to-noise ratio, key sensitivity analysis, differential analysis and decryption quality, show that the proposed image encryption algorithm is secure and reliable, with high potential to be adopted for the secure image communication applications.

Ontology-based healthcare context information model to implement ubiquitous environment

Abstract: To establish real u-healthcare environments, it is necessary to receive the context information obtained from various platforms at the proper time in portable devices which operate using both wired and wireless communication Moreover, a knowledge model is required that reflects the information and characteristics needed for such services while remaining appropriate for medical reference This paper develops an ontology-based healthcare context information model to implement a ubiquitous environment Contextual information will be extracted and classified to implement the healthcare services using the context information model The healthcare context information model can be defined using the ontology, and a common healthcare model will be developed by considering medical references and service environments Application and healthcare service developers can use the sensed information in various environments by authoring device- and space-specific ontologies based on this common ontology In addition, this paper designs a personalized u-healthcare service system The validity of the model used in this study is evaluated for the food and exercise recommendation in u-healthcare services

A parallel image encryption method based on compressive sensing

Abstract: Recently, compressive sensing-based encryption methods which combine sampling, compression and encryption together have been proposed. However, since the quantized measurement data obtained from linear dimension reduction projection directly serve as the encrypted image, the existing compressive sensing-based encryption methods fail to resist against the chosen-plaintext attack. To enhance the security, a block cipher structure consisting of scrambling, mixing, S-box and chaotic lattice XOR is designed to further encrypt the quantized measurement data. In particular, the proposed method works efficiently in the parallel computing environment. Moreover, a communication unit exchanges data among the multiple processors without collision. This collision-free property is equivalent to optimal diffusion. The experimental results demonstrate that the proposed encryption method not only achieves the remarkable confusion, diffusion and sensitivity but also outperforms the existing parallel image encryption methods with respect to the compressibility and the encryption speed.

Comparison of group recommendation algorithms

Abstract: In recent years recommender systems have become the common tool to handle the information overload problem of educational and informative web sites, content delivery systems, and online shops. Although most recommender systems make suggestions for individual users, in many circumstances the selected items (e.g., movies) are not intended for personal usage but rather for consumption in groups. This paper investigates how effective group recommendations for movies can be generated by combining the group members' preferences (as expressed by ratings) or by combining the group members' recommendations. These two grouping strategies, which convert traditional recommendation algorithms into group recommendation algorithms, are combined with five commonly used recommendation algorithms to calculate group recommendations for different group compositions. The group recommendations are not only assessed in terms of accuracy, but also in terms of other qualitative aspects that are important for users such as diversity, coverage, and serendipity. In addition, the paper discusses the influence of the size and composition of the group on the quality of the recommendations. The results show that the grouping strategy which produces the most accurate results depends on the algorithm that is used for generating individual recommendations. Therefore, the paper proposes a combination of grouping strategies which outperforms each individual strategy in terms of accuracy. Besides, the results show that the accuracy of the group recommendations increases as the similarity between members of the group increases. Also the diversity, coverage, and serendipity of the group recommendations are to a large extent dependent on the used grouping strategy and recommendation algorithm. Consequently for (commercial) group recommender systems, the grouping strategy and algorithm have to be chosen carefully in order to optimize the desired quality metrics of the group recommendations. The conclusions of this paper can be used as guidelines for this selection process.

Using transcoding for hidden communication in IP telephony

Abstract: The paper presents a new steganographic method for IP telephony called TranSteg (Transcoding Steganography). Typically, in steganographic communication it is advised for covert data to be compressed in order to limit its size. In TranSteg it is the overt data that is compressed to make space for the steganogram. The main innovation of TranSteg is to, for a chosen voice stream, find a codec that will result in a similar voice quality but smaller voice payload size than the originally selected. Then, the voice stream is transcoded. At this step the original voice payload size is intentionally unaltered and the change of the codec is not indicated. Instead, after placing the transcoded voice payload, the remaining free space is filled with hidden data. TranSteg proof of concept implementation was designed and developed. The obtained experimental results are enclosed in this paper. They prove that the proposed method is feasible and offers a high steganographic bandwidth while introducing small voice degradation. Moreover, TranSteg detection is difficult to perform when compared with existing VoIP steganography methods.

Multimedia classification and event detection using double fusion

Abstract: Multimedia Event Detection(MED) is a multimedia retrieval task with the goal of finding videos of a particular event in video archives, given example videos and event descriptions; different from MED, multimedia classification is a task that classifies given videos into specified classes. Both tasks require mining features of example videos to learn the most discriminative features, with best performance resulting from a combination of multiple complementary features. How to combine different features is the focus of this paper. Generally, early fusion and late fusion are two popular combination strategies. The former one fuses features before performing classification and the latter one combines output of classifiers from different features. Early fusion can better capture the relationship among features yet is prone to over-fit the training data. Late fusion deals with the over-fitting problem better but does not allow classifiers to train on all the data at the same time. In this paper, we introduce a fusion scheme named double fusion, which simply combines early fusion and late fusion together to incorporate their advantages. Results are reported on the TRECVID MED 2010, MED 2011, UCF50 and HMDB51 datasets. For the MED 2010 dataset, we get a mean minimal normalized detection cost (MMNDC) of 0.49, which exceeds the state-of-the-art performance by more than 12 percent. On the TRECVID MED 2011 test dataset, we achieve a MMNDC of 0.51, which is the second best among all 19 participants. On UCF50 and HMDB51, we obtain classification accuracy of 88.1 % and 48.7 % respectively, which are the best reported results to date.

Content-based image retrieval by integrating color and texture features

Abstract: Content-based image retrieval (CBIR) has been an active research topic in the last decade. Feature extraction and representation is one of the most important issues in the CBIR. In this paper, we propose a content-based image retrieval method based on an efficient integration of color and texture features. As its color features, pseudo-Zernike chromaticity distribution moments in opponent chromaticity space are used. As its texture features, rotation-invariant and scale-invariant image descriptor in steerable pyramid domain are adopted, which offers an efficient and flexible approximation of early processing in the human visual system. The integration of color and texture information provides a robust feature set for color image retrieval. Experimental results show that the proposed method yields higher retrieval accuracy than some conventional methods even though its feature vector dimension is not higher than those of the latter for different test DBs.

An adaptive watermarking scheme for e-government document images

Abstract: This paper proposes an adaptive watermarking scheme for e-government document images. The adaptive scheme combines the discrete cosine transform (DCT) and the singular value decomposition (SVD) using luminance masking. As a core of masking model in the human visual system (HVS), luminance masking is implemented to improve noise sensitivity. Genetic algorithm (GA), subsequently, is employed for the optimization of the scaling factor of the masking. Involving a number of steps, the scheme proposed through this study begins by calculating the mask of the host image using luminance masking. It is then continued by transforming the mask on each area into all frequencies domain. The watermark image, following this, is embedded by modifying the singular values of DCT-transformed host image with singular values of mask coefficient of host image and the control parameter of DCT-transformed watermark image using Genetic Algorithm (GA). The use of both the singular values and the control parameter respectively, in this case, is not only to improve the sensitivity of the watermark performance but also to avoid the false positive problem. The watermark image, afterwards, is extracted from the distorted images. The experiment results show the improved adaptive performance of the proposed scheme is in resistant to several types of attacks in comparison with the previous schemes; the adaptive performance refers to the adaptive parameter of the luminance masking functioned to improve the performance or robustness of an image from any attacks.

An innovative web-based collaborative platform for video annotation

Abstract: Large scale labeled datasets are of key importance for the development of automatic video analysis tools as they, from one hand, allow multi-class classifiers training and, from the other hand, support the algorithms' evaluation phase. This is widely recognized by the multimedia and computer vision communities, as witnessed by the growing number of available datasets; however, the research still lacks in annotation tools able to meet user needs, since a lot of human concentration is necessary to generate high quality ground truth data. Nevertheless, it is not feasible to collect large video ground truths, covering as much scenarios and object categories as possible, by exploiting only the effort of isolated research groups. In this paper we present a collaborative web-based platform for video ground truth annotation. It features an easy and intuitive user interface that allows plain video annotation and instant sharing/integration of the generated ground truths, in order to not only alleviate a large part of the effort and time needed, but also to increase the quality of the generated annotations. The tool has been on-line in the last four months and, at the current date, we have collected about 70,000 annotations. A comparative performance evaluation has also shown that our system outperforms existing state of the art methods in terms of annotation time, annotation quality and system's usability.

Security analysis of an image encryption algorithm based on a DNA addition combining with chaotic maps

Abstract: In this paper, we propose to cryptanalyse an encryption algorithm which combines a DNA addition and a chaotic map to encrypt a gray scale image. Our contribution consists on, at first, demonstrating that the algorithm, as it is described, is non-invertible, which means that the receiver cannot decrypt the ciphered image even if he posses the secret key. Then, a chosen plaintext attack on the invertible encryption block is described, where, the attacker can illegally decrypt the ciphered image by a temporary access to the encryption machinery.

Item recommendation based on context-aware model for personalized u-healthcare service

Abstract: A personalized service in the ubiquitous environment is to provide services or items, which reflect personal tastes, attitudes, and contexts. It is impossible to reflect the context information generated in u-healthcare environments due to the existing recommendation system performing the recommendation using the information directly input by users and application usage record only. This study develops a context-aware model using the context information provided by the context information model. The study applies it to the extraction of the missing value in a collaborative filtering process. The context-aware model reflects the information that selects items by users according to the appropriate context using the C-HMM and provides it to users. The solution of the missing value in the preference significantly affects the recommendation accuracy in a preference based item supply method. Thus, this study developed a new collaborative filtering for ubiquitous environments by reflecting the missing preference value and reflecting it to the collaborative filtering using the context-aware model. Also, the validity of this method will be evaluated by applying it to menu services in u-healthcare services.

A comprehensive review of past and present vision-based techniques for gait recognition

Abstract: Global security concerns have raised a proliferation of video surveillance devices. Intelligent surveillance systems seek to discover possible threats automatically and raise alerts. Being able to identify the surveyed object can help determine its threat level. The current generation of devices provide digital video data to be analysed for time varying features to assist in the identification process. Commonly, people queue up to access a facility and approach a video camera in full frontal view. In this environment, a variety of biometrics are available--for example, gait which includes temporal features like stride period. Gait can be measured unobtrusively at a distance. The video data will also include face features, which are short-range biometrics. In this way, one can combine biometrics naturally using one set of data. In this paper we survey current techniques of gait recognition and modelling with the environment in which the research was conducted. We also discuss in detail the issues arising from deriving gait data, such as perspective and occlusion effects, together with the associated computer vision challenges of reliable tracking of human movement. Then, after highlighting these issues and challenges related to gait processing, we proceed to discuss the frameworks combining gait with other biometrics. We then provide motivations for a novel paradigm in biometrics-based human recognition, i.e. the use of the fronto-normal view of gait as a far-range biometrics combined with biometrics operating at a near distance.

MI-File: using inverted files for scalable approximate similarity search

Abstract: We propose a new efficient and accurate technique for generic approximate similarity searching, based on the use of inverted files. We represent each object of a dataset by the ordering of a number of reference objects according to their distance from the object itself. In order to compare two objects in the dataset, we compare the two corresponding orderings of the reference objects. We show that this representation enables us to use inverted files to obtain very efficiently a very small set of good candidates for the query result. The candidate set is then reordered using the original similarity function to obtain the approximate similarity search result. The proposed technique performs several orders of magnitude better than exact similarity searches, still guaranteeing high accuracy. To also demonstrate the scalability of the proposed approach, tests were executed with various dataset sizes, ranging from 200,000 to 100 million objects.

Adaptive unequal protection for wireless video transmission over IEEE 802.11e networks

Abstract: Packet loss of video streams cannot be avoided at wireless links for limited wireless bandwidth and frequently changed environments. To provide differentiated Quality of Service (QoS) guarantees between multimedia and data services, IEEE 802.11e was proposed. However, its performance and flexibility need to be further improved. In this paper, after a survey on various modifications of IEEE 802.11e, we formulate the problem of video transmission over IEEE 802.11e networks to help scheme design and performance analysis. Then accompanied with in-depth analysis, an adaptive unequal protection schema is proposed, which is composed of three mechanisms: (1) Insert each video packet into the access category (AC) with the minimum relative queuing delay; (2) Assign each packet dynamically to a proper AC based on several parameters to guarantee the transmission of high priority frames; (3) Apply fuzzy logic controllers to adjust parameters so as to reply quickly to the variation of video data rate, coding structure and network load. Finally, regarding MPEG-4 codec as the example, we perform extensive evaluations and validate the effectiveness and flexibility of proposed scheme. Simulations are divided into WLAN and multihop parts, involving different video sequences and various traffic modes of data streams. Beside performance comparison between proposed scheme and other ones, influence of parameter setting and combination with routing algorithms are also evaluated.

A new image encryption scheme based on cyclic elliptic curve and chaotic system

Abstract: Recently, several cryptosystems based on chaos have been proposed. Nevertheless, most of them hinder the system performance, security, and suffer from the small key space problem. This paper introduces an efficient symmetric encryption scheme for secure digital images based on a cyclic elliptic curve and chaotic system that can overcome these disadvantages. The cipher encrypts 256-bit of plainimage to 256-bit of cipherimage within eight 32-bit registers. The scheme generates pseudorandom bit sequences for round keys based on a piecewise nonlinear chaotic map. Then, the generated sequences are mixed with the key sequences derived from the cyclic elliptic curve points. Results of statistical and differential analysis demonstrate that the proposed algorithm has adequate security for the confidentiality of digital images. Furthermore, it has key sensitivity together with a large key space and the encryption is fast compared to other competitive algorithms.

Embedding neural networks for semantic association in content based image retrieval

Abstract: Content based image retrieval (CBIR) systems provide potential solution of retrieving semantically similar images from large image repositories against any query image. The research community are competing for more effective ways of content based image retrieval, so they can be used in serving time critical applications in scientific and industrial domains. In this paper a Neural Network based architecture for content based image retrieval is presented. To enhance the capabilities of proposed work, an efficient feature extraction method is presented which is based on the concept of in-depth texture analysis. For this wavelet packets and Eigen values of Gabor filters are used for image representation purposes. To ensure semantically correct image retrieval, a partial supervised learning scheme is introduced which is based on K-nearest neighbors of a query image, and ensures the retrieval of images in a robust way. To elaborate the effectiveness of the presented work, the proposed method is compared with several existing CBIR systems, and it is proved that the proposed method has performed better then all of the comparative systems.

W3-privacy: understanding what, when, and where inference channels in multi-camera surveillance video

Abstract: Huge amounts of video are being recorded every day by surveillance systems. Since video is capable of recording and preserving an enormous amount of information which can be used in many applications, it is worth examining the degree of privacy loss that might occur due to public access to the recorded video. A fundamental requirement of privacy solutions is an understanding and analysis of the inference channels than can lead to a breach of privacy. Though inference channels and privacy risks are well studied in traditional data sharing applications (e.g., hospitals sharing patient records for data analysis), privacy assessments of video data have been limited to the direct identifiers such as people's faces in the video. Other important inference channels such as location (Where), time (When), and activities (What) are generally overlooked. In this paper we propose a privacy loss model that highlights and incorporates identity leakage through multiple inference channels that exist in a video due to what, when, and where information. We model the identity leakage and the sensitive information separately and combine them to calculate the privacy loss. The proposed identity leakage model is able to consolidate the identity leakage through multiple events and multiple cameras. The experimental results are provided to demonstrate the proposed privacy analysis framework.

Robust gesture recognition using feature pre-processing and weighted dynamic time warping

Abstract: Gesture recognition is a technology often used in human-computer interaction applications. Dynamic time warping (DTW) is one of the techniques used in gesture recognition to find an optimal alignment between two sequences. Oftentimes a pre-processing of sequences is required to remove variations due to different camera or body orientations or due to different skeleton sizes between the reference gesture sequences and the test gesture sequences. We discuss a set of pre-processing methods to make the gesture recognition mechanism robust to these variations. DTW computes a dissimilarity measure by time-warping the sequences on a per sample basis by using the distance between the current reference and test sequences. However, all body joints involved in a gesture are not equally important in computing the distance between two sequence samples. We propose a weighted DTW method that weights joints by optimizing a discriminant ratio. Finally, we demonstrate the performance of our pre-processing and the weighted DTW method and compare our results with the conventional DTW and state-of-the-art.

Graph regularized discriminative non-negative matrix factorization for face recognition

Abstract: Non-negative matrix factorization (NMF) has been widely employed in computer vision and pattern recognition fields since the learned bases can be interpreted as a natural parts-based representation of the input space, which is consistent with the psychological intuition of combining parts to form a whole. In this paper, we propose a novel constrained nonnegative matrix factorization algorithm, called the graph regularized discriminative non-negative matrix factorization (GDNMF), to incorporate into the NMF model both intrinsic geometrical structure and discriminative information which have been essentially ignored in prior works. Specifically, both the graph Laplacian and supervised label information are jointly utilized to learn the projection matrix in the new model. Further we provide the corresponding multiplicative update solutions for the optimization framework, together with the convergence proof. A series of experiments are conducted over several benchmark face datasets to demonstrate the efficacy of our proposed GDNMF.

Detection and localization of selected acoustic events in acoustic field for smart surveillance applications

Abstract: A method for automatic determination of position of chosen sound events such as speech signals and impulse sounds in 3-dimensional space is presented. The events are localized in the presence of sound reflections employing acoustic vector sensors. Human voice and impulsive sounds are detected using adaptive detectors based on modified peak-valley difference (PVD) parameter and sound pressure level. Localization based on signals from the multichannel acoustic vector probe is performed upon the detection. The described algorithms can be employed in surveillance systems to monitor behavior of public events participants. The results can be used to detect sound source position in real time or to calculate the spatial distribution of sound energy in the environment. Moreover, the spatial filtration can be performed to separate sounds arriving from a chosen direction.

Context-aware recommendations through context and activity recognition in a mobile environment

Abstract: The mobile Internet introduces new opportunities to gain insight in the user's environment, behavior, and activity. This contextual information can be used as an additional information source to improve traditional recommendation algorithms. This paper describes a framework to detect the current context and activity of the user by analyzing data retrieved from different sensors available on mobile devices. The framework can easily be extended to detect custom activities and is built in a generic way to ensure easy integration with other applications. On top of this framework, a recommender system is built to provide users a personalized content offer, consisting of relevant information such as points-of-interest, train schedules, and touristic info, based on the user's current context. An evaluation of the recommender system and the underlying context recognition framework shows that power consumption and data traffic is still within an acceptable range. Users who tested the recommender system via the mobile application confirmed the usability and liked to use it. The recommendations are assessed as effective and help them to discover new places and interesting information.

Hybrid video emotional tagging using users' EEG and video content

Abstract: In this paper, we propose novel hybrid approaches to annotate videos in valence and arousal spaces by using users' electroencephalogram (EEG) signals and video content. Firstly, several audio and visual features are extracted from video clips and five frequency features are extracted from each channel of the EEG signals. Secondly, statistical analyses are conducted to explore the relationships among emotional tags, EEG and video features. Thirdly, three Bayesian Networks are constructed to annotate videos by combining the video and EEG features at independent feature-level fusion, decision-level fusion and dependent feature-level fusion. In order to evaluate the effectiveness of our approaches, we designed and conducted the psychophysiological experiment to collect data, including emotion-induced video clips, users' EEG responses while watching the selected video clips, and emotional video tags collected through participants' self-report after watching each clip. The experimental results show that the proposed fusion methods outperform the conventional emotional tagging methods that use either video or EEG features alone in both valence and arousal spaces. Moreover, we can narrow down the semantic gap between the low-level video features and the users' high-level emotional tags with the help of EEG features.

Linguistic steganalysis using the features derived from synonym frequency

Abstract: A linguistic steganalysis method is proposed to detect synonym substitution-based steganography, which embeds secret message into a text by substituting words with their synonyms First, attribute pair of a synonym is introduced to represent its position in an ordered synonym set sorting in descending frequency order and the number of its synonyms As a result of synonym substitutions, the number of high frequency attribute pairs may be reduced while the number of low frequency attribute pairs would be increased By theoretically analyzing the changes of the statistical characteristics of attribute pairs caused by SS steganography, a feature vector based on the difference of the relative frequencies of different attribute pairs is utilized to detect the secret message Finally, the impact on the extracted feature vector caused by synonym coding strategies is analyzed Experimental results demonstrate that the proposed linguistic steganalysis method can achieve better detection performance than previous methods

A Huffman compression based text steganography method

Abstract: In this study, capacity and security issues of text steganography have been considered by proposing a compression based approach. Because of using textual data in steganography, firstly, the employed data compression algorithm has to be lossless. Accordingly, Huffmann coding has been chosen due to its frequent use in the literature and significant compression ratio. Besides, the proposed method constructs and uses stego-keys in order to increase security. Secret information has been hidden in the chosen text from the previously constructed text base that consists of naturally generated texts. Email has been chosen as communication channel between the two parties, so the stego cover has been arranged as a forward mail platform. As the result of performed experiments, average capacity has been computed as 7.962 % for the secret message with 300 characters (or 300∙8 bits). Finally, comparison of the proposed method with the other contemporary methods in the literature has been carried out in Section 5.

An augmented reality-based authoring tool for E-learning applications

Abstract: In recent years, augmented reality technologies have been a subject of great interest among the scientific community. However, most studies have focused on hardware and software development without particular emphasis on the authoring phase. As a consequence, the authoring process of augmented reality applications is accomplished today through hard-coding of a specific application. This approach, however, requires operators. In the education applications, the hard-coding methods tend to be retained, despite remarkable technological developments in the industrial area. Textbooks are mainly used in educational systems and many educators are very passive about applying new materials. In this paper, we present an immersive authoring tool for education using augmented reality, where applications authorized by our tool interact with the user in order to increase the learner's interest and reflect various desires of dynamic environment. Our authoring tool consists of a composing tool that can be used to create educational contents, a viewer that plays the content, and an engine to power the tool and viewer.

Classification of defects in steel strip surface based on multiclass support vector machine

Abstract: In this paper, we use support vector machine to classify the defects in steel strip surface images. After image binarization, three types of image features, including geometric feature, grayscale feature and shape feature, are extracted by combining the defect target image and its corresponding binary image. For the classification model based on support vector machine, we utilize Gauss radial basis as the kernel function, determine model parameters by cross-validation and employ one-versus-one method for multiclass classifier. Experiment results show that support vector machine model outperforms the traditional classification model based on back-propagation neural network in average classification accuracy.

High payload image steganography with reduced distortion using octonary pixel pairing scheme

Abstract: The crucial challenge that decides the success of any steganographic algorithm lies in simultaneously achieving the three contradicting objectives namely--higher payload capacity, with commendable perceptual quality and high statistical un-detectability. This work is motivated by the interest in developing such a steganographic scheme, which is aimed for establishing secure image covert channel in spatial domain using Octonary PVD scheme. The goals of this paper are to be realized through: (1) pairing a pixel with all of its neighbors in all the eight directions, to offer larger embedding capacity (2) the decision of the number of bits to be embedded in each pixel based on the nature of its region and not done universally same for all the pixels, to enhance the perceptual quality of the images (3) the re-adjustment phase, which sustains any modified pixel in the same level in the stego-image also, where the difference between a pixel and its neighbor in the cover image belongs to, for imparting the statistical un-detectability factor. An extensive experimental evaluation to compare the performance of the proposed system vs. other existing systems was conducted, on a database containing 3338 natural images, against two specific and four universal steganalyzers. The observations reported that the proposed scheme is a state-of-the-art model, offering high embedding capacity while concurrently sustaining the picture quality and defeating the statistical detection through steganalyzers.

A survey on visual adult image recognition

Abstract: We provide an overview of state-of-the-art approaches to visual adult image recognition which is a special case of one-class image classification. We present a representative selection of methods which we coarsely divide into three main groups. First we discuss color-based approaches which rely on the intuitive assumption that adult images usually feature skin-colored regions. Different ways of defining skin colors are described and example classification frameworks built on skin color models are presented. Another main group of approaches to adult image recognition is based on shape information which usually also exploit color information to find skin-colored regions of interest. Color and texture features are often used to augment such shape features. Finally we introduce approaches based on local feature descriptors.

Ontology driven interactive healthcare with wearable sensors

Abstract: Ubiquitous healthcare is the service that offers health-related information and contents to users without any limitations of time and space. Especially, to offer customized services to users, the technology of acquiring context information of users in real time is the most important consideration. In this paper, we researched wearable sensors. We proposed the ontology driven interactive healthcare with wearable sensors (OdIH_WS) to achieve customized healthcare service. For this purpose, wearable-sensor-based smart-wear and methods of data acquisition and processing are being developed. The proposed system has potential value in healthcare. A smart wear using wearable sensors is fabricated as a way of non-tight and comfortable style fitting for the curves of the human body based on clothes to wear in daily life. The design sample of the smart wear uses basic stretch materials and is designed to sustain its wearable property. To offer related information, it establishes an environment-information-based healthcare ontology model needed for inference, and it is composed of inside-outside context information models depending on the users' context. The modeling of the proposed system involved combinations of information streams, focusing on service context information. With the proposed service inference rules, customized information and contents could be drawn by the inference engine. In the established OdIH_WS, real-time health information monitoring was achieved. The results of system performance and users' satisfaction evaluations confirmed that the proposed system is superior to other existing systems.