Privacy image classification (PIC) has attracted increasing attention as it can help people make appropriate privacy decisions when sharing images. Most recently, some pioneer research efforts have been made to utilize multimodal information for PIC, since multi-modality can provide richer information than single modality. Those research efforts on multimodal PIC are under the assumption of independently identically distribution. However, connections between different modalities commonly exist in real-world cases. Taking the modalities of scene and object as example, in the scene of ’library/indoor’, the object ’book jacket’ resides with high probabilities. To this end, in this paper, a novel PIC approach, called CoupledPIC, is proposed to bridge this gap by comprehensively capturing the coupling relations between different modalities. In CoupledPIC, two submodules are designed to capture explicit and implicit coupling relations between different modalities respectively. The explicit modality coupling is learned with a tensor fusion networks based submodule, via the direct interaction of features. For the implicit modality coupling, a graph convolutional networks based submodule is proposed to learn on both the initial graphs and attention guided graphs, via information aggregation on graphs. Extensive experiments on the public benchmark, PicAlert, demonstrate the effectiveness of the proposed CoupledPIC, yielding significant improvement by modeling inter-modality coupling information.

Privacy protection in Content Based Image Retrieval (CBIR) is a new research topic in cyber security and privacy. The state-of-art CBIR systems usually adopt interactive mechanism, namely relevance feedback, to enhance the retrieval precision. How to protect the user's privacy in such Relevance Feedback based CBIR (RF-CBIR) is a challenge problem. In this paper, we investigate this problem and propose a new Private Relevance Feedback CBIR (PRF-CBIR) scheme. PRF-CBIR can leverage the performance gain of relevance feedback and preserve the user's search intention at the same time. The new PRF-CBIR consists of three stages: 1) private query; 2) private feedback; 3) local retrieval. Private query performs the initial query with a privacy controllable feature vector; private feedback constructs the feedback image set by introducing confusing classes following theK-anonymity principle; local retrieval finally re-ranks the images in the user side. Privacy analysis shows that PRF-CBIR fulfills the privacy requirements. The experiments carried out on the real-world image collection confirm the effectiveness of the proposed PRF-CBIR scheme.

Summary Image source identification plays an important role in image forensics. Traditional image source identification techniques rely on the assumption that the training datasets are well labeled. However, in the real world, this assumption may not be the truth, and some noisy samples may exist in the training datasets. In this paper, firstly, we theoretically investigate the influence of noisy samples to the identification performance. Then, a new image source identification approach, namely, Anti‐noise Image Source Identification (AISI), is proposed to deal with those noisy samples. AISI has three steps, ie, noise level evaluation, noise level based sampling, and multi‐classification. Noise level evaluation aims to assign each sample with a noise level that indicates the probability of being noisy. The basic idea of noise level based sampling is to sample images according to their noise levels. We provide a theoretically justification to demonstrate the effectiveness of AISI. Experiments conducted on a real‐world image collection confirm that the proposed AISI can alleviate the influence of noisy samples and can improve the identification accuracy while noise exists.

Recently, there has been great interest in feature-based image source identification. Previous statistical learning-based methods usually regarded the identification process as a classification problem. They assumed the dependence of features and the dependence of models. However, the two assumptions are usually problematic because of the genuine coupling of features and models. To address the issues, in this paper, we propose a novel image source identification scheme. For the feature coupling, a coupled feature representation is adopted to analyze the coupled interaction among features. The coupling relations among features and their powers are measured with Pearson’s correlations and integrated in a Taylor-like expansion manner. Regarding model coupling, a new coupled probability representation is developed. The model coupling relationships are characterized with conditional probabilities induced by the confusion matrix and then combined with the law of total probability. The experiments carried out on the Dresden image collection confirm the effectiveness of the proposed scheme. Via mining the feature coupling and model coupling, the identification accuracy can be significantly improved.

Feature based camera model identification plays an important role for forensics investigations on images. The conventional feature based identification schemes suffer from the problem of unknown models, that is, some images are captured by the camera models previously unknown to the identification system. To address this problem, we propose a new scheme: Source Camera Identification with Unknown models (SCIU). It has the capability of identifying images of the unknown models as well as distinguishing images of the known models. The new SCIU scheme consists of three stages: 1) unknown detection; 2) unknown expansion; and 3) (K+1 )-class classification. Unknown detection applies a k -nearest neighbours method to recognize a few sample images of unknown models from the unlabeled images. Unknown expansion further extends the set of unknown sample images using a self-training strategy. Then, we address a specific (K+1)-class classification, in which the sample images of unknown (1-class) and known models (K-class) are combined to train a classifier. In addition, we develop a parameter optimization method for unknown detection, and investigate the stopping criterion for unknown expansion. The experiments carried out on the Dresden image collection confirm the effectiveness of the proposed SCIU scheme. When unknown models present, the identification accuracy of SCIU is significantly better than the four state-of-art methods: 1) multi-class Support Vector Machine (SVM); 2) binary SVM; 3) combined classification framework; and 4) decision boundary carving.

In the past few years, the Web has become a de facto deployment environment for new application systems. Web-based Geospatial image map systems make satellite remote sensing data available to a wider range of public users than ever before. The storage and organization of global massive multi-dimensional remote sensing data have a big impact on the performance of Web mapping systems. To implement a performance-optimized Web mapping system, we propose a global grid division pyramid hierarchical data model for massive remote sensing data management, and adopt Hilbert curve allocation method for data placements. Collaborative web map browsing is also very important for many applications such as crisis management, military activities and government decision-making. However, realizing collaboration functionality on the basis of the stateless HTTP protocol, optimized for client requests, is not trivial. The limitations of the Web's request/response architecture prevent server from pushing real-time dynamic Web data. To address this problem, we propose a web-based interactive collaborative browsing framework based on server push technique (Comet). Moreover, we develop a prototype system called ACTGIS. Finally, we evaluate the prototype system using real remote sensing datasets, which demonstrate the good performance data access in our system.

Visualization and collaboration of large scale data sets on Internet is still one of biggest challenges in scientific visualization. A distributed, real-time, collaborative system for large scale data like seismic model can be a valuable tool to support scientific research. In this paper, we present a new approach for Web-based synchronized collaborative visualization of large scale data using Web services and rich Web clients which supports collaborative visualization in Web browsers. We use WS-resources in WSRF (Web services resource framework) to maintain states collaborative server. On client side, we design an Ajax-based (asynchronous JavaScript and XML) application using standard Web technologies. A collaborative demonstration of 3D seismic model which is 2GB size is presented and experimental results are showed finally.

Scientific collaboration has become more and more important in current scientific research. A collaboration environment which simplifies integration and collaboration of heterogeneous scientific resources, for instance scientific computing software and scientific apparatuses, can accelerate progress of scientific research remarkably. We present a novel middleware to facilitate development of distributed and collaborative application for scientific research. A service-oriented collaboration bus is proposed to enable scientific resources to be plugged in and users to interact with these resources collaboratively and transparently. Collaboration bus engines in different organizations can interoperate with each other to support distributed collaboration. We also show our prototype implementation of this middleware and a demonstration of Collaborative Visualization System for Seismic Data in earth science.