We propose an image hashing paradigm using visually significant feature points. The feature points should be largely invariant under perceptually insignificant distortions. To satisfy this, we propose an iterative feature detector to extract significant geometry preserving feature points. We apply probabilistic quantization on the derived features to introduce randomness, which, in turn, reduces vulnerability to adversarial attacks. The proposed hash algorithm withstands standard benchmark (e.g., Stirmark) attacks, including compression, geometric distortions of scaling and small-angle rotation, and common signal-processing operations. Content changing (malicious) manipulations of image data are also accurately detected. Detailed statistical analysis in the form of receiver operating characteristic (ROC) curves is presented and reveals the success of the proposed scheme in achieving perceptual robustness while avoiding misclassification. 相似文献
Image captured by low dynamic range (LDR) camera fails to capture entire exposure level of scene, and instead only covers certain range of exposures. In order to cover entire exposure level in single image, bracketed exposure LDR images are combined. The range of exposures in different images results in information loss in certain regions. These regions need to be addressed and based on this motive a novel methodology of layer based fusion is proposed to generate high dynamic range image. High and low-frequency layers are formed by dividing each image based on pixel intensity variations. The regions are identified based on information loss section created in differently exposed images. High-frequency layers are combined using region based fusion with Dense SIFT which is used as activity level testing measure. Low-frequency layers are combined using weighted sum. Finally combined high and low-frequency layers are merged together on pixel to pixel basis to synthesize fused image. Objective analysis is performed to compare the quality of proposed method with state-of-the-art. The measures indicate superiority of the proposed method.
Graph drawing and visualization represent structural information as diagrams of abstract graphs and networks. An important subset of graphs is directed acyclic graphs (DAGs). This paper presents a new E-Spring algorithm, extended from the popular spring embedder model, which eliminates node overlaps in clustered DAGs. In this framework, nodes are modeled as non-uniform charged particles with weights, and a final drawing is derived by adjusting the positions of the nodes according to a combination of spring forces and repulsive forces derived from electrostatic forces between the nodes. The drawing process needs to reach a stable state when the average distances of separation between nodes are near optimal. We introduce a stopping condition for such a stable state, which reduces equilibrium distances between nodes and therefore results in a significantly reduced area for DAG visualization. It imposes an upper bound on the repulsive forces between nodes based on graph geometry. The algorithm employs node interleaving to eliminate any residual node overlaps. These new techniques have been validated by visualizing eBay buyer–seller relationships and has resulted in overall area reductions in the range of 45–79%. 相似文献
Wireless Personal Communications - This paper proposes an combined method for manifold preservation and Subspace Eigenvectors(SE) based regression in high dimensional (HD) images. We studied... 相似文献
The Journal of Supercomputing - Currently, many smart speakers, even social robots, appear on the market to help people's lives become more convenient. Usually, people use smart speakers to... 相似文献
Medical practitioners are unduly stressed, leading to ill health, loss of work efficiency, sometimes affecting decision-making capability. The present study was conducted with the aim to quantify the psychosocial factors that affect the medical practitioners working in Indian hospitals. This study constructed and validated Re-Modified Work-Style Short Form Questionnaire, an eight-item instrument based on work style of 108 medical practitioners comprising Indian physicians and surgeons. The re-modified tool had acceptable validity and internal consistency, which the modified one did not. Explorative factor analysis identified and labelled three factors: ‘Working through pain’, ‘Deadlines/pressure’ and ‘Self-imposed workload’. The findings of the study reveal that the mean total work style score exceeded the standardised limits ≥16, which suggests that the work style of medical practitioners working in Indian hospitals are at risk which may precipitate psychosocial stress. Factor weights was derived through Analytic Hierarchy Process to prioritise the relative importance of three potential work-style factors. The study may help to increase the preventive strategies to proactively reduce the effect of risk factors for the precipitation of stress, successfully leading to its attenuation. 相似文献