Current Issue : January - March Volume : 2019 Issue Number : 1 Articles : 6 Articles
Secret image sharing (SIS) with small-sized shadow images has many benefits, such as\nsaving storage space, improving transmission time, and achieving information hiding. When adjacent\npixel values in an image are similar to each other, the secret image will be leaked when all random\nfactors of an SIS scheme are utilized for achieving small sizes of shadow images. Most of the studies\nin this area suffer from an inevitable problem: auxiliary encryption is crucial in ensuring the security\nof those schemes. In this paper, an SIS scheme with small-sized shadow images based on the Chinese\nremainder theorem (CRT) is proposed. The size of shadow images can be reduced to nearly 1/k of\nthe original secret image. By adding random bits to binary representations of the random factors in\nthe CRT, auxiliary encryption is not necessary for this scheme. Additionally, reasonable modifications\nof the random factors make it possible to incorporate all advantages of the CRT as well, including a\n(k, n) threshold, lossless recovery, and low computation complexity. Analyses and experiments are\nprovided to demonstrate the effectiveness of the proposed scheme....
With the rapidly growing number of images over the Internet, efficient scalable semantic image retrieval becomes increasingly\nimportant. This paper presents a novel approach for semantic image retrieval by combining Convolutional Neural Network (CNN)\nand Markov Random Field (MRF). As a key step, image concept detection, that is, automatically recognizing multiple semantic\nconcepts in an unlabeled image, plays an important role in semantic image retrieval. Unlike previous work that uses single-concept\nclassifiers one by one, we detect semanticmulticoncept by using amulticoncept scene classifier. In other words, our approach takes\nmultiple concepts as a holistic scene formulticoncept scene learning. Specifically, we first train a CNN as a concept classifier, which\nfurther includes two types of classifiers: a single-concept fully connected classifier that is best suited to single-concept detection and\na multiconcept scene fully connected classifier that is good for holistic scene detection.Then we propose an MRF-based late fusion\napproach that is able to effectively learn the semantic correlation between the single-concept classifier and multiconcept scene\nclassifier. Finally, the semantic correlation among the subconcepts of images is cought to further improve detection precision. In\norder to investigate the feasibility and effectiveness of our proposed approach, we conduct comprehensive experiments on two\npublicly available image databases.The results show that our proposed approach outperforms several state-of-the-art approaches....
It is a challenging issue to deal with kinds of appearance variations in visual tracking. Existing tracking algorithms build appearance\nmodels upon target templates. Those models are not robust to significant appearance variations due to factors such as illumination\nvariations, partial occlusions, and scale variation. In this paper, we propose a robust tracking algorithm with a learnt dictionary to\nrepresent target candidates. With the learnt dictionary, a target candidate is represented with a linear combination of dictionary\natoms. The discriminative information in learning samples is exploited. In the meantime, the learning processing of dictionaries\ncan learn appearance variations. Based on the learnt dictionary, we can get a more stable representation for target candidates.\nAdditionally, the observation likelihood is evaluated based on both the reconstruct error and dictionary coefficients with ...1\nconstraint. Comprehensive experiments demonstrate the superiority of the proposed tracking algorithm to some state-of-the-art\ntracking algorithms....
Scene understanding is to predict a class label at each pixel of an image. In this study, we propose a semantic segmentation\nframework based on classic generative adversarial nets (GAN) to train a fully convolutional semantic segmentation model along\nwith an adversarial network. To improve the consistency of the segmented image, the high-order potentials, instead of unary or\npairwise potentials, are adopted. We realize the high-order potentials by substituting adversarial network for CRF model, which\ncan continuously improve the consistency and details of the segmented semantic image until it cannot discriminate the segmented\nresult from the ground truth. A number of experiments are conducted on PASCAL VOC 2012 and Cityscapes datasets, and the\nquantitative and qualitative assessments have shown the effectiveness of our proposed approach....
Image segmentation is an essential task in computer vision and pattern recognition. There are two key challenges for image\nsegmentation. One is to find the most discriminative image feature set to get high-quality segments. The other is to achieve good\nperformance among various images. In this paper,wefirstlypropose a selective feature fusionalgorithmtochoose thebest feature set\nby evaluating the results of presegmentation. Specifically, the proposed method fuses selected features and applies the fused features\nto region growing segmentation algorithm. To get better segments on different images, we further develop an algorithm to change\nthreshold adaptively for each image by measuring the size of the region. The adaptive threshold can achieve better performance\non each image than fixed threshold. Experimental results demonstrate that our method improves the performance of traditional\nregion growing by selective feature fusion and adaptive threshold.Moreover, our proposed algorithm obtains promising results and\noutperforms some popular approaches....
Visual tracking is a challenging research topic in the field of computer vision with many potential applications. A large number of\ntracking methods have been proposed and achieved designed tracking performance.However, the current state-of-the-art tracking\nmethods still can not meet the requirements of real-world applications. One of the main challenges is to design a good appearance\nmodel to describe the targetâ??s appearance. In this paper, we propose a novel visual tracking method, which uses compressed features\nto model targetâ??s appearances and then uses SVM to distinguish the target from its background. The compressed features were\nobtained by the zero-tree coding on multi scale wavelet coefficients extracted from an image, which have both the low dimensionality\nand discriminate ability and therefore ensure to achieve better tracking results. The experimental comparisons with several state of-\nthe-art methods demonstrate the superiority of the proposed method....
Loading....