Showing papers on "Channel (digital image) published in 2016"
01 Jan 2016
TL;DR: This thesis develops an effective but very simple prior, called the dark channel prior, to remove haze from a single image, and thus solves the ambiguity of the problem.
Abstract: Haze brings troubles to many computer vision/graphics applications. It reduces the visibility of the scenes and lowers the reliability of outdoor surveillance systems; it reduces the clarity of the satellite images; it also changes the colors and decreases the contrast of daily photos, which is an annoying problem to photographers. Therefore, removing haze from images is an important and widely demanded topic in computer vision and computer graphics areas. The main challenge lies in the ambiguity of the problem. Haze attenuates the light reflected from the scenes, and further blends it with some additive light in the atmosphere. The target of haze removal is to recover the reflected light (i.e., the scene colors) from the blended light. This problem is mathematically ambiguous: there are an infinite number of solutions given the blended light. How can we know which solution is true? We need to answer this question in haze removal. Ambiguity is a common challenge for many computer vision problems. In terms of mathematics, ambiguity is because the number of equations is smaller than the number of unknowns. The methods in computer vision to solve the ambiguity can roughly categorized into two strategies. The first one is to acquire more known variables, e.g., some haze removal algorithms capture multiple images of the same scene under different settings (like polarizers).But it is not easy to obtain extra images in practice. The second strategy is to impose extra constraints using some knowledge or assumptions .All the images in this thesis are best viewed in the electronic version. This way is more practical since it requires as few as only one image. To this end, we focus on single image haze removal in this thesis. The key is to find a suitable prior. Priors are important in many computer vision topics. A prior tells the algorithm "what can we know about the fact beforehand" when the fact is not directly available. In general, a prior can be some statistical/physical properties, rules, or heuristic assumptions. The performance of the algorithms is often determined by the extent to which the prior is valid. Some widely used priors in computer vision are the smoothness prior, sparsity prior, and symmetry prior. In this thesis, we develop an effective but very simple prior, called the dark channel prior, to remove haze from a single image. The dark channel prior is a statistical property of outdoor haze-free images: most patches in these images should contain pixels which are dark in at least one color channel. These dark pixels can be due to shadows, colorfulness, geometry, or other factors. This prior provides a constraint for each pixel, and thus solves the ambiguity of the problem. Combining this prior with a physical haze imaging model, we can easily recover high quality haze-free images.
2,055 citations
08 Oct 2016
TL;DR: A multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps by combining a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale network which refines results locally.
Abstract: The performance of existing image dehazing methods is limited by hand-designed features, such as the dark channel, color disparity and maximum contrast, with complex fusion schemes. In this paper, we propose a multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps. The proposed algorithm consists of a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale net which refines results locally. To train the multi-scale deep network, we synthesize a dataset comprised of hazy images and corresponding transmission maps based on the NYU Depth dataset. Extensive experiments demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods on both synthetic and real-world images in terms of quality and speed.
1,230 citations
TL;DR: In this article, the authors introduce the channel and spatial reliability concepts to DCF tracking and provide a novel learning algorithm for its efficient and seamless integration in the filter update and the tracking process.
Abstract: Short-term tracking is an open and challenging problem for which discriminative correlation filters (DCF) have shown excellent performance. We introduce the channel and spatial reliability concepts to DCF tracking and provide a novel learning algorithm for its efficient and seamless integration in the filter update and the tracking process. The spatial reliability map adjusts the filter support to the part of the object suitable for tracking. This both allows to enlarge the search region and improves tracking of non-rectangular objects. Reliability scores reflect channel-wise quality of the learned filters and are used as feature weighting coefficients in localization. Experimentally, with only two simple standard features, HoGs and Colornames, the novel CSR-DCF method -- DCF with Channel and Spatial Reliability -- achieves state-of-the-art results on VOT 2016, VOT 2015 and OTB100. The CSR-DCF runs in real-time on a CPU.
203 citations
TL;DR: Experimental results on three publicly available databases show that the proposedBIQA algorithm is highly consistent with human perception and outperforms many representative BIQA metrics.
Abstract: In this paper, we propose an efficient blind image quality assessment (BIQA) algorithm, which is characterized by a new feature fusion scheme and a ${k}$ -nearest-neighbor (KNN)-based quality prediction model. Our goal is to predict the perceptual quality of an image without any prior information of its reference image and distortion type. Since the reference image is inaccessible in many applications, the BIQA is quite desirable in this context. In our method, a new feature fusion scheme is first introduced by combining an image’s statistical information from multiple domains (i.e., discrete cosine transform, wavelet, and spatial domains) and multiple color channels (i.e., Y, Cb, and Cr). Then, the predicted image quality is generated from a nonparametric model, which is referred to as the label transfer (LT). Based on the assumption that similar images share similar perceptual qualities, we implement the LT with an image retrieval procedure, where a query image’s KNNs are searched for from some annotated images. The weighted average of the KNN labels (e.g., difference mean opinion score or mean opinion score) is used as the predicted quality score. The proposed method is straightforward and computationally appealing. Experimental results on three publicly available databases (i.e., LIVE II, TID2008, and CSIQ) show that the proposed method is highly consistent with human perception and outperforms many representative BIQA metrics.
163 citations
01 Jul 2016
TL;DR: The proposed salient object detection method for RGB-D images based on evolution strategy outperforms the state-of-the-art methods and utilizes cellular automata to iteratively propagate saliency on the initial saliency map.
Abstract: Salient object detection aims to detect the most attractive objects in images, which has been widely used as a fundamental of various multimedia applications. In this paper, we propose a novel salient object detection method for RGB-D images based on evolution strategy. Firstly, we independently generate two saliency maps on color channel and depth channel of a given RGB-D image based on its super-pixels representation. Then, we fuse the two saliency maps with refinement to provide an initial saliency map with high precision. Finally, we utilize cellular automata to iteratively propagate saliency on the initial saliency map and generate the final detection result with complete salient objects. The proposed method is evaluated on two public RGB-D datasets, and the experimental results show that our method outperforms the state-of-the-art methods.
134 citations
TL;DR: Comparisons with competing methods on benchmark real-world databases consistently show the superiority of the proposed methods for both color FR and reconstruction.
Abstract: Collaborative representation-based classification (CRC) and sparse RC (SRC) have recently achieved great success in face recognition (FR). Previous CRC and SRC are originally designed in the real setting for grayscale image-based FR. They separately represent the color channels of a query color image and ignore the structural correlation information among the color channels. To remedy this limitation, in this paper, we propose two novel RC methods for color FR, namely, quaternion CRC (QCRC) and quaternion SRC (QSRC) using quaternion $\ell _{1}$ minimization. By modeling each color image as a quaternionic signal, they naturally preserve the color structures of both query and gallery color images while uniformly coding the query channel images in a holistic manner. Despite the empirical success of CRC and SRC on FR, a few theoretical results are developed to guarantee their effectiveness. Another purpose of this paper is to establish the theoretical guarantee for QCRC and QSRC under mild conditions. Comparisons with competing methods on benchmark real-world databases consistently show the superiority of the proposed methods for both color FR and reconstruction.
129 citations
TL;DR: In this paper, principal component analysis (PCA) is used for hyperspectral imagery denoising, which is defined in such a way that the first principal component has the largest possible variance under the constraint that it is orthogonal to the preceding components.
Abstract: . Minimum noise fraction (MNF) is a well-known technique for hyperspectral imagery denoising. It transforms a noisy data cube into output channel images with steadily increasing noise levels, which means that the MNF output images contain steadily decreasing image quality. Principal component analysis (PCA) can also be used for hyperspectral imagery denoising. The PCA is defined in such a way that the first principal component has the largest possible variance, and each succeeding component has the highest variance possible under the constraint that it is orthogonal to the preceding components. It can be shown that these components are the Eigenvectors of the covariance matrix of the samples. In this study, we compare PCA-based methods with MNF-based methods for hyperspectral imagery denoising. Our comparison consists of the following 3 steps: (1) forward MNF/PCA transform of a noisy hyperspectral data cube; (2) reduce noise in selected output channel images with index k > k0, a channel number cut...
122 citations
01 Aug 2016
TL;DR: It is shown that a low number of discriminatingly selected Integral Channel Features are sufficient to achieve state-of-the-art results on the MOT2015 and MOT2016 benchmark.
Abstract: Online multi-person tracking benefits from using an online learned appearance model to associate detections to tracks and further to close gaps in detections. Since Integral Channel Features (ICF) are popular for fast pedestrian detection, we propose an online appearance model that is using the same features without recalculation. The proposed method uses online Multiple-Instance Learning (MIL) to incrementally train an appearance model for each person discriminating against its surrounding. We show that a low number of discriminatingly selected Integral Channel Features are sufficient to achieve state-of-the-art results on the MOT2015 and MOT2016 benchmark.
105 citations
TL;DR: This work proposes and demonstrates an RGB VLC transmission using CMOS image sensor with multi-input multi-output (MIMO) technique to mitigate the ICI and retrieve the three independent color channels in the rolling shutter pattern.
Abstract: Red, green, blue (RGB) light-emitting-diodes (LEDs) are used to increase the visible light communication (VLC) transmission capacity via wavelength-division-multiplexing (WDM), and the color image sensor in mobile phone is used to separate different color signals via a color filter array. However, due to the wide optical bandwidths of the color filters, there is a high spectral overlap among different channels, and a high inter-channel interference (ICI) happens. Here, we propose and demonstrate an RGB VLC transmission using CMOS image sensor with multi-input multi-output (MIMO) technique to mitigate the ICI and retrieve the three independent color channels in the rolling shutter pattern. Data pattern extinction-ratio (ER) enhancement and thresholding are deployed.
78 citations
TL;DR: Quantitative and qualitative results obtained from experiments on a wide variety of natural scene images demonstrate the effectiveness of the proposed approach over other methods at reducing artefact while increasing image contrast and colourfulness.
76 citations
TL;DR: RGB image has given better clarity and noise free image which is suitable for infected leaf detection than Grayscale image.
Abstract: Background/Objectives: Digital image processing is used various fields for analyzing different applications such as medical sciences, biological sciences. Various image types have been used to detect plant diseases. This work is analyzed and compared two types of images such as Grayscale, RGB images and the comparative result is given. Methods/Statistical Analysis: We examined and analyzed the Grayscale and RGB images using image techniques such as pre processing, segmentation, clustering for detecting leaves diseases. Results/Finding: In detecting the infected leaves, color becomes an important feature to identify the disease intensity. We have considered Grayscale and RGB images and used median filter for image enhancement and segmentation for extraction of the diseased portion which are used to identify the disease level. Conclusion: RGB image has given better clarity and noise free image which is suitable for infected leaf detection than Grayscale image.
TL;DR: A learning strategy to select the optimal parameters of the nonlinear stretching by optimizing a novel image quality measurement, named as the Modified Contrast-Naturalness-Colorfulness (MCNC) function, which employs a more effective objective criterion and can better agree with human visual perception.
TL;DR: Wang et al. as discussed by the authors proposed a quaternion principal component analysis network (QPCANet) for color image classification, which takes into account the spatial distribution information of RGB channels in color images.
01 Sep 2016
TL;DR: Experimental results show that combining two modalities gives better recognition accuracy than using each modality individually.
Abstract: In this paper, we propose an approach to recognize human actions by the fusion of RGB and Depth data. Firstly, Motion History Images (MHI) are generated from RGB videos which represent the temporal information about the action. Then the original depth data is rotated in 3D point clouds and three Depth Motion Maps (DMM) are generated over the entire depth sequence corresponding to the front, side and top projection views. A 4 Channel Deep Convolutional Neural Network is trained, where the first channel is for classifying MHIs and the remaining three for the front, side and top view generated from depth data respectively. The proposed method is evaluated on publically available UTD-MHAD dataset which contains both RGB and depth videos. Experimental results show that combining two modalities gives better recognition accuracy than using each modality individually.
Posted Content•
TL;DR: In this paper, the camera sensor's color multiplexing pattern is learned by encoding it as layer whose learnable weights determine which color channel, from among a fixed set, will be measured at each location.
Abstract: Recent progress on many imaging and vision tasks has been driven by the use of deep feed-forward neural networks, which are trained by propagating gradients of a loss defined on the final output, back through the network up to the first layer that operates directly on the image. We propose back-propagating one step further---to learn camera sensor designs jointly with networks that carry out inference on the images they capture. In this paper, we specifically consider the design and inference problems in a typical color camera---where the sensor is able to measure only one color channel at each pixel location, and computational inference is required to reconstruct a full color image. We learn the camera sensor's color multiplexing pattern by encoding it as layer whose learnable weights determine which color channel, from among a fixed set, will be measured at each location. These weights are jointly trained with those of a reconstruction network that operates on the corresponding sensor measurements to produce a full color image. Our network achieves significant improvements in accuracy over the traditional Bayer pattern used in most color cameras. It automatically learns to employ a sparse color measurement approach similar to that of a recent design, and moreover, improves upon that design by learning an optimal layout for these measurements.
TL;DR: An adaptive gain adjustment method is proposed here aiming at minimizing the number of over-range pixels while maximizing the image sharpness and information content and results have demonstrated that the proposed method outperforms the others with regard to colorfulness, information content, and sharpness.
TL;DR: In this article, the authors used detailed field surveys to assess the capability of the CASI hyperspectral imaging system and Aquarius bathymetric LiDAR to measure bed elevations in rivers with disparate optical characteristics.
Abstract: Remote sensing is a powerful tool for examining river morphology. This study used detailed field surveys to assess the capability of the CASI hyperspectral imaging system and Aquarius bathymetric LiDAR to measure bed elevations in rivers with disparate optical characteristics. Field measurements of water column optical properties in the clear Snake River, the more complex Blue and Colorado, and highly turbid Muddy Creek were used to calculate depth retrieval precision and dynamic range. Differences in depth of a few centimeters were detectable via passive optical techniques in the clearest stream, but precision was greatly reduced under turbid conditions. The bathymetric LiDAR evaluated in this study could not detect shallow depths or differences in depth smaller than 11 cm owing to the difficulty of distinguishing water surface and bottom returns in laser waveforms. In clear water and with high radiometric resolution, hyperspectral systems such as CASI could detect depths approaching 10 m, but semi-empirical analysis of the Aquarius LiDAR indicated that maximum detectable depths were of the order of 2–3 m in the clear-flowing Snake River, and closer to 1 m in the more turbid streams. Turbidity also constrained spectrally based depth retrieval, and depth estimates from the Blue/Colorado were far less reliable than on the Snake. Both sensors yielded positively biased (0.03 m for CASI, 0.08 m for Aquarius) bed elevations on the Snake, with precisions of 0.16–0.17 m. For the Blue/Colorado, mean errors were of the order of 0.2 m, biased shallow for optical data and biased deep for LiDAR, although no Aquarius laser returns were recorded from the deepest parts of these channels; precisions were reduced to 0.29–0.32 m. Both approaches have advantages and limitations, and prospective users must understand the capabilities and constraints associated with various types of remote sensing to ensure efficient use of these evolving technologies. Copyright © 2015 John Wiley & Sons, Ltd.
TL;DR: Improved digital image watermarking model based on a coefficient quantization technique that intelligently encodes the owner's information for each color channel to improve imperceptibility and robustness of the hidden information is presented.
Abstract: Novel digital image watermarking method using a wavelet-based quantization approachOptimal color channel selection scheme for the embeddingOtsu's classification-based adaptive threshold for the extraction processOutperformance of imperceptibility and robustness to state-of-the-art techniques Supporting safe and resilient authentication and integrity of digital images is of critical importance in a time of enormous creation and sharing of these contents This paper presents an improved digital image watermarking model based on a coefficient quantization technique that intelligently encodes the owner's information for each color channel to improve imperceptibility and robustness of the hidden information Concretely, a novel color channel selection mechanism automatically selects the optimal HL4 and LH4 wavelet coefficient blocks for embedding binary bits by adjusting block differences, calculated between LH and HL coefficients of the host image The channel selection aims to minimize the visual difference between the original image and the embedded image On the other hand, the strength of the watermark is controlled by a factor to achieve an acceptable tradeoff between robustness and imperceptibility The arrangement of the watermark pixels before shuffling and the channel into which each pixel is embedded is ciphered in an associated key This key is utterly required to recover the original watermark, which is extracted through an adaptive clustering thresholding mechanism based on the Otsu's algorithm Benchmark results prove the model to support imperceptible watermarking as well as high robustness against common attacks in image processing, including geometric, non-geometric transformations, and lossy JPEG compression The proposed method enhances more than 4źdB in the watermarked image quality and significantly reduces Bit Error Rate in the comparison of state-of-the-art approaches
TL;DR: The simulated experimental results and security analysis show that the proposed cryptosystem has fairly good encryption effect than the original fusion scheme but also has the capability to sustain noise which gets add during transmission over noisy channel.
Abstract: A Modified Dual Fusion (MDF) technique of image encryption is proposed in this paper to overcome the limitations that exist in the original research work of Q. Zhang et al. (Optik 124:3596---3600, 2013). A novel technique of DNA encoding is applied through chaotic maps on pixel level and SHA-256 hash of the plain image is used to generate secret keys to avoid chosen-plaintext attack. Also, in the modified scheme, two random images are generated from chaotic maps to fuse with the plain image after permutation in digital and DNA domains using XOR and addition operations respectively. The simulated experimental results and security analysis show that the proposed cryptosystem has fairly good encryption effect than the original fusion scheme but also has the capability to sustain noise which gets add during transmission over noisy channel. Besides, the paramount factor of improved scheme is suitable for the real time applications.
TL;DR: An in-depth analysis of the problem of disease symptom differentiation is presented, in which issues such as lesion delimitation, illumination, leaf venation interference, leaf ruggedness, among others, are thoroughly discussed.
Abstract: A new computer algorithm is proposed to differentiate signs and symptoms of plant disease from asymptomatic tissues in plant leaves. The simple algorithm manipulates the histograms of the H (from HSV color space) and a (from the L*a*b* color space) color channels. All steps in the algorithmic process are automatic, with the exception of the final step in which the user decides which channel (H or a) provides the better differentiation. An in-depth analysis of the problem of disease symptom differentiation is also presented, in which issues such as lesion delimitation, illumination, leaf venation interference, leaf ruggedness, among others, are thoroughly discussed. The proposed algorithm was tested under a wide variety of conditions, which included 19 plant species, 82 diseases, and images gathered under controlled and uncontrolled environmental conditions. The algorithm proved useful for a wide variety of plant diseases and conditions, although some situations may require alternative solutions.
01 Dec 2016
TL;DR: This work introduces a novel approach that estimates the back-scattered light locally, based on the observation of a neighborhood around the pixel of interest, and proposes to fuse the images obtained over both small and large neighborhoods, each capturing distinct features from the input image.
Abstract: Underwater images suffer from severe perceptual/visual degradation, due to the dense and non-uniform medium, causing scattering and attenuation of the propagated light that is sensed. Typical restoration methods rely on the popular Dark Channel Prior to estimate the light attenuation factor, and subtract the back-scattered light influence to invert the underwater imaging model. However, as a consequence of using approximate and global estimates of the back-scattered light, most existing single-image underwater descattering techniques perform poorly when restoring non-uniformly illuminated scenes. To mitigate this problem, we introduce a novel approach that estimates the back-scattered light locally, based on the observation of a neighborhood around the pixel of interest. To circumvent issue related to selection of the neighborhood size, we propose to fuse the images obtained over both small and large neighborhoods, each capturing distinct features from the input image. In addition, the Laplacian of the original image is provided as a third input to the fusion process, to enhance texture details in the reconstructed image. These three derived inputs are seamlessly blended via a multi-scale fusion approach, using saliency, contrast, and saturation metrics to weight each input. We perform an extensive qualitative and quantitative evaluation against several specialized techniques. In addition to its simplicity, our method outperforms the previous art on extreme underwater cases of artificial ambient illumination and high water turbidity.
TL;DR: When the chaos masking technique is adopted, the image encrypted by the proposed encryption scheme can be successfully transmitted and decrypted in a 10 km single mode fiber channel from SL1 to SL2, which is accompanied by a bit error rate of less than 6.18 × 10-19.
Abstract: A novel symmetric image encryption-then-transmission system based on optical chaos using semiconductor lasers is proposed. In this paper, with identical chaotic injection from a master laser, two slave lasers (SL1 and SL2) can output similar chaotic signals served as chaotic carrier to transmit image. Meanwhile, the chaotic signal of SL1 can be used to generate the key of the encryption scheme. After employing the three-dimensional (3D) cat map and logistic chaotic map, the positions of image pixels are shuffled, and the relationship between the cipher-image and the plain-image is confused simultaneously. Therefore, the system can resist the common attacks such as statistical attack, differential attack, and brute force attack. Through numerical simulations, the high quality chaos synchronization between SL1 and SL2 is obtained. When the chaos masking technique is adopted, the image encrypted by the proposed encryption scheme can be successfully transmitted and decrypted in a 10 km single mode fiber channel from SL1 to SL2, which is accompanied by a bit error rate of less than ${\rm{6.18\,\times \,10}}^{- 19}$ . Exhaustive tests about security analysis are carried out, demonstrating the valuable feasibility and high security of the image encryption-then-transmission system.
TL;DR: Compared with the state-of-the-art methods, the proposed method via image texture features that are extracted from well selected color model and color channel is superior in both detection accuracy and robustness.
TL;DR: The random path simulative model of Retinex can be given a representation in terms of Absorbing Markov Chains, by means of the embedding into a suitable state-space and the Markov Chain based algorithm is found to be more efficient than the basic random path sampling in obtaining noise free images.
TL;DR: Experimental results indicate that the proposed algorithm can simultaneously enhance the low-light images and reduce noise effectively and could also perform quite well compared with the current common image enhancement and noise reduction algorithms in terms of the subjective visual effects and objective quality assessments.
Abstract: Images obtained under low-light conditions tend to have the characteristics of low-grey levels, high-noise levels, and indistinguishable details. Image degradation not only affects the recognition of images, but also influences the performance of the computer vision system. The low-light image enhancement algorithm based on the dark channel prior de-hazing technique can enhance the contrast of images effectively and can highlight the details of images. However, the dark channel prior de-hazing technique ignores the effects of noise, which leads to significant noise amplification after the enhancement process. In this study, a de-hazing-based simultaneous enhancement and noise reduction algorithm of are proposed by analysing the essence of the dark channel prior de-hazing technique and bilateral filter. First, the authors estimate the values of the initial parameters of the hazy image model by de-hazing technique. Then, they correct the parameters of the hazy image model alternately with the iterative joint bilateral filter. Experimental results indicate that the proposed algorithm can simultaneously enhance the low-light images and reduce noise effectively. The proposed algorithm could also perform quite well compared with the current common image enhancement and noise reduction algorithms in terms of the subjective visual effects and objective quality assessments.
TL;DR: In this article, the authors proposed a new method of underwater image restoration and enhancement which was inspired by the dark channel prior in image dehazing field, by estimating and rectifying the bright channel image, estimating the atmospheric light and estimating and refining the transmittance image, eventually underwater images were restored.
Abstract: This paper proposed a new method of underwater images restoration and enhancement which was inspired by the dark channel prior in image dehazing field. Firstly, we proposed the bright channel prior of underwater environment. By estimating and rectifying the bright channel image, estimating the atmospheric light, and estimating and refining the transmittance image, eventually underwater images were restored. Secondly, in order to rectify the color distortion, the restoration images were equalized by using the deduced histogram equalization. The experiment results showed that the proposed method could enhance the quality of underwater images effectively.
19 Aug 2016
TL;DR: A deep transmission network for robust single image dehazing that simultaneously copes with three color channels and local patch information to automatically explore and exploit haze-relevant features in a learning framework is developed.
Abstract: State-of-the-art single image dehazing algorithms have some challenges to deal with images captured under complex weather conditions because their assumptions usually do not hold in those situations. In this paper, we develop a deep transmission network for robust single image dehazing. This deep transmission network simultaneously copes with three color channels and local patch information to automatically explore and exploit haze-relevant features in a learning framework. We further explore different network structures and parameter settings to achieve tradeoffs between performance and speed, which shows that color channels information is the most useful haze-relevant feature rather than local information. Experiment results demonstrate that the proposed algorithm outperforms state-of-the-art methods on both synthetic and real-world datasets.
TL;DR: Experimental results show that the proposed watermarking scheme not only provides better imperceptibility and robustness against various attacks (including common image processing operations and geometric distortions), but also yields better watermark detection performance than some state-of-the-art imageWatermarking schemes.
Abstract: Moments and moment invariants have become a powerful tool in gray image watermarking. More recently, a few moment-based approaches were developed to embed watermark into color host image by marking the luminance component or three color channels, and they always cannot obtain better imperceptibility and robustness because of ignoring the correlation between different color channels. Quaternion is a generalization of the complex numbers, and can treat a color image as a vector field without losing color information. In this paper, based on algebra of quaternions and radial harmonic Fourier moments (RHFMs), we introduced quaternion radial harmonic Fourier moments (QRHFMs) for color images, which can be seen as the generalization of RHFMs for gray-level images. We analyzed and discussed the geometric invariant property of QRHFMs, and proposed a geometric invariant color image watermarking scheme using QRHFMs. Experimental results show that the proposed watermarking scheme not only provides better imperceptibility and robustness against various attacks (including common image processing operations and geometric distortions), but also yields better watermark detection performance than some state-of-the-art image watermarking schemes.
01 Jun 2016
TL;DR: This work assesses the performance of two state-of-the-art correlationfilter-based object tracking methods on Linköping Thermal InfraRed (LTIR) dataset of medium wave and longwave infrared videos, using deep convolutional neural networks (CNN) features as well as other traditional hand-crafted descriptors.
Abstract: Correlation filters for visual object tracking in visible imagery has been well-studied. Most of the correlation-filterbased methods use either raw image intensities or feature maps of gradient orientations or color channels. However, well-known features designed for visible spectrum may not be ideal for infrared object tracking, since infrared and visible spectra have dissimilar characteristics in general. We assess the performance of two state-of-the-art correlationfilter-based object tracking methods on Linkoping Thermal InfraRed (LTIR) dataset of medium wave and longwave infrared videos, using deep convolutional neural networks (CNN) features as well as other traditional hand-crafted descriptors. The deep CNN features are trained on an infrared dataset consisting of 16K objects for a supervised classification task. The highest performance in terms of the overlap metric is achieved when these deep CNN features are utilized in a correlation-filter-based tracker.
TL;DR: Experimental results show that the proposed CMD-C strategy has made great improvement over conventional methods in resisting state-of-the-art steganalytic methods.
Abstract: It is conventionally assumed that steganographic schemes for gray-scale images can be directly applied to color images by embedding messages independently in different color channels. However, the correlation among color channels may be disturbed and it is unclear how to preserve the channel correlation so as to increase empirical security. In this paper, we propose a strategy called CMD-C (clustering modification directions for color components). The basic idea of the strategy is to change different color components from the same pixel location towards a positive or negative direction consistently. To implement the strategy, we decompose an image into several sub-images in which segmented hidden message bits are successively embedded. The embedding costs of a sub-image are computed by considering the correlation both within and among color channels. Experimental results show that the proposed CMD-C strategy has made great improvement over conventional methods in resisting state-of-the-art steganalytic methods.