Showing papers on "Channel (digital image) published in 2017"

Discriminative Correlation Filter with Channel and Spatial Reliability

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 allows tracking of non-rectangular objects as well as extending the search region. Channel reliability reflects the quality of the learned filter and it is used as a feature weighting coefficient 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 OTB. The CSR-DCF runs in real-time on a CPU.

Underwater Image Restoration Based on Image Blurriness and Light Absorption

Abstract: Underwater images often suffer from color distortion and low contrast, because light is scattered and absorbed when traveling through water. Such images with different color tones can be shot in various lighting conditions, making restoration and enhancement difficult. We propose a depth estimation method for underwater scenes based on image blurriness and light absorption, which can be used in the image formation model (IFM) to restore and enhance underwater images. Previous IFM-based image restoration methods estimate scene depth based on the dark channel prior or the maximum intensity prior. These are frequently invalidated by the lighting conditions in underwater images, leading to poor restoration results. The proposed method estimates underwater scene depth more accurately. Experimental results on restoring real and synthesized underwater images demonstrate that the proposed method outperforms other IFM-based underwater image restoration methods.

Fast Image Dehazing Method Based on Linear Transformation

Abstract: Images captured in hazy or foggy weather conditions are seriously degraded by the scattering of atmospheric particles, which directly influences the performance of outdoor computer vision systems. In this paper, a fast algorithm for single image dehazing is proposed based on linear transformation by assuming that a linear relationship exists in the minimum channel between the hazy image and the haze-free image. First, the principle of linear transformation is analyzed. Accordingly, the method of estimating a medium transmission map is detailed and the weakening strategies are introduced to solve the problem of the brightest areas of distortion. To accurately estimate the atmospheric light, an additional channel method is proposed based on quad-tree subdivision. In this method, average grays and gradients in the region are employed as assessment criteria. Finally, the haze-free image is obtained using the atmospheric scattering model. Numerous experimental results show that this algorithm can clearly and naturally recover the image, especially at the edges of sudden changes in the depth of field. It can, thus, achieve a good effect for single image dehazing. Furthermore, the algorithmic time complexity is a linear function of the image size. This has obvious advantages in running time by guaranteeing a balance between the running speed and the processing effect.

Deep Extreme Cut: From Extreme Points to Object Segmentation

Abstract: This paper explores the use of extreme points in an object (left-most, right-most, top, bottom pixels) as input to obtain precise object segmentation for images and videos. We do so by adding an extra channel to the image in the input of a convolutional neural network (CNN), which contains a Gaussian centered in each of the extreme points. The CNN learns to transform this information into a segmentation of an object that matches those extreme points. We demonstrate the usefulness of this approach for guided segmentation (grabcut-style), interactive segmentation, video object segmentation, and dense segmentation annotation. We show that we obtain the most precise results to date, also with less user input, in an extensive and varied selection of benchmarks and datasets. All our models and code are publicly available on this http URL.

An Innovative Salient Object Detection Using Center-Dark Channel Prior

Abstract: Saliency detection aims to detect the most attractive objects in images, which has been widely used as a foundation for various multimedia applications. In this paper, we propose a novel salient object detection algorithm for RGB-D images using center-dark channel prior. First, we generate an initial saliency map based on a color saliency map and a depth saliency map of a given RGB-D image. Then, we generate a center-dark channel map based on a center saliency prior and a dark channel prior. Finally, we fuse the initial saliency map with the center dark channel map to generate the final saliency map. The proposed algorithm is evaluated on two public RGB-D datasets, and the experimental results show that our method outperforms the state-of-the-art methods.

DNA Chaos Blend to Secure Medical Privacy

Abstract: In this technological era, it is highly essential to protect the digital medical data from the fraud and forgery as they are transmitted over the public channel. Also with the increased data traffic, it is hard to transmit the entire bulky medical data. New methods have come into the scene to reduce the traffic while maintaining the sufficient level of security. Partial encryption is one of the methods which selectively encrypt the bulky medical image. Meanwhile, if the same medical image is needed to be reused for another diagnosis, then it is recommended to protect the entire medical image. This paper proposes a hybrid encryption scheme based on deoxyribo nucleic acid and chaotic maps, which can be adaptable for both selective and full medical image encryption. The proposed algorithm uses multiple chaotic maps in single process to generate the highly random keys for encrypting the color digital imaging and communications in medicine image. The algorithm comprises three phases, namely, permutation, encoding, and diffusion. In all the phases, the selection of specific rule set depends on the key sequences produced from the combined chaotic system. Experimental results are carried out to validate the resistance of the developed algorithm toward statistical, differential, and brute force attacks.

Cascaded Feature Network for Semantic Segmentation of RGB-D Images

Abstract: Fully convolutional network (FCN) has been successfully applied in semantic segmentation of scenes represented with RGB images. Images augmented with depth channel provide more understanding of the geometric information of the scene in the image. The question is how to best exploit this additional information to improve the segmentation performance.,,In this paper, we present a neural network with multiple branches for segmenting RGB-D images. Our approach is to use the available depth to split the image into layers with common visual characteristic of objects/scenes, or common “scene-resolution”. We introduce context-aware receptive field (CaRF) which provides a better control on the relevant contextual information of the learned features. Equipped with CaRF, each branch of the network semantically segments relevant similar scene-resolution, leading to a more focused domain which is easier to learn. Furthermore, our network is cascaded with features from one branch augmenting the features of adjacent branch. We show that such cascading of features enriches the contextual information of each branch and enhances the overall performance. The accuracy that our network achieves outperforms the stateof-the-art methods on two public datasets.

Infrared Image Colorization Based on a Triplet DCGAN Architecture

Abstract: This paper proposes a novel approach for colorizing near infrared (NIR) images using a Deep Convolutional Generative Adversarial Network (GAN) architecture. The proposed approach is based on the usage of a triplet model for learning each color channel independently, in a more homogeneous way. It allows a fast convergence during the training, obtaining a greater similarity between the colored NIR image and the corresponding ground truth. The proposed approach has been evaluated with a large data set of NIR images and compared with a recent approach, which is also based on a GAN architecture where all the color channels are obtained at the same time.

Low-light image enhancement using CNN and bright channel prior

Abstract: In this paper, we propose a joint framework to enhance images under low-light conditions. First, a convolutional neural network (CNN) based architecture is proposed to denoise low-light images. Then, based on atmosphere scattering model, we introduce a low-light model to enhance image contrast. In our low-light model, we propose a simple but effective image prior, bright channel prior, to estimate the transmission parameter; besides, an effective filter is designed to adaptively estimate environment light in different image areas. Experimental results demonstrate that our method achieves superior performance over other methods.

Dehazing of remote sensing images using improved restoration model based dark channel prior

Abstract: Haze degrades visual information of remotely sensed images. Therefore, haze removal is a demanding and significant task for visual multispectral information improvement. The existing haze removal techniques utilize different restrictions and before restoring hazy images in an efficient manner. The review of existing haze removal methods demonstrates that the haze-free images suffer from colour distortion and halo artefacts problems. To solve these issues, an improved restoration model based dark channel prior is proposed in this paper. The proposed technique has redefined transmission map, with the aim to reduce the colour distortion problem. The modified joint trilateral filter is also utilized to improve the coarse estimated atmospheric veil. The experimental results reveal that the proposed approach provides visually significant haze-free images and also preserves the significant detail.

A Retinal Vessel Detection Approach Based on Shearlet Transform and Indeterminacy Filtering on Fundus Images

Abstract: A fundus image is an effective tool for ophthalmologists studying eye diseases. Retinal vessel detection is a significant task in the identification of retinal disease regions. This study presents a retinal vessel detection approach using shearlet transform and indeterminacy filtering. The fundus image’s green channel is mapped in the neutrosophic domain via shearlet transform. The neutrosophic domain images are then filtered with an indeterminacy filter to reduce the indeterminacy information. A neural network classifier is employed to identify the pixels whose inputs are the features in neutrosophic images. The proposed approach is tested on two datasets, and a receiver operating characteristic curve and the area under the curve are employed to evaluate experimental results quantitatively. The area under the curve values are 0.9476 and 0.9469 for each dataset respectively, and 0.9439 for both datasets. The comparison with the other algorithms also illustrates that the proposed method yields the highest evaluation measurement value and demonstrates the efficiency and accuracy of the proposed method.

A Hyperspectral Image Classification Framework with Spatial Pixel Pair Features

Abstract: During recent years, convolutional neural network (CNN)-based methods have been widely applied to hyperspectral image (HSI) classification by mostly mining the spectral variabilities. However, the spatial consistency in HSI is rarely discussed except as an extra convolutional channel. Very recently, the development of pixel pair features (PPF) for HSI classification offers a new way of incorporating spatial information. In this paper, we first propose an improved PPF-style feature, the spatial pixel pair feature (SPPF), that better exploits both the spatial/contextual information and spectral information. On top of the new SPPF, we further propose a flexible multi-stream CNN-based classification framework that is compatible with multiple in-stream sub-network designs. The proposed SPPF is different from the original PPF in its paring pixel selection strategy: only pixels immediately adjacent to the central one are eligible, therefore imposing stronger spatial regularization. Additionally, with off-the-shelf classification sub-network designs, the proposed multi-stream, late-fusion CNN-based framework outperforms competing ones without requiring extensive network configuration tuning. Experimental results on three publicly available datasets demonstrate the performance of the proposed SPPF-based HSI classification framework.

A novel blind color image watermarking based on Contourlet transform and Hessenberg decomposition

Abstract: In this paper, a novel blind color image watermarking based on Contourlet transform and Hessenberg decomposition is proposed to protect digital copyright of color image. Firstly, each color channel of the host image is transformed by Contourlet transform and its low frequency sub-band is divided into 4ź×ź4 non-overlap coefficient block. Secondly, the coefficient block selected by MD5-based Hash pseudo-random algorithm is decomposed by Hessenberg decomposition. Thirdly, the watermark information permuted by Arnold transform is embedded into the biggest energy element of the upper Hessenberg matrix by quantization technique. In extraction process, the quantization strength is used for blindly extracting watermark information from the attacked host image without the help of any original image. The results show that the proposed scheme has higher imperceptibility and robustness against most common image attacks in comparison with other related methods.

Single Image Dehazing via Large Sky Region Segmentation and Multiscale Opening Dark Channel Model

Abstract: Outdoor images acquired under poor weather conditions are usually contaminated by suspended particles and aerosols in the atmosphere These captured images easily suffer from contrast reduction, low visibility, and color distortion In this paper, we develop a novel single image dehazing method based on large sky region segmentation and multiscale opening dark channel model (MODCM) First, a simple but effective method for large sky region detection based on SVM classification is presented, which can be considered as the first step of atmospheric light estimation Then, two different strategies are utilized for obtaining a more accurate estimate of the atmospheric light according to the mentioned detection result Furthermore, MODCM can adaptively make use of different patch sizes to calculate the dark channel according to different edge levels, which can prevent halo artifacts near edges of depth discontinuity In addition, the gradient domain guided filter is adopted to refine the initial transmission map due to its accuracy near edges Finally, the haze-free image can be obtained through correcting the colors of the sky region and combining the sky and non-sky region Experimental results on different kinds of hazy images indicate that our proposed approach can produce the visually desirable results with genuine color and high scene visibility, even superior than the other state-of-the-art dehazing methods

A novel microaneurysms detection approach based on convolutional neural networks with reinforcement sample learning algorithm

Abstract: Microaneurysms (MAs) are known as early signs of diabetic-retinopathy which are called red lesions in color fundus images. Detection of MAs in fundus images needs highly skilled physicians or eye angiography. Eye angiography is an invasive and expensive procedure. Therefore, an automatic detection system to identify the MAs locations in fundus images is in demand. In this paper, we proposed a system to detect the MAs in colored fundus images. The proposed method composed of three stages. In the first stage, a series of pre-processing steps are used to make the input images more convenient for MAs detection. To this end, green channel decomposition, Gaussian filtering, median filtering, back ground determination, and subtraction operations are applied to input colored fundus images. After pre-processing, a candidate MAs extraction procedure is applied to detect potential regions. A five-stepped procedure is adopted to get the potential MA locations. Finally, deep convolutional neural network (DCNN) with reinforcement sample learning strategy is used to train the proposed system. The DCNN is trained with color image patches which are collected from ground-truth MA locations and non-MA locations. We conducted extensive experiments on ROC dataset to evaluate of our proposal. The results are encouraging.

Color transfer for underwater dehazing and depth estimation

Abstract: Imaging in the underwater environment suffers from color degradation and poor visibility since the light spectrum is selectively absorbed and scattered by water and floating particles. In this paper we introduce a simple but effective underwater dehazing approach that builds on an original color transfer strategy to align the color statistics of a hazy input to the ones of a reference image, also captured underwater, but with neglectable water attenuation. As an original specificity, our proposed color transfer approach is designed to promote the preservation of salient regions, as well as of the details obtained by subtracting from the input an edge-preserving smoothed version of itself. The color-transferred input is then restored by inverting a simplified version of the McGlamery underwater image formation model, using the conventional Dark Channel Prior to estimate the transmission map and the back-scattered light parameter involved in the model. We demonstrate that our color transfer step is crucial for a good transmission estimation but mostly for underwater dehazing where other specialized techniques fail. Extensive qualitative and quantitative results demonstrate the effectiveness of the proposed approach to estimate the transmission, including for cases where traditional specialized techniques fail, and to improve the image quality.

The application of nonlocal total variation in image denoising for mobile transmission

Abstract: Image transmission is one of the key techniques in image mobile communication. However, it is generally corrupted by noise in wireless channel, which will decrease the visual quality and affect the sub-sequential applications, such as pattern recognition, classification and so on. Total variation is widely used in the problems of image denoising, due to its advantage in preserving texture in image. In this paper, a novel minimization framework is presented where the objective function includes an usual l2 data-fidelity term and two types of total variation regularizer. According to the theory analysis, the novel objective function can preserve the local geometric structure in restored image. Furthermore, we proposes to solve the novel framework with majorization- minimization and compares this novel algorithm with some current restoration method. The numerical experiments show the efficiency and effectiveness of the proposed algorithm.

Sparsity-Based Color Image Super Resolution via Exploiting Cross Channel Constraints

Abstract: Sparsity constrained single image super-resolution (SR) has been of much recent interest. A typical approach involves sparsely representing patches in a low-resolution (LR) input image via a dictionary of example LR patches, and then using the coefficients of this representation to generate the high-resolution (HR) output via an analogous HR dictionary. However, most existing sparse representation methods for SR focus on the luminance channel information and do not capture interactions between color channels. In this paper, we extend sparsity-based SR to multiple color channels by taking the color information into account. Edge similarities amongst RGB color bands are exploited as cross channel correlation constraints. These additional constraints lead to a new optimization problem, which is not easily solvable; however, a tractable solution is proposed to solve it efficiently. Moreover, to fully exploit the complementary information among color channels, a dictionary learning method is also proposed specifically to learn color dictionaries that encourage edge similarities. Merits of the proposed method over state of the art are demonstrated both visually and quantitatively using image quality metrics.

A Multi-view RGB-D Approach for Human Pose Estimation in Operating Rooms

Abstract: Many approaches have been proposed for human pose estimation in single and multi-view RGB images. However, some environments, such as the operating room, are still very challenging for state-of-the-art RGB methods. In this paper, we propose an approach for multi-view 3D human pose estimation from RGB-D images and demonstrate the benefits of using the additional depth channel for pose refinement beyond its use for the generation of improved features. The proposed method permits the joint detection and estimation of the poses without knowing a priori the number of persons present in the scene. We evaluate this approach on a novel multi-view RGB-D dataset acquired during live surgeries and annotated with ground truth 3D poses.

A machine learning method to identify and remove reflection artifacts in photoacoustic channel data

Abstract: Photoacoustic imaging is often used to visualize point-like targets, including circular cross sections of small cylindrical implants like brachytherapy seeds as well as circular cross sections of metal needles. When imaging these pointlike targets in the presence of highly echogenic structures, the resulting image will suffer due to reflection artifacts which appear as true signals in the traditional beamformed image. We propose to use machine learning methods to identify these types of noise artifacts for removal. A deep convolutional neural network was trained to locate and classify source and reflection artifacts in photoacoustic channel data simulated in k-Wave. Simulated channel data contained one source and one artifact with varying target locations, medium sound speeds, and −3dB channel noise. In testing 3,998 simulated images, we achieved a 99.1% and 98.8% success rate in classifying sources and artifacts, respectively, while obtaining a misclassification rate below 3.1%, where a misclassification was defined as a source or artifact detected as an artifact or source, respectively. The network, which was only trained on simulated data, was then transferred to experimental data with 100% source classification accuracy and 0.40 mm mean source location accuracy. These results are promising as they show that a network trained with only simulated data can distinguish experimental sources and artifacts in photoacoustic channel data and display this information in a novel artifact-free image format.

A Region-Wised Medium Transmission Based Image Dehazing Method

Abstract: Image dehazing is a technique to enhance the images acquired in poor weather conditions, such as fog and haze. Existing image dehazing methods are mainly based on dark channel prior. Since the dark channel is not reasonable for sky regions, a sky segmentation and region wised medium transmission based image dehazing method is proposed in this paper. Firstly, sky regions are segmented by quad-tree splitting based feature pixels detection. Then, a medium transmission estimation method for sky regions is proposed based on color characteristic observation of sky regions. The medium transmission is then filtered by an edge preserving guided filter. Finally, based on the estimated medium transmission, the hazed images are restored. Experimental results demonstrate that the performance of the proposed method is better than that of existing methods. The restored image is more natural, especially in the sky regions.

A Multi-view RGB-D Approach for Human Pose Estimation in Operating Rooms

Abstract: Many approaches have been proposed for human pose estimation in single and multi-view RGB images. However, some environments, such as the operating room, are still very challenging for state-of-the-art RGB methods. In this paper, we propose an approach for multi-view 3D human pose estimation from RGB-D images and demonstrate the benefits of using the additional depth channel for pose refinement beyond its use for the generation of improved features. The proposed method permits the joint detection and estimation of the poses without knowing a priori the number of persons present in the scene. We evaluate this approach on a novel multi-view RGB-D dataset acquired during live surgeries and annotated with ground truth 3D poses.

Locally Adaptive Color Correction for Underwater Image Dehazing and Matching

Abstract: Underwater images are known to be strongly deteriorated by a combination of wavelength-dependent light attenuation and scattering. This results in complex color casts that depend both on the scene depth map and on the light spectrum. Color transfer, which is a technique of choice to counterbalance color casts, assumes stationary casts, defined by global parameters, and is therefore not directly applicable to the locally variable color casts encountered in underwater scenarios. To fill this gap, this paper introduces an original fusion-based strategy to exploit color transfer while tuning the color correction locally, as a function of the light attenuation level estimated from the red channel. The Dark Channel Prior (DCP) is then used to restore the color compensated image, by inverting the simplified Koschmieder light transmission model, as for outdoor dehazing. Our technique enhances image contrast in a quite effective manner and also supports accurate transmission map estimation. Our extensive experiments also show that our color correction strongly improves the effectiveness of local keypoints matching.