Showing papers on "Grayscale published in 2016"

Colorful Image Colorization

Abstract: Given a grayscale photograph as input, this paper attacks the problem of hallucinating a plausible color version of the photograph. This problem is clearly underconstrained, so previous approaches have either relied on significant user interaction or resulted in desaturated colorizations. We propose a fully automatic approach that produces vibrant and realistic colorizations. We embrace the underlying uncertainty of the problem by posing it as a classification task and use class-rebalancing at training time to increase the diversity of colors in the result. The system is implemented as a feed-forward pass in a CNN at test time and is trained on over a million color images. We evaluate our algorithm using a “colorization Turing test,” asking human participants to choose between a generated and ground truth color image. Our method successfully fools humans on 32 % of the trials, significantly higher than previous methods. Moreover, we show that colorization can be a powerful pretext task for self-supervised feature learning, acting as a cross-channel encoder. This approach results in state-of-the-art performance on several feature learning benchmarks.

Colorful Image Colorization

Abstract: Given a grayscale photograph as input, this paper attacks the problem of hallucinating a plausible color version of the photograph. This problem is clearly underconstrained, so previous approaches have either relied on significant user interaction or resulted in desaturated colorizations. We propose a fully automatic approach that produces vibrant and realistic colorizations. We embrace the underlying uncertainty of the problem by posing it as a classification task and use class-rebalancing at training time to increase the diversity of colors in the result. The system is implemented as a feed-forward pass in a CNN at test time and is trained on over a million color images. We evaluate our algorithm using a "colorization Turing test," asking human participants to choose between a generated and ground truth color image. Our method successfully fools humans on 32% of the trials, significantly higher than previous methods. Moreover, we show that colorization can be a powerful pretext task for self-supervised feature learning, acting as a cross-channel encoder. This approach results in state-of-the-art performance on several feature learning benchmarks.

Let there be color!: joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification

Abstract: We present a novel technique to automatically colorize grayscale images that combines both global priors and local image features. Based on Convolutional Neural Networks, our deep network features a fusion layer that allows us to elegantly merge local information dependent on small image patches with global priors computed using the entire image. The entire framework, including the global and local priors as well as the colorization model, is trained in an end-to-end fashion. Furthermore, our architecture can process images of any resolution, unlike most existing approaches based on CNN. We leverage an existing large-scale scene classification database to train our model, exploiting the class labels of the dataset to more efficiently and discriminatively learn the global priors. We validate our approach with a user study and compare against the state of the art, where we show significant improvements. Furthermore, we demonstrate our method extensively on many different types of images, including black-and-white photography from over a hundred years ago, and show realistic colorizations.

Real-Time 3D Reconstruction and 6-DoF Tracking with an Event Camera

Abstract: We propose a method which can perform real-time 3D reconstruction from a single hand-held event camera with no additional sensing, and works in unstructured scenes of which it has no prior knowledge. It is based on three decoupled probabilistic filters, each estimating 6-DoF camera motion, scene logarithmic (log) intensity gradient and scene inverse depth relative to a keyframe, and we build a real-time graph of these to track and model over an extended local workspace. We also upgrade the gradient estimate for each keyframe into an intensity image, allowing us to recover a real-time video-like intensity sequence with spatial and temporal super-resolution from the low bit-rate input event stream. To the best of our knowledge, this is the first algorithm provably able to track a general 6D motion along with reconstruction of arbitrary structure including its intensity and the reconstruction of grayscale video that exclusively relies on event camera data.

Scribbler: Controlling Deep Image Synthesis with Sketch and Color

Abstract: Recently, there have been several promising methods to generate realistic imagery from deep convolutional networks. These methods sidestep the traditional computer graphics rendering pipeline and instead generate imagery at the pixel level by learning from large collections of photos (e.g. faces or bedrooms). However, these methods are of limited utility because it is difficult for a user to control what the network produces. In this paper, we propose a deep adversarial image synthesis architecture that is conditioned on sketched boundaries and sparse color strokes to generate realistic cars, bedrooms, or faces. We demonstrate a sketch based image synthesis system which allows users to 'scribble' over the sketch to indicate preferred color for objects. Our network can then generate convincing images that satisfy both the color and the sketch constraints of user. The network is feed-forward which allows users to see the effect of their edits in real time. We compare to recent work on sketch to image synthesis and show that our approach can generate more realistic, more diverse, and more controllable outputs. The architecture is also effective at user-guided colorization of grayscale images.

Deep Image Homography Estimation

Abstract: We present a deep convolutional neural network for estimating the relative homography between a pair of images. Our feed-forward network has 10 layers, takes two stacked grayscale images as input, and produces an 8 degree of freedom homography which can be used to map the pixels from the first image to the second. We present two convolutional neural network architectures for HomographyNet: a regression network which directly estimates the real-valued homography parameters, and a classification network which produces a distribution over quantized homographies. We use a 4-point homography parameterization which maps the four corners from one image into the second image. Our networks are trained in an end-to-end fashion using warped MS-COCO images. Our approach works without the need for separate local feature detection and transformation estimation stages. Our deep models are compared to a traditional homography estimator based on ORB features and we highlight the scenarios where HomographyNet outperforms the traditional technique. We also describe a variety of applications powered by deep homography estimation, thus showcasing the flexibility of a deep learning approach.

Grayscale transparent metasurface holograms

Abstract: We demonstrate transparent metaholograms based on silicon metasurfaces that allow high-resolution grayscale images to be encoded. The holograms feature the highest diffraction and transmission efficiencies, and operate over a broad spectral range.

Learning Collaborative Sparse Representation for Grayscale-Thermal Tracking

Abstract: Integrating multiple different yet complementary feature representations has been proved to be an effective way for boosting tracking performance. This paper investigates how to perform robust object tracking in challenging scenarios by adaptively incorporating information from grayscale and thermal videos, and proposes a novel collaborative algorithm for online tracking. In particular, an adaptive fusion scheme is proposed based on collaborative sparse representation in Bayesian filtering framework. We jointly optimize sparse codes and the reliable weights of different modalities in an online way. In addition, this paper contributes a comprehensive video benchmark, which includes 50 grayscale-thermal sequences and their ground truth annotations for tracking purpose. The videos are with high diversity and the annotations were finished by one single person to guarantee consistency. Extensive experiments against other state-of-the-art trackers with both grayscale and grayscale-thermal inputs demonstrate the effectiveness of the proposed tracking approach. Through analyzing quantitative results, we also provide basic insights and potential future research directions in grayscale-thermal tracking.

Pairwise Decomposition of Image Sequences for Active Multi-view Recognition

Abstract: A multi-view image sequence provides a much richer capacity for object recognition than from a single image. However, most existing solutions to multi-view recognition typically adopt hand-crafted, model-based geometric methods, which do not readily embrace recent trends in deep learning. We propose to bring Convolutional Neural Networks to generic multi-view recognition, by decomposing an image sequence into a set of image pairs, classifying each pair independently, and then learning an object classifier by weighting the contribution of each pair. This allows for recognition over arbitrary camera trajectories, without requiring explicit training over the potentially infinite number of camera paths and lengths. Building these pairwise relationships then naturally extends to the next-best-view problem in an active recognition framework. To achieve this, we train a second Convolutional Neural Network to map directly from an observed image to next viewpoint. Finally, we incorporate this into a trajectory optimisation task, whereby the best recognition confidence is sought for a given trajectory length. We present state-of-the-art results in both guided and unguided multi-view recognition on the ModelNet dataset, and show how our method can be used with depth images, greyscale images, or both.

Non-Local Color Image Denoising with Convolutional Neural Networks

Abstract: We propose a novel deep network architecture for grayscale and color image denoising that is based on a non-local image model. Our motivation for the overall design of the proposed network stems from variational methods that exploit the inherent non-local self-similarity property of natural images. We build on this concept and introduce deep networks that perform non-local processing and at the same time they significantly benefit from discriminative learning. Experiments on the Berkeley segmentation dataset, comparing several state-of-the-art methods, show that the proposed non-local models achieve the best reported denoising performance both for grayscale and color images for all the tested noise levels. It is also worth noting that this increase in performance comes at no extra cost on the capacity of the network compared to existing alternative deep network architectures. In addition, we highlight a direct link of the proposed non-local models to convolutional neural networks. This connection is of significant importance since it allows our models to take full advantage of the latest advances on GPU computing in deep learning and makes them amenable to efficient implementations through their inherent parallelism.

Infrared small-target detection using multiscale gray difference weighted image entropy

Abstract: We propose an effective small-target detection approach based on weighted image entropy. The approach weights the local entropy measure by the multiscale grayscale difference followed by an adaptive threshold operation, which aims to improve the signal-to-noise ratio for cases in which jamming objects in the scene have similar thermal intensity measure with respect to the background as small target. The detection capability of the proposed approach has been validated on six real sequences, and the results demonstrate its significance and improvement.

Multi-Exposure and Multi-Focus Image Fusion in Gradient Domain

Abstract: A multi-exposure and multi-focus image fusion algorithm is proposed. The algorithm is developed for color images and is based on blending the gradients of the luminance components of the input images using the maximum gradient magnitude at each pixel location and then obtaining the fused luminance using a Haar wavelet-based image reconstruction technique. This image reconstruction algorithm is of O(N) complexity and includes a Poisson solver at each resolution to eliminate artifacts that may appear due to the nonconservative nature of the resulting gradient. The fused chrominance, on the other hand, is obtained as a weighted mean of the chrominance channels. The particular case of grayscale images is treated as luminance fusion. Experimental results and comparison with other fusion techniques indicate that the proposed algorithm is fast and produces similar or better results than existing techniques for both multi-exposure as well as multi-focus images.

Quaternion Collaborative and Sparse Representation With Application to Color Face Recognition

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.

Robust Texture Image Representation by Scale Selective Local Binary Patterns

Abstract: Local binary pattern (LBP) has successfully been used in computer vision and pattern recognition applications, such as texture recognition. It could effectively address grayscale and rotation variation. However, it failed to get desirable performance for texture classification with scale transformation. In this paper, a new method based on dominant LBP in scale space is proposed to address scale variation for texture classification. First, a scale space of a texture image is derived by a Gaussian filter. Then, a histogram of pre-learned dominant LBPs is built for each image in the scale space. Finally, for each pattern, the maximal frequency among different scales is considered as the scale invariant feature. Extensive experiments on five public texture databases (University of Illinois at Urbana-Champaign, Columbia Utrecht Database, Kungliga Tekniska Hogskolan-Textures under varying Illumination, Pose and Scale, University of Maryland, and Amsterdam Library of Textures) validate the efficiency of the proposed feature extraction scheme. Coupled with the nearest subspace classifier, the proposed method could yield competitive results, which are 99.36%, 99.51%, 99.39%, 99.46%, and 99.71% for UIUC, CUReT, KTH-TIPS, UMD, and ALOT, respectively. Meanwhile, the proposed method inherits simple and efficient merits of LBP, for example, it could extract scale-robust feature for a $200\times 200$ image within 0.24 s, which is applicable for many real-time applications.

Deep Colorization

Abstract: This paper investigates into the colorization problem which converts a grayscale image to a colorful version. This is a very difficult problem and normally requires manual adjustment to achieve artifact-free quality. For instance, it normally requires human-labelled color scribbles on the grayscale target image or a careful selection of colorful reference images (e.g., capturing the same scene in the grayscale target image). Unlike the previous methods, this paper aims at a high-quality fully-automatic colorization method. With the assumption of a perfect patch matching technique, the use of an extremely large-scale reference database (that contains sufficient color images) is the most reliable solution to the colorization problem. However, patch matching noise will increase with respect to the size of the reference database in practice. Inspired by the recent success in deep learning techniques which provide amazing modeling of large-scale data, this paper re-formulates the colorization problem so that deep learning techniques can be directly employed. To ensure artifact-free quality, a joint bilateral filtering based post-processing step is proposed. We further develop an adaptive image clustering technique to incorporate the global image information. Numerous experiments demonstrate that our method outperforms the state-of-art algorithms both in terms of quality and speed.

Infrared Colorization Using Deep Convolutional Neural Networks

Abstract: This paper proposes a method for transferring the RGB color spectrum to near-infrared (NIR) images using deep multi-scale convolutional neural networks. A direct and integrated transfer between NIR and RGB pixels is trained. The trained model does not require any user guidance or a reference image database in the recall phase to produce images with a natural appearance. To preserve the rich details of the NIR image, its high frequency features are transferred to the estimated RGB image. The presented approach is trained and evaluated on a real-world dataset containing a large amount of road scene images in summer. The dataset was captured by a multi-CCD NIR/RGB camera, which ensures a perfect pixel to pixel registration.

Cascades of Regression Tree Fields for Image Restoration

Abstract: Conditional random fields (CRFs) are popular discriminative models for computer vision and have been successfully applied in the domain of image restoration, especially to image denoising. For image deblurring, however, discriminative approaches have been mostly lacking. We posit two reasons for this: First, the blur kernel is often only known at test time, requiring any discriminative approach to cope with considerable variability. Second, given this variability it is quite difficult to construct suitable features for discriminative prediction. To address these challenges we first show a connection between common half-quadratic inference for generative image priors and Gaussian CRFs. Based on this analysis, we then propose a cascade model for image restoration that consists of a Gaussian CRF at each stage. Each stage of our cascade is semi-parametric, i.e., it depends on the instance-specific parameters of the restoration problem, such as the blur kernel. We train our model by loss minimization with synthetically generated training data. Our experiments show that when applied to non-blind image deblurring, the proposed approach is efficient and yields state-of-the-art restoration quality on images corrupted with synthetic and real blur. Moreover, we demonstrate its suitability for image denoising, where we achieve competitive results for grayscale and color images.

Feature detection and tracking with the dynamic and active-pixel vision sensor (DAVIS)

Abstract: Because standard cameras sample the scene at constant time intervals, they do not provide any information in the blind time between subsequent frames. However, for many high-speed robotic and vision applications, it is crucial to provide high-frequency measurement updates also during this blind time. This can be achieved using a novel vision sensor, called DAVIS, which combines a standard camera and an asynchronous event-based sensor in the same pixel array. The DAVIS encodes the visual content between two subsequent frames by an asynchronous stream of events that convey pixel-level brightness changes at microsecond resolution. We present the first algorithm to detect and track visual features using both the frames and the event data provided by the DAVIS. Features are first detected in the grayscale frames and then tracked asynchronously in the blind time between frames using the stream of events. To best take into account the hybrid characteristics of the DAVIS, features are built based on large, spatial contrast variations (i.e., visual edges), which are the source of most of the events generated by the sensor. An event-based algorithm is further presented to track the features using an iterative, geometric registration approach. The performance of the proposed method is evaluated on real data acquired by the DAVIS.

A Novel LSB Based Quantum Watermarking

Abstract: Quantum watermarking is a technique which embeds the invisible quantum signal such as the owners identification into quantum multimedia data (such as audio, video and image) for copyright protection. In this paper, using a quantum representation of digital images a new quantum watermarking protocol including quantum image scrambling based on Least Significant Bit (LSB) is proposed. In this protocol, by using m-bit embedding key K 1 and m-bit extracting key K 2 a m-pixel gray scale image is watermarked in a m-pixel carrier image by the original owner of the carrier image. For validation of the presented scheme the peak-signal-to-noise ratio (PSNR) and histogram graphs of the images are analyzed.

Implementation of RGB and Grayscale Images in Plant Leaves Disease Detection - Comparative Study

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.

Image encryption scheme using chaos and simulated annealing algorithm

Abstract: In this paper, we proposed a novel image encryption scheme based on chaos and simulated annealing algorithm. The proposed algorithm considers the generation of random sequence as a problem seeking for optimal solution and then uses the simulated annealing algorithm to further obtain the optimal pseudorandom sequences. Chaos has been combined together with it for the confusion and diffusion. The target objects to be processed of this article are general grayscale images with no other restrictions. Many tests have been done to check the effect against a variety of attacks, and results of experiments and analysis present that the proposed algorithm has good feature of security. It is able to resist common attacks. So our scheme is secure enough for image encryption.

Medical image protection using genetic algorithm operations

Abstract: The security of digital medical images has attracted much attention recently, especially when these images are sent through the communication networks. An image encryption technique tries to convert an image to another image that is hard to understand. In this communication, we propose an encryption method for gray scale medical images based on the features of genetic algorithms. Performance analysis show that the proposed scheme has good statistical character, key sensitivity and can resist brute-force attack, differential attack, plaintext attack and entropy attack efficiently.

Image Multithresholding based on Kapur/Tsallis Entropy and Firefly Algorithm

Abstract: Background/Objectives: In this paper, Firefly Algorithm (FA) based multilevel thresholding is proposed to segment the gray scale image by maximizing the entropy value. Methods/Statistical analysis: Better segmentation method gives appropriate threshold values to enhance the region of interest in the digital image. The entropy based methods, such as Kapur’s and Tsallis functions are chosen in this paper to segment the image. This work is implemented using the gray scale images obtained from Berkeley segmentation dataset. The FA assisted segmentation with entropy function is confirmed using the universal image superiority measures existing in the literature.Findings: Results of this simulation work show that Tsallis function offers better performance measure values, whereas the Kapur’s approach offers earlier convergence with comparatively lower CPU time. Applications/Improvements: Proposed method can be tested using other recent heuristic methods existing in the literature.

Single-shot absolute 3D shape measurement with Fourier transform profilometry

Abstract: Fourier transform profilometry (FTP) is one of the frequently adopted three-dimensional (3D) shape measurement methods due to its ability to recover single-shot 3D shapes, yet it is challenging to retrieve the absolute phase map solely from one single grayscale fringe image. This paper presents a computational framework that overcomes this limitation of FTP with digital fringe projection (DFP). By using geometric constraints, an absolute phase map can be retrieved point-by-point from one single grayscale fringe image. Experiments demonstrate the success of our proposed framework with single-shot absolute 3D shape measurement capability.

Still image/video frame lossy compression providing a desired visual quality

Abstract: The problem of how to automatically provide a desired (required) visual quality in lossy compression of still images and video frames is considered in this paper. The quality can be measured based on different conventional and visual quality metrics. In this paper, we mainly employ human visual system (HVS) based metrics PSNR-HVS-M and MSSIM since both of them take into account several important peculiarities of HVS. To provide a desired visual quality with high accuracy, iterative image compression procedures are proposed and analyzed. An experimental study is performed for a large number of grayscale test images. We demonstrate that there exist several coders for which the number of iterations can be essentially decreased using a reasonable selection of the starting value and the variation interval for the parameter controlling compression (PCC). PCC values attained at the end of the iterative procedure may heavily depend upon the coder used and the complexity of the image. Similarly, the compression ratio also considerably depends on the above factors. We show that for some modern coders that take HVS into consideration it is possible to give practical recommendations on setting a fixed PCC to provide a desired visual quality in a non-iterative manner. The case when original images are corrupted by visible noise is also briefly studied.