Search

In the field of real-time image enhancement, image super-resolution (SR) is an important research hotspot. As an image super-resolution method, deep learning can extract more stable and higher level features. However, image super-resolution processing is an ill posed problem. Due to the lack of self-attentional negative feedback mechanism, the existing methods can not better constrain the mapping space from low-resolution image to high-resolution image, so generated high-resolution (HR) image does not conform to human visual perception. Therefore, this paper proposes a self-attention negative feedback network (SRAFBN) for realizing the real-time image SR. The network model constrains the image mapping space and selects the key information of the image through the self-attention negative feedback model, so that higher quality images can be generated to meet human visual perception. Specifically, a Recurrent Neural Network (RNN) is firstly utilized to construct multiple negative feedback modules, and each module generates a HR image. Then, the key information of the generated image is extracted by the self-attention mechanism. Finally, the extracted information is fused to generate the final HR image. Experimental results prove the proposed SRAFBN network model not only has higher PSNR and SSIM, but also can reconstruct more realistic and clear real-time images.

Geohazard recognition and inventory mapping are absolutely the keys to the establishment of reliable susceptibility and hazard maps. However, it has been challenging to implement geohazards recognition and inventory mapping in mountainous areas with complex topography and vegetation cover. Progress in the light detection and ranging (LiDAR) technology provides a new possibility for geohazard recognition in such areas. Specifically, this study aims to evaluate the performances of the LiDAR technology in recognizing geohazard in the mountainous areas of Southwest China through visually analyzing airborne LiDAR DEM derivatives. Quasi-3D relief image maps are generated based on the sky-view factor (SVF), which makes it feasible to interpret precisely the features of geohazard. A total of 146 geohazards are remotely mapped in the entire 135 km2 study area in Danba County, Southwest China, and classified as landslide, rock fall, debris flow based on morphologic characteristics interpreted from SVF visualization maps. Field validation indicate the success rate of LiDAR-derived DEM in recognition and mapping geohazard with higher precision and accuracy. These mapped geohazards lie along both sides of the river, and their spatial distributions are related highly to human engineering activities, such as road excavation and slope cutting. The minimum geohazard that can be recognized in the 0.5 m resolution DEM is about 900 m2. Meanwhile, the SVF visualization method is demonstrated to be a great alternative to the classical hillshaded DEM method when it comes to the determination of geomorphological properties of geohazard. Results of this study highlight the importance of LiDAR data for creating complete and accurate geohazard inventories, which can then be used for the production of reliable susceptibility and hazard maps and thus contribute to a better understanding of the movement processes and reducing related losses.

Purpose: In order to analyze the images to be produced by tone variations in the smoky makeup, according to the forms of eyes, this study evaluated them by applying adjective image scales as the tool for quantitative assessment.Methods: By categorizing female eyes into seven forms, we examined images in which the tones of smoky makeup changed across five stages, ranging from the highest to the lowest brightness. We varied the positions of the eyes on the image map.Results: The eyes without makeup have different images, depending on the forms of eyes: standard eyes with folded eyelids and large eyes have dynamic and soft images, while drooping eyes have static and stiff images. The positions of eyes were varied on the image map. Although the standard eyes which were evaluated as having the most soft images could express very various images, by changing the tones of the smoky makeup, those which could be expressed by drooping eyes were very restricted, even though the tones of the smoky makeup were changed.Conclusion: It is consequently found that there are large variations in image areas to be produced by makeup, and that the image map is a tool useful for systematically analyzing the dynamic characteristics of variations in eyes’ images, as the tones of makeup are changed.

Rainy weather greatly affects the visibility of salient objects and scenes in the captured images and videos. The object/scene visibility varies with the type of raindrops, i.e. adherent rain droplets, streaks, rain, mist, etc. Moreover, they pose multifaceted challenges to detect and remove the raindrops to reconstruct the rain-free image for higher-level tasks like object detection, road segmentation etc. Recently, both Convolutional Neural Networks (CNN) and Generative Adversarial Network (GAN) based models have been designed to remove rain droplets from a single image by dealing with it as an image to image mapping problem. However, most of them fail to capture the complexities of the task, create blurry output, or are not time efficient. GANs are a prime candidate for solving this problem as they are extremely effective in learning image maps without harsh overfitting. In this paper, we design a simple yet effective ‘DerainGAN’ framework to achieve improved deraining performance over the existing state-of-the-art methods. The learning is based on a Wasserstein GAN and perceptual loss incorporated into the architecture. We empirically analyze the effect of different parameter choices to train the model for better optimization. We also identify the strengths and limitations of various components for single image deraining by performing multiple ablation studies on our model. The robustness of the proposed method is evaluated over two synthetic and one real-world rainy image datasets using Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) values. The proposed DerainGAN significantly outperforms almost all state-of-the-art models in Rain100L and Rain700 datasets, both in semantic and visual appearance, achieving SSIM of 0.8201 and PSNR 24.15 in Rain700 and SSIM of 0.8701 and PSNR of 28.30 in Rain100L. This accounts for an average improvement of 10 percent in PSNR and 20 percent in SSIM over benchmarked methods. Moreover, the DerainGAN is one of the fastest methods in terms of time taken to process the image, giving it over 0.1 to 150 seconds of advantage in some cases.

An image-map is a compromise between an image and a map. The quality of such maps is affected by several factors, such as (a) the matching between the features on images and the graphic symbols fro...

Image authentication based on image hashing has gained large attention in recent years. However, limited work has been done in color image hashing. Also, most of the existing methods are unable to detect tampering, if the composite rotation–scaling–translation (RST) distortion and tampering in a color image occur simultaneously. In this paper, an image hashing technique has been proposed based on convolutional stacked denoising auto-encoders (CSDAEs). In addition, a blind geometric correction approach is used to correct the composite RST distortion in the image. An input image is hierarchically mapped to a lower-dimensional hash code via CSDAEs, which have been trained for content-preserving operations (CPOs). An image map is generated from the hash via the decoder. The tampered area has been localized, by comparing the image map of hash codes from the reference image and the received image. The experimental results show that the proposed method is robust against most of the CPOs, especially to composite RST, a better trade-off between robustness and discrimination, and can localize the tampered regions. The receiver operating characteristics show that the proposed model is better than some of the state-of-the-art methods.

UAV aerial remote sensing system has the characteristics of strong real-time, flexible, high image resolution and low cost, which can be applied to map mapping tasks under various terrain. In this paper, the key technology of UAV Remote Sensing Surveying and mapping, the process of image processing, the research of mosaic method and the field application of remote sensing technology are studied. Aiming at the characteristics of UAV image with high resolution and small image frame, three methods of image map making are proposed, namely, single image geometric correction method, mosaic correction method and aerial triangulation method. This paper focuses on the key technical problems of the three methods, and makes a comprehensive analysis and experimental verification of each method from the aspects of mapping effect, accuracy and efficiency. The experimental results show that the UAV remote sensing technology can meet the real-time basic surveying and mapping data requirements of urban mapping. This method can meet the needs of 1:500 high-precision mapping. The system can reduce the cost and improve the usability when it is used to update the basic data of Urban Surveying and mapping.

This study aims to develop and evaluate a new computer-aided diagnosis (CADx) scheme based on analysis of global mammographic image features to predict likelihood of cases being malignant. An image dataset involving 1,959 cases was retrospectively assembled. Suspicious lesions were detected and biopsied in each case. Among them, 737 cases are malignant and 1,222 are benign. Each case includes four mammograms of craniocaudal and mediolateral oblique view of left and right breasts. CADx scheme is applied to pre-process mammograms, generate two image maps in frequency domain using discrete cosine transform and fast Fourier transform, compute bilateral image feature differences from left and right breasts, and apply a support vector machine (SVM) to predict likelihood of the case being malignant. Three sub-groups of image features were computed from the original mammograms and two transformation maps. Four SVMs using three sub-groups of image features and fusion of all features were trained and tested using a 10-fold cross-validation method. The computed areas under receiver operating characteristic curves (AUCs) range from 0.85 to 0.91 using image features computed from one of three sub-groups, respectively. By fusion of all image features computed in three sub-groups, the fourth SVM yields a significantly higher performance with AUC = 0.96±0.01 (p

China's first Mars exploration mission will carry out comprehensive global surveys of the planet from data collected by instruments carried in orbit and roving on the planet itself. Goals of the mission include detailed inspections and surveys of key areas on the surface of Mars. One of the main scientific payloads installed on the orbiter is the moderate resolution camera. Its mission is to image the surface of Mars sufficiently to produce a global remote sensing image map of the planet, and to explore and record changes to the topography of Mars, including major geological structures, and to advance research on topography and geomorphology in general. The moderate resolution camera uses a lightweight and compact integrated design; its primary components are an optical module, a focal plane module, a camera control module, a power and interface module, a camera support module, a thermal control module, and a reference module. Radiometric calibration, color calibration, and geometric calibration have been carried out to ensure that the camera can acquire sufficient accurate data to complete mission goals. This paper introduces the camera's detection mission, its system composition, and its working principle; it also describes the camera's ground calibration tests and their results, and provides a reference for processing the camera's scientific data and for future applications.

The use of magnetic resonance imaging (MRI) for radiotherapy treatment planning (RTP) is increasing due to excellent tissue contrast and high-resolution images compared to other modalities. However, the issue of image inhomogeneity which affects tissue delineation and contrast during treatment planning needs to be resolved. This study is aimed to qualitatively observe image inhomogeneity in T2-weighted images and T2 measurement using head phantom. Agar hydrogel phantom of various concentrations were used to form inhomogeneous phantom for mimicking tissue variation in the brain in addition to American College of Radiology accredited phantom. T2 images from both phantoms were obtained using fast spin echo sequence with variation of echo time (TE) and repetition time. Image processing was processed to obtain signal intensity and image mapping and the effect of inhomogeneity was observed qualitatively. T2 values were obtained by fitting signal intensity against TE and T2-mapping images were obtained. T2-weighted and T2-mapping images from the experiment provided qualitative description on image inhomogeneity and contrast. The result showed that T2-mapping images offered more information on phantom properties and described image inhomogeneity and contrast better than T2-weighted images. T2 measurement provided an alternative method for better description of image contrast which could enhance localization and tissue delineation in MRI-based RTP.

Here we present implementations snapshot–image reorganization/mapping techniques including IMS (Imaging Mapping Spectrometry), and high density fiber image processors. These instruments are compact, non-scanning / high speed and provide high light throughput. The general principle of these methods is based on mapping areas (pixel, lines) of the object/scene on a large format CCD/CMOS to create void regions for spectral spread and simultaneous 3D+ data acquisition. This allows for a rapid detection and/or for increased SNR. High light throughput allows imaging at ultra-short acquisitions (entire cubes) down to microsecond levels. Our newest implementations include gas detection, environmental imaging and compact UAV applications. This presentation describes advantages of IMS, and fiber based systems and compares them to other snapshot techniques (computational methods). Examples of remote sensing results are presented (vegetation/crops assessment).

There is a tradeoff between hash length and small area tampered localization based on the block-based analysis. In this paper, we have mitigated this issue using only global features. A compact image hash is constructed using LL band of Lifting Wavelet Transform (LWT) followed by Discrete Cosine Transform (DCT). An image map is reconstructed from the hash. Based on the difference of image map obtained from the received hash and received image, tampering regions have been localized. Experimented the blind geometric correction removes the influences of geometric distortion while tampering with localization. While decreasing the hash length, a very small area of tampered regions has been localized using the proposed approach. Due to the blind geometric correction, the proposed method can localize tampering, even if tampering and composite RST geometric transformations occur simultaneously. The experimental results reveal that the proposed technique can upgrade the tampering localization compared to both the block-based and existing global features based state-of-the-art methods.

Blind people can benefit greatly from a system capable of localising and reading comprehension text embedded in natural scenes and providing useful information that boosts their self-esteem and autonomy in everyday situations. Regardless of the fact that existing optical character recognition programmes seem to be quick and effective, the majority of them are not able to correctly recognise text embedded in usual panorama images. The methodology described in this paper is to localise textual image regions and pre-process them using the naïve Bayesian algorithm. A weighted reading technique is used to generate the correct text data from the complicated image regions. Usually, images hold some disturbance as a result of the fact that filtration is proposed during the early pre-processing step. To restore the image's quality, the input image is processed employing gradient and contrast image methods. Following that, the contrast of the source images would be enhanced using an adaptive image map. The stroke width transform, Gabor’s transform, and weighted naïve Bayesian classifier methodologies have been used in complicated degraded images to segment, feature extraction, and detect textual and non-textual elements. Finally, to identify categorised textual data, the confluence of deep neural networks and particle swarm optimisation is being used. The text in the image is transformed into an acoustic output after identification. The dataset IIIT5K is used for the development portion, and the performance of the suggested come up is evaluated using parameters such as accuracy, recall, precision, and F1-score.

This study developed an investigative learning support program that had two steps with multiple features including pillars of investigation for searching and grasping subjects of learning from multiple dimensions and then evaluated the goal achievement of the program. We examined literature and included reference materials and image maps, both with and without clues, and incorporated the tasks of revising or adding pillars of investigation in the program. Although there are some issues such as the consideration of instructions and prior support methods for students who have little experience in investigative learning, some students met the achievement goals of the program.

Single image deraining is an important yet challenging task due to the ill-posed nature of the problem to derive the rain-free clean image from a rainy image. In this paper, we propose Recurrent RLCN-Guided Attention Network (RRANet) for single image deraining. Our main technical contributions lie in threefold: (i) We propose rectified local contrast normalization (RLCN) to apply to the input rainy image to effectively mark candidates of rain regions. (ii) We propose RLCN-guided attention module (RLCN-GAM) to learn an effective attention map for the deraining without the necessity of ground-truth rain masks. (iii) We incorporate RLCN-GAM into a recurrent neural network to progressively derive the rainy-to-clean image mapping. The quantitative and qualitative evaluations using representative deraining benchmark datasets demonstrate that our proposed RRANet outperforms existing state-of-the-art deraining methods, where it is particularly noteworthy that our method clearly achieves the best performance on a realworld dataset.

Image quality manipulating in JPEG is done by quantization tables. JPEG has two quantization tables – one table for the luminance information and one table for the chrominance information. These quantization tables have been designed in support of images with few sharp changes; however, typically most GPS image maps have many sharp changes and as a result, the images are not optimally compressed. The designers of the quantization tables have presumed that sharp changes in the colors will rarely occur. Therefore, they divide the values that represent sharp changes in the frequency space by large numbers and divide other values by smaller numbers. As a result, when there are sharp changes in an image, the proportional allocation for each kind of data in the compressed image is inappropriate and results in an inefficient compression. In this paper the standard quantization tables have been modified as to handle the different kinds of GPS image map data appropriately. Consequently, the experimental results show that images with sharp changes are compressed more efficiently when making use of the new quantization tables.

With the progression of picture archiving and communication systems (PACSs) over the past decade, it has become imperative that such systems be optimised in security, storage, and transmission aspects. The work presented in this Letter shows a framework for medical image compression and secure image transmission for PACSs. The work aims to achieve a lower dimensionality of input medical image signified by a high-compression ratio, a secure image transmission that can withstand adversarial attacks and provide a reversible reconstruction with minimal error. The authors illustrate that sinusoid modulated Gaussian texture maps, multi-level chaotic maps, and high-frequency image maps can be efficiently fused and utilised in a deep learning architecture. The overall analysis depicts promising results with regard to the capability of image compression, security, and transmission. The proposed framework will be a potential candidate for use in PACSs, which effectively is the backbone of the current healthcare paradigm.

The semiconductor industry has become fully automated during the manufacturing process and abundant process parameters are collected online by sensors for fault detection and classification purposes. Analyzing process parameters and identifying a smaller set of key parameters that have crucial influence on wafer quality will bring great benefits in stabilizing the manufacturing process and enhancing productive yield. Typically, this type of the parameter set is called the “raw trace data.” This paper considers image processing techniques as a novel approach for analyzing and visualizing the raw trace data. First, the 1-D time series data of a wafer batch was transformed into a 2-D image. Fisher’s criterion ratios of the labeled good and defective wafer image maps are computed to identify the key parameters. The key parameters identified by the proposed image processing technique are consistent with the technical experience of the process engineers. Furthermore, the texture analysis technique with 2-D Fourier transform is utilized to analyze the images of the key parameters to detect defective wafers. The proposed key parameter identification and wafer classification method proves to be a viable solution under the paradigm of advanced process control practice for semiconductor manufacturing.

In applications of deep reinforcement learning to robotics, it is often the case that we want to learn pose invariant policies: policies that are invariant to changes in the position and orientation of objects in the world. For example, consider a pegin-hole insertion task. If the agent learns to insert a peg into one hole, we would like that policy to generalize to holes presented in different poses. Unfortunately, this is a challenge using conventional methods. This paper proposes a novel state and action abstraction that is invariant to pose shifts called deictic image maps that can be used with deep reinforcement learning. We provide broad conditions under which optimal abstract policies are optimal for the underlying system. Finally, we show that the method can help solve challenging robotic manipulation problems.

Image maps are a popular cartographic product, as the synthesis of remote sensing imagery with cartographic symbols gives the map an authentic look and feel. Traditionally, the design of im...

This paper describes the procedure for creating tactile interfaces for Android smart phones. It uses the HTML5 Vibration API and the Javascript programming language to create vibration patterns in order to increase the interaction between visually impaired people with their smart phones. Apart from vision, audio and haptics are used to maximize the Human – Computer Interaction between the Android phones and users with visual impairments. Three methods are proposed for the creation of tactile interfaces in smart phones, one is with the use of the HTML image map tag, and the other with the Mask R-CNN Artificial Intelligence algorithm. The Mean Opinion Score procedure is used in order to evaluate the proposed vibration patterns for Human - Computer Interaction Techniques.

In this computing era, data are represented as images that are to be processed for retrieval. Need for high accuracy in retrieval made this area more challenging. Content Based Image Retrieval system uses features of query image with that of an existing database image set for retrieval using precision and recall ratio. Features of images include color, shape, texture, etc. Techniques for retrieval include histogram, wavelength transformation, statistical methods, Euclidean distance, etc. Color feature though forms the fundamental image feature for retrieval techniques, other features are also considered to be more important and necessary as they play vital role in retrieval process. Many programs and tools have been developed to formulate and execute queries. CBIR researchers need to improve precision rate (accuracy), that lead to variation of search ranges and search object increment. This in turn brought about the combination of two or more features for efficient retrieval. Together with features, today’s research is highly concentrated on image set with large varied databases, documents of differing sorts and with varying characteristics that have high social implications. The image set can be motion or motionless. Earlier research concentrated on motionless images in CBIR while motion images are also considered in recent years. This paper presents the literature survey on recent medical image retrieval techniques.

This paper presents a novel snapshot imaging spectrometer based on the image mapping and compressed sensing concept named Compressed Sensing Image Mapping Spectrometer (CSIMS). The operation principle is to slice the input image to different directions and encode the strip pieces before dispersion by a prism. The detector obtains the mixture spatial-spectral data simultaneously. The datacube is reconstructed by the compressed sensing algorithm and combining all the pieces together. The mathematical model of CSIMS is established to describe the light wave propagation through the entire system based on the scalar diffraction theory. The simulations are conducted to prove the effectiveness of the CSIMS principle, and the results show that the reconstructed datacube reveals higher spatial resolution and more accurate spectral curves than that of the relative snapshot imaging spectrometer based on compressed sensing.

Minimizing costs and increasing sales are a goal for every busi- ness nowadays. This fact, together with the development of new technologies, have driven the emergence of virtual applications where the customers can configure the product they are interested in only interacting with the images where the products appear. Many applications are available on Internet or app stores for this purpose. In all of them, a high realism is required. However, this fact is directly related to a high cost of storage of data and to the difficulty of generating the images of the scenes where the product is exposed. This paper presents a virtual configurator addressed to tile factories that solves these problems maintaining a high realism. The developed application generates the configurable images by rendering 3D modeled environments and the customization is performed taking advantage of the graphics hardware. It is in charge of performing the tiling of any size tiles in real time. The presented image mapping system is based on the real measurements of the walls or floor of the environment that appear in the image and on the dimensions of the tile to map. Taking these data into account, the application performs the final appearance adapting the final image to the requirements of the user. The presented method reduces the amount of stored information maintaining the realism of the customized images.

Photography is the activity of recording precious moments which are often difficult to make up afterwards. Therefore, taking the correct picture under proper guidance assistance is important. Although there are many factors that can determine a good photo, in general, photos that do not follow the composition rules usually look bad that make the viewer feel uncomfortable. Acting as a solution, in this paper, we propose an intelligent photographing guidance system using machine learning. The guidance is based on a tree-based interpretable machine learning model that can give reasons for decisions. There are two categories of features for guidance, which are traditional image features and deep features. Traditional features include prominent lines and image maps, such as saliency map and sharpness map, each of which exists in a multi-scale Gaussian pyramid. Deep features are extracted during the establishment of a CNN-based image composition classifier. We use these two categories of features as inputs for the interpretable machine learning model to establish a feasible photographing guidance system. The guidance system references our composition classifier with precision rate of 94.8%, and recall rate of 95.0% where the comprising tree-based interpretable model is capable of guiding camera users to alter image contents for obtaining better aesthetical compositions to take photos of good quality.

Machine vision helps a lot with the latest recognition technology. To get the best recognition results, the initial phase of image processing should be done as best as possible. This phase involves the production of an image map of the resulting image using edge detection. The Canny method is often used because of its performance of producing meticulous strong edges but this method is sensitive to changes in image intensity when involving complex images such as image leaves and results in a lot of noise at the edges of the resulting image. This is because in this method the threshold value is selected empirically on the image globally. In this study, local image analysis will be discussed along with its impact on the resulting image edge results. In addition, a set of data from herbal leaves in Malaysia has also been produced by containing ground truth images for each herbal image available. The results from this study found that the locally analysing image approach has outperform the global approach of the conventional Canny method. Findings from this study may help the identification system in the future.

The article recommended a new application on teaching—a project base learning by graphic interchange format (GIF) based on data of geographic information system (GIS). Teachers and students implemented the project researching the status of air pollution at high schools in Hanoi, one of the urgent problems in recent times in Hanoi, Vietnam. The air pollution at high schools was shown by collecting data of polluted index (AQI) of the United State of Environmental Protection Agency (EPA) from December 5th to 22nd 2019 in some schools in Hanoi. By integrating ArcGIS Desktop and GIF, the static and dynamic image map of the status of air pollution was built for assessing levels of pollution following spatial distribution. The project was not only a new application of ArcGIS Desktop and GIF on learning but also alerting about pollution issues impacting the health of students and teachers in high schools. It is an essential issue for proposing mitigation and adaptive solutions for educational managers.

Finding a template patch in a target image, including object detection and tracking, is a core component in computer vision applications. This paper introduces a fast and robust image matching based on depth-wise convolution features and unique nearest neighbour similarity. Experiments with its results show that our algorithm can effectively solve the problem of image mapping with complex deformation, and the matching performance is better than the existing optimal feature matching algorithms by improving the matching accuracy about 10.68%.

Image filtering is a technique that can create additional visual representations of the original image. Entropy filtering is a specific application that can be used to highlight randomness of pixel grayscale intensities within an image. These image map created from filtering are based on the number of surrounding neighbourhood of pixels considered. However, there is no standard procedure for determining the correct "neighbourhood size" to use. We investigated the effects of neighbourhood size on the entropy calculation and provide a standardized approach for determining an appropriate neighbourhood size in entropy filtering in a musculoskeletal application. Ten healthy subjects showing no symptoms related to neuromuscular disease were recruited and ultrasound images of their trapezius muscle were acquired. The muscle regions in the images were manually isolated and regions of interest with varying neighbourhood sizes (increasing by 2 pixels) from 3x3 to 61X61 pixels were extracted. The entropy, relative signal entropy over noise entropy, statistical effect size as well as the percentage change of the effect size and instantaneous slope of the effect size was examined. The analysis showed that a neighbourhood size within the range of 21-25 pixels provides the maximum amount of information gained and coincides with a percentage change of the effect size of less than 5% and instantaneous slopes < 0.05.

An image mapping spectrometer (IMS) is a snapshot hyperspectral imager that simultaneously captures both the spatial ( x , y ) and spectral ( λ ) information of incoming light. The IMS maps a three-dimensional (3D) datacube ( x , y , λ ) to a two-dimensional (2D) detector array ( x , y ) for parallel measurement. To reconstruct the original 3D datacube, one must construct a lookup table that connects voxels in the datacube and pixels in the raw image. Previous calibration methods suffer from either low speed or poor image quality. We herein present a slit-scan calibration method that can significantly reduce the calibration time while maintaining high accuracy. Moreover, we quantitatively analyzed the major artifact in the IMS, the striped image, and developed three numerical methods to correct for it.

Although existing image inpainting approaches have been able to produce visually realistic and semantically correct results, they produce only one result for each masked input. In order to produce multiple and diverse reasonable solutions, we present Unsupervised Cross-space Translation Generative Adversarial Network (called UCTGAN) which mainly consists of three network modules: conditional encoder module, manifold projection module and generation module. The manifold projection module and the generation module are combined to learn one-to-one image mapping between two spaces in an unsupervised way by projecting instance image space and conditional completion image space into common low-dimensional manifold space, which can greatly improve the diversity of the repaired samples. For understanding of global information, we also introduce a new cross semantic attention layer that exploits the long-range dependencies between the known parts and the completed parts, which can improve realism and appearance consistency of repaired samples. Extensive experiments on various datasets such as CelebA-HQ, Places2, Paris Street View and ImageNet clearly demonstrate that our method not only generates diverse inpainting solutions from the same image to be repaired, but also has high image quality.

Most existing dehazing methods are not robust to nonhomogeneous haze. Meanwhile, the information of dense haze region is usually unknown and hard to estimate, leading to blurry in dehaze result for those regions. Focusing on these two issues, we propose a novel coarse-to-fine model, namely Trident Dehazing Network (TDN), to learn the hazy to hazy- free image mapping with automatic haze density recognition. In detail, TDN is composed of three sub-nets: the Encoder-Decoder Net (EDN) is the main net of TDN to reconstruct the coarse hazy-free feature; the Detail Refinement sub-Net (DRN) helps to refine the high frequency details that was easily lost in the pooling layers in the encoder; and the Haze Density Map Generation sub-Net (HDMGN) can automatically distinguish the thick haze region with thin one, to prevent over-dehazing or under-dehazing in regions of different haze density. Moreover, we propose a frequency domain loss function to make supervision of different frequency band more uniform. Extensive experimental results on synthetic and real datasets demonstrate that our proposed TDN outperforms the state-of-the-arts with better fidelity and perceptual, generalizing well on both dense haze and nonhomogeneous haze scene. Our method won the first place in NTIRE2020 nonhomogeneous dehazing challenge.

We make an offer of a state-of-the-art method of the deep salient wood image-based quality assessment (DS-WIQA) for no-reference image appraisal. We explore a five-layer deep convolutional neural network (DCNN) for the salient wood image map. The DS-WIQA uses the concave n-square method. The outcomes allow that DS-WIQA model has a greater achievement on Zenodo and Lignoindo datasets, respectively. We appraise a salient wood image map by extracting in small wood image patches. The DS-WIQA has an admirable performance of other recent methods on Zenodo and Lignoindo datasets, respectively. DS-WIQA outdoes other recent techniques by 14.29% and 19.96% more advanced than other techniques with respect to SROCC and LCC measurement, respectively. DS-WIQA shows up to be more significant than the other DCNN methods.

3D scene reconstruction provides an improved representation from which features of critical objects or targets may be extracted. Both electro-optical (EO) and synthetic aperture radar (SAR) sensors have been exploited for this purpose, but each modality possesses issues resulting in different sources for reconstruction errors. Reconstruction from EO data is limited by frame rate and can be blurred by moving targets or optical distortions in the lens, which leads to errors in the 3D model. Meanwhile, SAR offers the opportunity to correct from some of these errors through its capacity for making range measurements, even under clouds or during nighttime, when EO data would not be available. Conversely, SAR imagery lacks the texture offered by optical images and is more sensitive to perspective, while moving targets can likewise result in reconstruction errors. This work aims at exploiting the strengths of both modalities to reconstruct 3D scenes from multi-sensor EO-SAR data. In particular, we consider the fusion of multi-pass Gotcha SAR data with a modeled EO-data for the particular scene. We propose a framework that fuses 2D image maps acquired from airborne EO data as well as airborne SAR, which leverages the range information of SAR and object shape information of EO imagery. From an initial 2D image of the scene, with each additional sources of sensor data (EO or SAR), a 3D reconstruction is formed that is iteratively improved. This approach allows for the potential to achieve robust and real-time 3D representations as a basis for 4D surveillance.

We introduce a novelty in the method of the deep salient wood image quality assessment (DS-WIQA) for no-reference image quality assessment (NR-IQA). We exploit a five-layer deep convolutional neural network (DCNN) for the salient wood image map. DS-WIQA also employs the n-convex-concave model. The outcomes obviously prove that our DCNN and DS-WIQA architectures can deliver a superior achievement on Zenodo and Lignoindo datasets, respectively. We compute a salient wood image map of each wood image in small wood image patches. Our exploratory outcomes evince that the proposed DCNN and DS-WIQA methods are superior to other the advanced methods on Zenodo and Lignoindo datasets, respectively. Our proposed DCNN for NR-IQA also obtains a better result compared with the other NR-IQA methods in the five distortion types of JP2K, JPEG, white noise Gaussian, blocking artifact, and the fast fading and also in the undistorted wood images. Our DCNN outruns the recent most sophisticated methods in terms of SROCC and LCC evaluation, respectively. DS-WIQA outpaces other the advanced methods by $$0.38\%$$ and $$0.22\%$$ greater than our proposed DCNN, and $$34.84\%$$ and $$30.15\%$$ greater than other methods with respect to SROCC and LCC, respectively. In computational complexity of our proposed DCNN and DS-WIQA cut down the shift add operation in exponential, logarithmic, and trigonometric functions. DS-WIQA shows up to be more significant than our proposed DCNN and the other DCNN methods.

The progress of science and technology has changed the way of topographic mappingwhich is no longer limited to traditional ground and aerial photogrammetry. Unmanned ariel vechicle (UAV) is used to create image maps, light-probing maps, measurement vehicle scans as a new state of the art technology. Drone flight tests are different from traditional large aircraft aerial measurements. Drones are not affected by climate much and does not cause any casualty with good safety, low-altitude operation, obtaining high-precision images. They have wider building coverage. Using drones increases the multi-faceted texture image of buildings with enhaced scale up to 1:1000. The images from drones avoids cloud cover with low cost, easy operation and maintenance. Mapping is very important in geography, architecture and other fields, especially in urban planning. Thus, we combine UAV technology with urban planning to build a three-dimensional (3D) model from the original two-dimensional (2D) plane of the urban planning and economic zone. Geographic Information Systems (GIS) is also used for urban planning to facilitate subsequent application and treatment.

Depression is a mental illness that may be harmful to an individual’s health. Using deep learning models to recognize the facial expressions of individuals captured in videos has shown promising results for automatic depression detection. Typically, depression levels are recognized using 2D-Convolutional Neural Networks (CNNs) that are trained to extract static features from video frames, which impairs the capture of dynamic spatio-temporal relations. As an alternative, 3D-CNNs may be employed to extract spatiotemporal features from short video clips, although the risk of overfitting increases due to the limited availability of labeled depression video data. To address these issues, we propose a novel temporal pooling method to capture and encode the spatio-temporal dynamic of video clips into an image map. This approach allows fine-tuning a pre-trained 2D CNN to model facial variations, and thereby improving the training process and model accuracy. Our proposed method is based on two-stream model that performs late fusion of appearance and dynamic information. Extensive experiments on two benchmark AVEC datasets indicate that the proposed method is efficient and outperforms the state-of-the-art schemes.

To minimize damage during disasters, the rapid collection and delivery of accurate information are essential. Then, we proposed an automatic disaster situation visualization system and implemented a prototype of it in the previous study. The system collects images taken by the car-mounted camera of a truck running in areas where a disaster occurs and displays them on a web-based map. By using the system, we can grasp the situation in the target area quickly and comprehensively. In this study, we improve the system from two perspectives. The first one is to add a function to post images to Twitter, and the second one is the improvement of the image mapping function.

The purpose of this study is to assess feasibility of developing a new case-based computer-aided diagnosis (CAD) scheme of mammograms based on a tree-based analysis of SSIM characteristics of the matched bilateral local areas of left and right breasts to predict likelihood of cases being malignant. We assembled a dataset involving screening mammograms acquired from 1000 patients. Among them, 500 cases were positive with cancer detected and verified, while other 500 cases had benign masses. Both CC and MLO view of the mammograms were used for feature extraction in this study. A CAD scheme was applied to preprocess the bilateral mammograms of the left and right breasts, generate image maps in the special domain, compute SSIM-based image features between the matched bilateral mammograms, and apply a support vector machine model to classify between malignant and benign cases. For performance evaluation, CAD scheme was trained and tested using a 10-fold cross-validation method. The area under a receiving operating characteristic curve (AUC) was computed as an index of performance evaluation. Using the poll of 12 extracted SSIM features, the CAD scheme yielded a performance level of AUC = 0.84±0.016, which is significantly higher than using each individual SSIM feature for the classification purpose (p < 0.05), and an odds ratio of 19.0 with 95% confidence interval of [15.3, 29.8]. Thus, this study supports the feasibility of applying an innovative method to develop a new case-based CAD scheme without lesion segmentation and demonstrates higher performance of new CAD scheme to classify between malignant and benign mammographic cases.

In this Letter, we present a snapshot hyperspectral light field imaging system using a single camera. By integrating an unfocused light field camera with a snapshot hyperspectral imager, the image mapping spectrometer, we captured a five-dimensional (5D) ( x , y , u , v , λ ) ( x , y , spatial coordinates; u , v , emittance angles; λ , wavelength) datacube in a single camera exposure. The corresponding volumetric image ( x , y , z ) at each wavelength is then computed through a scale-depth space transform. We demonstrated the snapshot advantage of our system by imaging the spectral-volumetric scenes in real time.

This paper presents a spectral mapping based image coding approach for suspicious region detection using architectural region detection. In the analysis of detecting suspicious regions in mammogram image, segmentation approaches were applied. In the process of region selection, accuracy of decision depends on the coding algorithm, segmentation, and feature descriptor and classification algorithm. The existing approach of suspicious region detection is based on the content, which get distorted during capturing, transmission, or storage process. The distortion added to the image impact the accuracy of region detection and classification. In this paper, to improve the performance of detection, a new spectral domain deviation in textural content of the mammogram region is presented. The direct image mapping of spatial content doesn’t reveal the nature of variation, which tends to misclassification in decision. To improve the accuracy of region selection a spectral domain mapping of energy deviation in textural representation is proposed.

In this work, using GPS which has best accuracy that can be established set of GCPs, also two satellite images can be used, first with high resolution QuickBird, and second has low resolution Landsat image and topographic maps with 1:100,000 and 1:250,000 scales. The implementing of these factors (GPS, two satellite images, different scales for topographic maps, and set of GCPs) can be applying. In this study, must be divided this work into two parts geometric accuracy and informative accuracy investigation. The first part is showing geometric correction for two satellite images and maps.The second part of the results is to demonstrate the features (how the features appearance) of topographic map or pictorial map (image map), Where it is highlight the different features with different scales to know the accuracy of information. Where can be noticed through graphics that features appear very close to each other at a certain scale and become detached at another scale and this problem can be solved by generalization method. Geodatabase in GIS program also have been used as a modern style store all data related to the project in one folder divisions with that data. In addition to storage in a shape file. Geographic Information Systems (GIS) uses Remote Sensing (RS) data for a lot of applications. One of the application areas is the updating of the GIS database using high resolution imagery. Finally, high resolution satellite imagery data is very important to obtain updating map for Kut city by implementation two methods geodatabase and shapefile.

In this work, an efficient multiple sclerosis (MS) segmentation technique is proposed to simplify pre-processing steps and diminish processing time using heterogeneous single-channel magnetic resonance imaging (MRI). A spatial-filtering image mapping, histogram reference image, and histogram matching techniques are effectively applied to possess a local threshold per image using the global threshold algorithm. Feature extraction is performed using mathematical and morphological operations, and a multilayer feed-forward neural network (MLFFNN) is used identify multiple sclerosis’ tissues. Fluid-attenuated inversion recovery (FLAIR) series are used to integrate a faster system while maintaining reliability and accuracy. A sagittal (SAG) FLAIR-based system is proposed for the first time in MS detection systems, which reduces the number of utilized images, and decreases the processing time by nearly one-third. Our detection system provided a significant recognition rate of up to 98.5%. Moreover, a relatively high dice coefficient (DC) value (0.71 ± 0.18) was observed upon testing new images.

The Duolong area is in a strong potential copper mineralization zone associated with felsic intrusions, and several porphyry copper deposits (PCDs) have been identified. The PCDs are characterized by hydrothermal alteration zones. In this study, Sentinel-2A MultiSpectral Instrument (MSI), Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER), and Hyperion data are combined to map hydrothermally altered minerals. Three temporal Sentinel-2A MSI images are processed by integrating the Crosta technique and the anomaly-overlaying selection method to map iron oxides and hydroxyl-bearing minerals. These approaches are implemented to omit interference-induced false anomalies. The six shortwave infrared (SWIR) bands of ASTER are used to extract information on Al-OH and Mg-OH group minerals. The distribution of Al-OH minerals in the ASTER image map corresponds to that of hydroxyl-bearing minerals in the MSI image map. A combination of minimum noise fraction (MNF), pixel purity index (PPI), n-dimensional visualizer (n-D Visualizer) and matched filtering (MF) is adopted to process the Hyperion image to obtain accurate hydrothermal alteration mapping results. The overall accuracy for mineral mapping is 92.75% and the kappa coefficient is 0.89. The results of the Hyperion image are spatially consistent with those of the Sentinel-2A MSI and ASTER images. The image processing results were validated by field investigations and spectral reflectance measurements. Hydrothermally altered rocks correspond well with the five PCDs in the Duolong area. Three mineralization prospects associated with felsic intrusions are discovered in accordance with the results. The methodologies and data are effective in detecting porphyry copper mineralization in other arid areas.

In recent years, an evolutionary change occurred in the digital world when various social networking sites became popular. This led to a big increase of users who share their activities in digital form. A huge amount of digital information has become available, providing researchers with a unique insight into the behavior and activities of entire population. The use of Geo-tagged social media data became an emerging trend to represent user actions and behaviour at specific geographical locations. However, the inaccuracies of Geo-tagged data from social media often limits the utility of this data source in micro scale analysis (at the street or place of interest level (POI)). Our study supports how social media data could be matched accurately with specific physical locations. More specifically, our investigation includes Geo-tweet data and image data from flickr to map accurately physical location using machine leaning and deep learning techniques. In this paper, a preliminary discussion of this work is provided, using Geo-tagged data from Twitter and Open StreetMap in cities such as San Francisco and London as well as for image mapping using Flickr data in cities such as San Francisco and Kyoto.

Light Detection and Ranging (LIDAR) is a technology to range and image the surrounding obstructions. The range gives quantitative information to the Machine Learning (ML) algorithm about the obstacle’s distance from the LIDAR system. The image map gives the approximate height and width of the obstruction, assisting the ML algorithm in making a set of instructions to avoid the obstacle. In this paper, we discuss a geometric optics approach to model LIDAR system. The various control parameters of modeling LIDAR system such as cone release angle, the number of rays launched, and angular step size of elevated and azimuthal angle step are discussed. The effect of these control parameters on the error of mapped image are also discussed. The error of the mapped image of the car and pedestrian with 10,000 released rays, cone angle of 5°, and angular step size of 2° was reported with an error of 18% ± 3%.