Information Content Of Images Research Articles

Abstract 55: Comparison of Sequential Multi-Detector CT and Cone-Beam CT Perfusion Maps in 54 Subjects With an Acute Ischemic Stroke

Introduction: Time from diagnostic imaging to groin puncture highly correlates with outcome and often accounts for delays between hospital arrival and EVT. Our study comparing image quality and information content of MDCTP and CBCTP provides feasibility data for selected AIS patients to go straight to the angio-suite for comprehensive imaging and treatment. Methods: AIS patients eligible for EVT underwent MDCTP, then a CBCTP study on arrival in angio-suite. Of 939 admitted June 2017-April 2019, 226 (24%) received EVT. Of these 54 (35%) were enrolled to receive additional CBCTP imaging. Inability to obtain consent and co-morbidities were major causes for non-enrollment. Times from the start of MDCTP to angio-suite and from angio-suite arrival to first arterial image were recorded. Acquired CBCTP data were reconstructed and processed with an in-house toolbox. MDCTP and CBCTP data were matched for slice thickness and angulation and were processed using RAPID CTP (iSchemaView, Inc.). The rCBF, rCBV, MTT, tMAX maps were randomized to generate 3 unique evaluation sets. 3 neuroradiologists scored diagnostic image quality, artifacts, mismatch pattern detection and EVT indication using 5-point Likert scales. Stroke laterality was compared with the clinical standard for diagnostic accuracy. Results: Accuracies for stroke diagnosis are 97% [95%, 97%] with MDCTP and 92% [90%, 95%] with CBCTP. Cohen’s Kappa between observers is 0.90 for MDCTP-based diagnosis and 0.89 for CBCTP-based diagnosis. Scores of CBCTP to make the stroke diagnosis, detect mismatch pattern, and make treatment decision were non-inferior to corresponding scores for MDCTP (alpha=0.05) within 10% of the whole score range. Subjective scores of MDCTP for image quality and artifacts were slightly superior to those of CBCTP (1.8 vs. 2.3, p<0.01). Conclusions: In this study, a direct to angio-suite workflow provided non-inferior perfusion imaging for AIS patient triage while saving nearly one hour per patient.

Feature-segmentation strategy based convolutional neural network for no-reference image quality assessment

Convolutional neural networks (CNN) have been shown to deliver outstanding performance for image quality assessment (IQA). Most CNN models are trained using small image patches with a fixed resolution of 32 × 32. However, more information of image content and human visual system should be taken into account. This paper proposes a post segmentation based CNN model for no-reference quality assessment without any pre-processing. The network consists of five convolutional layers with max pooling, one special fully connected layer feature-segmentation and one output layer. This paper adopts the feature-segmentation strategy to assure enough training data. We modify the structure of fully connected layer and regard every feature vector of the last pooling maps as an independent sample to train our proposed model. In this way, the raw images can be fed into the input and do not need to be split into patches, to avoid any hand-crafted features. Moreover, the size of the input images is not fixed, and the size of the extracted feature vector is invariant. Experiments on LIVE, CSIQ and TID2008 databases demonstrate that our approach has high consistency with the subjective evaluation scores. The experimental results show that the proposed network outperforms state-of-the-art no-reference IQA algorithms and is comparable to some full-reference IQA algorithms.

Image Recommendation Algorithm Based on Deep Learning

With the rapid development of network technology, the number of digital images is growing at an alarming rate, people's demand for information gradually shift from text into images. However, it is very difficult for users to quickly find the images they are interested in from the large number of image libraries. The purpose of this paper is to study the image recommendation algorithm based on deep learning. In this paper, image classification algorithm is firstly studied. LReLU - Softplus activation function is formed by combining LReLU function and Softplus function, and CNN is improved. Then, an image retrieval model based on local sensitive hash algorithm is proposed in this paper. This model calculates the distance in hamming space for the binary hash code generated by mapping. Euclidean distance is calculated inside the result set after similarity measurement to improve the accuracy, and the image retrieval model is constructed. Finally, an image recommendation model based on implicit support vector machine (SVM) is proposed in this paper. This image recommendation method combines image text information and image content information. The experimental results show that the proposed image recommendation model can meet the practical needs. In this paper, the overlap rate between the CNN-based recommendation model and the human recommendation algorithm was tested, and the coincidence degree of the two recommended images reached 88%.

Multimodal Brain Images Fusion using Cultural Algorithm Optimized Multispectral Features

Medical images can be acquired through different techniques (modalities), which have their own application areas; some of them provide information on the functional activity, while others contain only anatomic information. Usually, in the first case, images have low spatial resolution while in the second case have a higher resolution. However, the analysis of medical images often requires the evaluation of more than one modality; in order provide the specialist with more information for decision making as well as for the analysis and the treatment of diseases. Image fusion aims to combine information from the same sensor or different sensors, so that the image fused retain the information content of each individual image. In remote perception, when multispectral images are analyzed, it is very important to preserve the content of spectral information of each of the bands. The challenge is to obtain good quality images that allow us to extract as much amount of information possible, for which it is sometimes necessary to enhance or modify the image to improve its appearance or combine images or portions thereof to combine the information. An ideal fusion of multispectral images and the band panchromatic will result in a new series of bands with greater spatial resolution and equal spectral content. This paper proposes a PCA, DWT and cultural optimized entropy based DWT fusion with the evaluation parameters; arithmetic mean (SM), Maximum value ( ) and Minimum value ( ).

Rheological and interfacial properties of basil seed gum modified with octenyl succinic anhydride

This study aimed to evaluate rheological and interfacial properties of basil seed gum (BSG) esterified with octenyl succinic anhydride (OSA) at different OSA:BSG weight ratios (WRs) of 0, 0.01, and 0.03. The amounts of added OSA were analyzed by high performance liquid chromatography (HPLC) and ion mobility spectroscopy (IMS). The high correlation coefficient (R2 = 0.998) between the results of HPLC (0%, 0.277%, and 1.01%) and IMS (0%, 0.31%, and 0.97%), obtained at different WRs, indicated that IMS can be considered as an alternative analytical technique for HPLC to determine the extent of modification. The entropy (image information content) of scanning electron micrographs of lyophilized BSG was decreased after modification and attributed to relative disappearance of spherical particles and formation of a structure with higher integrity. A decrease in interfacial tension, an increase in contact angle and molecular weight, and more negative values of zeta-potential were recorded after modification. All dispersions showed shear-thinning behavior with an increase in apparent viscosity after modification. The first-order stress decay with a non-zero equilibrium stress was better than other models for predicting the thixotropic properties. The dilute solution properties were better fitted with slope-based models than intercept-based models. A dominant elastic behavior was observed in BSG dispersions and corresponding BSG-stabilized emulsions and improved after modification. The OSA-modified BSG exhibited an improvement in the emulsifying and foaming capacities and colloidal stability over time. Emulsions prepared with modified gums showed a smaller droplet size. OSA-modified BSG might be a good candidate for improving the long-term stability of emulsions.

Learning from visual content and style: an image-enhanced recommendation model

Image based platforms are popular in recent years. With a large number of images in these image based platforms, how to properly recommend images that suit each user’s interest is a key problem for recommender systems. While a simple idea is to adopt collaborative filtering for image recommendation, it does not fully utilize the visual information and suffers from the data sparsity issue. Recently, with the huge success of Convolutional Neural Networks (CNN) for image analysis, some researchers proposed to leverage image content information for recommendation. Specifically, Visual Bayesian Personalized Ranking (VBPR) (He and McAuley, in: The association for the advancement of artificial intelligence, 2016) is a state-of-the-art visual based recommendation model, which proposed to learn users’ preferences to items from two spaces: a visual content space learned from CNNs, and a latent space learned from classical collaborative filtering models. VBPR and its variants showed better recommendation performance with image content modeling. In the real-world, when browsing visual images, users not only care the image content, but also concern the matching degree of the image style. Compared to image content, the role of visual styles has been largely ignored in the image recommendation community. Therefore, in this paper, we study the problem of learning both the visual content and style for image recommendation. We leverage advances in computer vision to learn the visual content and style representation, and propose to how to combine visual signals with users’ collaborative data. Finally, experimental results on a real-world dataset clearly show the effectiveness of our proposed model.

Single sample description based on Gabor fusion

Owing to lack of enough face image and invalidation of many traditional face recognition algorithms, face recognition with single training sample is really a great challenge. To solve the above problem, this study proposes a novel local weighted fusion Gabor (LWFG) algorithm. First, one single sample is segmented into a series of block sub-images, and then, each of these sub-images is decomposed into a series of multi-resolution Gabor wavelets with multi-orientation and multi-scale. Second, different orientation Gabor wavelets with the same scale are fused. Next, different scale Gabor wavelets with the same orientation are fused according to the proposed fusion criterion. Third, the fusion Gabor feature histograms are calculated in each of the divided local regions. Meanwhile, every local region's information importance is measured by the proposed local image information content model. Finally, the fusion Gabor wavelet histograms are adaptively weighed by weighting map which calculated from information content model. This study conducted simulation experiments on different face databases under the different conditions including partial occlusion, expression change and illumination variation. The results indicated that the proposed LWFG algorithm is more effective with single training sample.

Fusion Method Evaluation and Classification Suitability Study of Wetland Satellite Imagery

Based on HJ-1A HSI data and Landsat-8 OLI data, RS image fusion experiments were carried out using three fusion methods: principal component (PC) transform, Gram Schimdt (GS) transform and nearest neighbor diffusion (NND) algorithm. Four evaluation indexes, namely mean, standard deviation, information entropy and average gradient, were selected to evaluate the fusion results from the aspects of image brightness, clarity and information content. Wetland vegetation was classified by spectral angle mapping (SAM) to find a suitable fusion method for wetland vegetation information extraction. The results show that PC fusion image contains the largest amount of information, GS fusion image has certain advantages in brightness and clarity maintenance, and NND fusion method can retain the spectral characteristics of the image to the maximum extent; Among the three fusion methods, PC transform is the most suitable for wetland information extraction. It can retain more spectral information while improving spatial resolution, with classification accuracy of 89.24% and Kappa coefficient of 0.86.

To the question of the choice of effective tools оf graphical visualization in the design tasks

Modern trends in graphic design development are characterized by widespread transition from man-made graphics to digital technology. Rapidly developing of computer and information technology is resulting in increased physical correctness images, in active use of market-ready elements, component models, in increasing the functionality of software. The developers are trying to create computer programs as convenient, easier to learn, and their interfaces are characterized be term "humane."In such circumstances there is a risk of images originality loss of projected objects, mostly through thoughtless use of ready "template" computer configurations that partly makes graphics unclear, low quality and devalues it.Creation of qualitative graphics requires the development and implementation of scientifically grounded principles, some of which are based on classical laws and experience of traditional man-made tools of image.In the given article, the principles of use of modelling tools of objective and esthetic properties of the projected forms proceeding from in advance defined conditions were issued.Perception of various aspects of an object is practically implemented by means of a number of special images. Each of them, revealing a certain aspect of the design plan, can also have an emotional assessment of its perception. The problem of ensuring the functionality, information content, laconicism and relevance of project images, as well as emphasis of the figurative characteristics of a designed project put by the author, conducts to the solution of the question of the expediency of graphic tools. From this perspective, the recommendations on the choice of modelling tools of certain objective and subjective properties of the designed forms on predetermined conditions were developed, and it is possible to increase efficiency of the graphic determination by using these recommendations.The research conducted in this work can be used for the purpose of creation of the systematized technique of application of means of design graphics in formative process.

Principal Components Analysis as enhancement Operator and Compression factor

Principal components analysis (PCA) is effective at compressing information in multivariate data sets by computing orthogonal projections that maximize the amount of data variance. Unfortunately, information content in hyper spectral images does not always coincide with such projections. We propose an application of projection pursuit (pp), which seeks to find a set of projections that are "interesting" in the sense that they deviate from the Gaussian distribution assumption.
 Once these projections are obtained, they can be used for image compression, segmentation, or enhancement for visual analysis. To find these projections, a two –step iterative process is followed where we first search for a projection that maximizes a projection index based on the information divergence of the projections estimated probability distribution from the Gaussian distribution and then reduce the rank by projections the data on to the subspace orthogonal to the previous projection . To calculate each projections, we use a simplified approach to maximizing the projection index, which does not require optimization algorithm. It searches for a solution by obtaining a set of candidate projections from the data and choosing the one with the highest projection index. The effectiveness of the method is demonstrated through simulated examples as well as data from the hyper spectral digital imagery collection experiment and the spatially enhanced broadband and array spectrograph system.

Simultaneous recovery of both bright and dim structures from noisy fluorescence microscopy images using a modified TV constraint.

The quality and information content of biological images can be significantly enhanced by postacquisition processing using deconvolution and denoising. However, when imaging complex biological samples, such as neurons, stained with fluorescence labels, the signal level of different structures can differ by several orders of magnitude. This poses a challenge as current image reconstruction algorithms are focused on recovering low signals and generally have sample-dependent performance, requiring tedious manual tuning. This is one of the main hurdles for their wide adoption by nonspecialists. In this work, we modify the general constrained reconstruction method (in our case utilizing a total variation constraint) so that both bright and dim structures can drive the deconvolution with equal force. In this way, we can simultaneously obtain high-quality reconstruction across a wide range of signals within a single image or image sequence. The algorithm is tested on both simulated and experimental data. When compared with current state-of-art algorithms, our algorithm outperforms others in terms of maintaining the resolution in the high-signal areas and reducing artefacts in the low-signal areas. The algorithm was also tested on image sequences where one set of parameters are used to reconstruct all images, with blind evaluation by a group of biologists demonstrating a marked preference for the images produced by our method. This means that our method is suitable for batch processing of image sequences obtained from either spatial or temporalscanning. LAY DESCRIPTION: Fluorescence microscopy images of complex biological samples contain a wide range of signal levels. This signal variation leads current reconstruction algorithms, which aim to enhance the quality of the raw images, to have sample-dependent performance. In this work, we design a new optimization that allows the reconstruction to "pay equal eqattention to" both bright and dim structures. In this way, we can simultaneously recover both bright and dim structures within a single image or image sequence, as validated when the algorithm was quantitatively tested on both simulated and experimental data. When our method was evaluated alongside current state of art algorithms by a group of biologists, our algorithm was considered qualitativelysuperior.

Which Has Better Visual Quality: The Clear Blue Sky or a Blurry Animal?

Image content variation is a typical and challenging problem in no-reference image-quality assessment (NR-IQA). This work pays special attention to the impact of image content variation on NR-IQA methods. To better analyze this impact, we focus on blur-dominated distortions to exclude the impacts of distortion-type variations. We empirically show that current NR-IQA methods are inconsistent with human visual perception when predicting the relative quality of image pairs with different image contents. In view of deep semantic features of pretrained image classification neural networks always containing discriminative image content information, we put forward a new NR-IQA method based on semantic feature aggregation (SFA) to alleviate the impact of image content variation. Specifically, instead of resizing the image, we first crop multiple overlapping patches over the entire distorted image to avoid introducing geometric deformations. Then, according to an adaptive layer selection procedure, we extract deep semantic features by leveraging the power of a pretrained image classification model for its inherent content-aware property. After that, the local patch features are aggregated using several statistical structures. Finally, a linear regression model is trained for mapping the aggregated global features to image-quality scores. The proposed method, SFA, is compared with nine representative blur-specific NR-IQA methods, two general-purpose NR-IQA methods, and two extra full-reference IQA methods on Gaussian blur images (with and without Gaussian noise/JPEG compression) and realistic blur images from multiple databases, including LIVE, TID2008, TID2013, MLIVE1, MLIVE2, BID, and CLIVE. Experimental results show that SFA is superior to the state-of-the-art NR methods on all seven databases. It is also verified that deep semantic features play a crucial role in addressing image content variation, and this provides a new perspective for NR-IQA.

Metric-Learning-Based Deep Hashing Network for Content-Based Retrieval of Remote Sensing Images

Hashing methods have been recently found very effective in retrieval of remote sensing (RS) images due to their computational efficiency and fast search speed. The traditional hashing methods in RS usually exploit hand-crafted features to learn hash functions to obtain binary codes, which can be insufficient to optimally represent the information content of RS images. To overcome this problem, in this paper we introduce a metric-learning based hashing network, which learns: 1) a semantic-based metric space for effective feature representation; and 2) compact binary hash codes for fast archive search. Our network considers an interplay of multiple loss functions that allows to jointly learn a metric based semantic space facilitating similar images to be clustered together in that target space and at the same time producing compact final activations that lose negligible information when binarized. Experiments carried out on two benchmark RS archives point out that the proposed network significantly improves the retrieval performance under the same retrieval time when compared to the state-of-the-art hashing methods in RS.

Purifying naturalistic images through a real-time style transfer semantics network

Recently, the progress of learning-by-synthesis has proposed a training model for synthetic images, which can effectively reduce the cost of human and material resources. However, due to the different distribution of synthetic images compared to real images, the desired performance cannot still be achieved. Real images consist of multiple forms of light orientation, while synthetic images consist of a uniform light orientation. These features are considered to be characteristic of outdoor and indoor scenes, respectively. To solve this problem, the previous method learned a model to improve the realism of the synthetic image. Different from the previous methods, this paper takes the first step to purify real images. Through the style transfer task, the distribution of outdoor real images is converted into indoor synthetic images, thereby reducing the influence of light. Therefore, this paper proposes a real-time style transfer network that preserves image content information (e.g., gaze direction, pupil center position) of an input image (real image) while inferring style information (e.g., image color structure, semantic features) of style image (synthetic image). In addition, the network accelerates the convergence speed of the model and adapts to multi-scale images. Experiments were performed using mixed studies (qualitative and quantitative) methods to demonstrate the possibility of purifying real images in complex directions. Qualitatively, it compares the proposed method with the available methods in a series of indoor and outdoor scenarios of the LPW dataset. In quantitative terms, it evaluates the purified image by training a gaze estimation model on the cross data set. The results show a significant improvement over the baseline method compared to the raw real image.

Copy-move forgery detection based on multifractals

Digital images and video are the basic media for communication nowadays. They are used as authenticated proofs or corroboratory evidence in different areas like: forensic studies, law enforcement, journalism and others. With development of software for editing digital images, it has become very easy to change image content, add or remove important information or even to make one image combining multiple images. Thus, the development of methods for such change detection has become very important. One of the most common methods is copy-move forgery detection (CMFD). Methods of this type include change detection that occur by copying a part of an image and pasting it to another location within the image. We propose new method for detection of such changes using certain multifractal parameters as characteristic features, as well as common statistical parameters. Before the analysis, images are divided into non-overlapping blocks of fixed dimensions. For each block, the characteristic features are calculated. In order to classify observed blocks, we used metaheuristic method and proposed new semi-metric function for similarity analysis between blocks. Simulation shows that the proposed method provides good results in terms of precision and recall, with low computational complexity.

An Unsupervised Multicode Hashing Method for Accurate and Scalable Remote Sensing Image Retrieval

Hashing methods have recently attracted great attention for approximate nearest neighbor search in massive remote sensing (RS) image archives due to their computational and storage effectiveness. The existing hashing methods in RS represent each image with a single-hash code that is usually obtained by applying hash functions to global image representations. Such an approach may not optimally represent the complex information content of RS images. To overcome this problem, in this letter, we present a simple yet effective unsupervised method that represents each image with primitive-cluster sensitive multi-hash codes (each of which corresponds to a primitive present in the image). To this end, the proposed method consists of two main steps: 1) characterization of images by descriptors of primitive-sensitive clusters and 2) definition of multi-hash codes from the descriptors of the primitive-sensitive clusters. After obtaining multi-hash codes for each image, retrieval of images is achieved based on a multi-hash-code-matching scheme. Any hashing method that provides single-hash code can be embedded within the proposed method to provide primitive-sensitive multi-hash codes. Compared with state-of-the-art single-code hashing methods in RS, the proposed method achieves higher retrieval accuracy under the same retrieval time, and thus it is more efficient for operational applications.

Revisiting the effect of spatial resolution on information content based on classification results

ABSTRACTPolarimetric Synthetic Aperture Radar (PolSAR) images are an important source of information. Speckle noise gives SAR images a granular appearance that makes interpretation and analysis hard tasks. A major issue is the assessment of information content in these kinds of images, and how it is affected by usual processing techniques. Previous works have resulted in various approaches for quantifying image information content. In this paper, we study this problem from the classification accuracy viewpoint, focusing on the filtering and the classification stages. Thus, through classified images, we verify how changing the properties of the input data affects their quality. The input is an actual PolSAR image, the control parameters are (i) the filter (Local Mean, LM, or Model-Based PolSAR, MBPolSAR) and the size of their support, and (ii) the classification method (Maximum Likelihood, ML, or Support Vector Machine, SVM), and the output is the precision of the classification algorithm applied to the filtered data. To expand the conclusions, this study deals not only with Classification Accuracy but also with Kappa and Overall Accuracy as measures of map precision. Experiments were conducted on two airborne PolSAR images. Differently from what was observed in previous works, almost all quality measures are good and increase with degradation, i.e. the filtering algorithms that we used always improve the classification results at least up to supports of size 7 × 7.

A Tri- State Filter for the Removal of Salt and Pepper Noise in Mammogram Images.

A new algorithm which uses tree based decision and tri-state non linear values to eliminate high density outlier noise in mammogram images is proposed. The proposed algorithm uses the number of non noisy pixels in the current processing vicinity as values in the decision tree. Tri-state values such as unsymmetrical truncated median or modified Winsorized mean or midpoint replaces the corrupted pixel based on the decision tree in the current processing kernel. The algorithm exhibits good PSNR, IEF, low MSE and High structural preservation property even after removing high density noise. The performance of the proposed algorithm was also found good visually. The Key aspect of the work is the combination of tree based decision and tri-state non linear values which preserves the information content of images that are required for further processing.

Information Content in Nuclear Medicine Imaging

The aim of the present study was to investigate the information content of positron emission tomography (PET) images. We used the GATE Monte Carlo package (GEANT4 application for tomographic emission) and reconstructed images, obtained using the software for tomographic image reconstruction (STIR). The case study for the investigation of the PET images information content was the General Electric Discovery-ST (USA) PET scanner. A thin film plane source aluminum (Al) foil, coated with a thin layer of silica and a fluorodeoxyglucose (18F-FDG) bath distribution of (1 MBq) was used in the simulation for the image signal to noise ratio assessment. The influence of the maximum likelihood estimation ordered subsets maximum a posteriori one step late (MLE)-OS-MAP-OSL algorithm, using various subsets (1 to 21) and iterations (1 to 20) was examined. The image information content was assessed in terms of the information capacity (IC). Results showed that the single index information capacity maximized for the range of 8-20 iterations and 3 subsets. In conclusion, our study showed that the image information content of PET scanners can be fully characterized and further improved by investigation of the imaging chain components through Monte Carlo methods. Moreover, new perspectives are created by using the suggested techniques in the context of a global cloud service that could serve as an online quality evaluation metric for the PET scanners and other medical imaging systems.

Fractal analysis of information content of multispectral images in problems of ecological monitoring

Fractal analysis of information content of multispectral images in problems of ecological monitoring