Information Content Of Images Research Articles

A coupled atmospheric and topographic correction algorithm for remotely sensed satellite imagery over mountainous terrain

Radiometric correction is an important issue in the quantitative remote-sensing community. By integrating dark object subtraction (DOS)-based atmospheric correction with physics-based topographic correction, a coupled land surface reflectance retrieval algorithm (coupled atmospheric and topographic correction algorithm, named the CAT algorithm) for rugged mountainous regions is proposed. Terra MODIS-derived atmospheric characterization data (including aerosol optical depth, integrated precipitable water, surface pressure, and ozone concentration) are employed as inputs for the proposed algorithm. A physics-based path radiance estimation model is proposed and embedded in the CAT algorithm, and band-specific per-pixel path radiance values are calculated. After the CAT algorithm was performed, the correlation between reflectance and terrain was dramatically reduced, with correlation coefficients nearly equal zero, especially for the near infrared and short-wave infrared bands, meanwhile the image information content increased over 20%. To provide a comparison with previous studies, two commonly used methods in the literature (DOS + Cosine and DOS + C) were employed. The results of the comparison show that the proposed algorithm performed better in both atmospheric and topographic corrections without empirical regression.

Figurative frames: A critical vocabulary for images in information visualization

Critical analyses provide information visualization practitioners with insight into the range and suitability of different techniques for visualization. Theory provides the necessary models and vocabulary to deconstruct, explain and classify visualizations, allowing the analysis and comparison of alternate designs, and evaluation of their success. While the critical vocabulary for information visualization in general is well developed, the same cannot be said for ‘hybrid’ information visualizations which combine abstract representation of data with figurative elements such as illustrations. Figurative elements are widely used in information visualization in practice and are increasingly recognized as beneficial for memorability. However, the information encoded by a figurative image and how that information contributes to the overall content of the visualization lacks robust definition within visualization theory. To support critical analysis of hybrid visualization, we provide a model of the information content of a figurative image, which we call the figurative frame model. We use the model to classify hybrid visualizations along two dimensions: information density in the images (defined as the number of features and preserved measurements) and integration of figurative and abstract forms of representation. The new vocabulary for analysing hybrid visualizations reveals how the figurative images expand the expressiveness of information visualization by integrating descriptive and abstract information and allows the formulation of new measures of visualization quality which can be applied to hybrid visualizations.

INFORMATION TECHNOLOGY TO IMPROVE THE INFORMATIVE VALUE OF THE IMAGES OF THE FOREST FIRES EPICENTERS

Solution of scientific and engineering problems when working with visual data requires a lot of efforts and is based on knowledge of specific methods. Appropriate and relevant scientific and practical task is the activities related to the improvement of the contemporary and the development of new methods of digital image processing. The solution of many problems of modern science and practice leads to the need to extract useful information from various kinds of digital images. Such problems arise in medicine, radio, heat, sonar, space and Earth exploration etc. In this work possibility to improve quality and increase the information content of aerial images is obtained with small aircraft – quadrocopters for quick identification of epicentres of forest fires. As results of the research the author has improved methods of processing digital images and video sequences, which allowed applying them during monitoring and assessment of extreme situations, in particular forest fires.The author has also analyzed methods and algorithms for improving the visual quality of digital images of the epicenters of forest fires on aerophotograph obtained with quadrocopters. Tasks of image processing, to reduce to a small number of major are as follows: filtering and improving the visual perception of the image; recovery of lost plots; finding objects and their identification on some background; estimate geometric transformation and image combining; estimation of the parameters. This group includes the tasks of measuring the characteristics of the images and their elements – probability characteristics, position, size and the like; image compression. The study tested the methods of digital processing of images and video sequences, which allowed us to apply them during monitoring and assessment of extreme situations, particularly fires. Special attention was paid to methods of early detection of forest fires. The result of the consolidation of methods of processing digital images and video streams are presented; their use allows increasing the accuracy of the data about the presence of the epicentres of forest fires.

Image quality transfer and applications in diffusion MRI

This paper introduces a new computational imaging technique called image quality transfer (IQT). IQT uses machine learning to transfer the rich information available from one-off experimental medical imaging devices to the abundant but lower-quality data from routine acquisitions. The procedure uses matched pairs to learn mappings from low-quality to corresponding high-quality images. Once learned, these mappings then augment unseen low quality images, for example by enhancing image resolution or information content. Here, we demonstrate IQT using a simple patch-regression implementation and the uniquely rich diffusion MRI data set from the human connectome project (HCP). Results highlight potential benefits of IQT in both brain connectivity mapping and microstructure imaging. In brain connectivity mapping, IQT reveals, from standard data sets, thin connection pathways that tractography normally requires specialised data to reconstruct. In microstructure imaging, IQT shows potential in estimating, from standard “single-shell” data (one non-zero b-value), maps of microstructural parameters that normally require specialised multi-shell data. Further experiments show strong generalisability, highlighting IQT's benefits even when the training set does not directly represent the application domain. The concept extends naturally to many other imaging modalities and reconstruction problems.

Personalized Image Annotation Using Deep Architecture

In image-centric social networks, such as Instagram and Pinterest, users tend to share photos with several tags. These tags describe the content of the image or provide additional contextual information, and therefore may not be necessarily tied to image content and usually carry personal preference. Annotating images in social networks in a personalized manner is in demand. However, the existing image annotation models, which rely only on image content information, cannot capture the user’s tagging preference. In this paper, we propose a deep architecture for personalized image annotation by leveraging the wealth of information in user’s tagging history. The proposed architecture consists of three components: two components for learning features of the image content and user’s history tags and the other one for combining the two learned features to predict the tags. We also explore two ways to model user’s history tags: 1) simply average the embeddings of user’s history tags and 2) model user’s history tags with a sequence model by long short-term memory recurrent neural network. We evaluate our proposed deep architecture on a large-scale and realistic data set, consisting of ~22.8 million public images uploaded by ~4.69 million users. Experimental results show that our proposed deep architecture is effective on a personalized image annotation task.

First Results of a Detection Sensor for the Monitoring of Laying Hens Reared in a Commercial Organic Egg Production Farm Based on the Use of Infrared Technology.

The development of a monitoring system to identify the presence of laying hens, in a closed room of a free-range commercial organic egg production farm, was the aim of this study. This monitoring system was based on the infrared (IR) technology and had, as final target, a possible reduction of atmospheric ammonia levels and bacterial load. Tests were carried out for three weeks and involved 7 ISA (Institut de Sélection Animale) brown laying hens. The first 5 days was used to set up the detection sensor, while the other 15 days were used to evaluate the accuracy of the resulting monitoring system, in terms of sensitivity and specificity. The setup procedure included the evaluation of different color background (CB) thresholds, used to discriminate the information contents of the thermographic images. At the end of this procedure, a CB threshold equal to an increase of 3 °C from the floor temperature was chosen, and a cutoff level of 196 colored pixels was identified as the threshold to use to classify a positive case. The results of field tests showed that the developed monitoring system reached a fine detection accuracy (sensitivity = 97.9% and specificity = 94.9%) and the IR technology proved to be a possible solution for the development of a detection sensor necessary to reach the scope of this study.

Growing random forest on deep convolutional neural networks for scene categorization

Breakthrough performances have been achieved in computer vision by utilizing deep neural networks. In this paper we propose to use random forest to classify image representations obtained by concatenating multiple layers of learned features of deep convolutional neural networks for scene classification. Specifically, we first use deep convolutional neural networks pre-trained on the large-scale image database Places to extract features from scene images. Then, we concatenate multiple layers of features of the deep neural networks as image representations. After that, we use random forest as the classifier for scene classification. Moreover, to reduce feature redundancy in image representations we derived a novel feature selection method for selecting features that are suitable for random forest classification. Extensive experiments are conducted on two benchmark datasets, i.e. MIT-Indoor and UIUC-Sports. Obtained results demonstrated the effectiveness of the proposed method. The contributions of the paper are as follows. First, by extracting multiple layers of deep neural networks, we can explore more information of image contents for determining their categories. Second, we proposed a novel feature selection method that can be used to reduce redundancy in features obtained by deep neural networks for classification based on random forest. In particular, since deep learning methods can be used to augment expert systems by having the systems essentially training themselves, and the proposed framework is general, which can be easily extended to other intelligent systems that utilize deep learning methods, the proposed method provide a potential way for improving performances of other expert and intelligent systems.

Learning two-pathway convolutional neural networks for categorizing scene images

Scenes are closely related to the kinds of objects that may appear in them. Objects are widely used as features for scene categorization. On the other hand, landscapes with more spatial structures of scenes are representative of scene categories. In this paper, we propose a deep learning based algorithm for scene categorization. Specifically, we design two-pathway convolutional neural networks for exploiting both object attributes and spatial structures of scene images. Different from conventional deep learning methods, which usually focus on only one aspect of images, each pathway of the proposed architecture is tuned to capture a different aspect of images. As a result, complementary information of image contents can be utilized effectively. In addition, to deal with the feature redundancy problem caused by combining features from different sources, we adopt the l 2,1 norm during classifier training to control selectivity of each type of features. Extensive experiments are conducted to evaluate the proposed method. Obtained results demonstrate that the proposed approach achieves superior performances over conventional methods. Moreover, the proposed method is a general framework, which can be easily extended to more pathways and applied to solve other problems.

Enhance the Information Content of Medical Image by Image Fusion Techniques - A Survey

Enhance the Information Content of Medical Image by Image Fusion Techniques - A Survey

Thermographic Detection of separated Flow

Thermographic wind tunnel measurements, both on a cylinder as well as on a 2D airfoil, were performed at various Reynolds numbers in order to evaluate the possibility of detecting and visualizing separated flow areas. A new approach by acquiring a series of thermographic images and applying a spatial-temporal statistical analysis allows improving both the resolution and the information content of the thermographic images. Separated flow regions become visible and laminar/turbulent transitions can be detected more accurately. The knowledge about possibly present stall cells can be used to confirm two-dimensional flow conditions and support the development of more effective and silent rotorblades.

The Effects of Restaurant and LOHAS Images on Customer Satisfaction and Loyalty: Focusing on the Incremental Information Content of LOHAS Image

The Effects of Restaurant and LOHAS Images on Customer Satisfaction and Loyalty: Focusing on the Incremental Information Content of LOHAS Image

The Effects of Restaurant and LOHAS Images on Customer Satisfaction and Loyalty: Focusing on the Incremental Information Content of LOHAS Image

The Effects of Restaurant and LOHAS Images on Customer Satisfaction and Loyalty: Focusing on the Incremental Information Content of LOHAS Image

Joint 3-D Image Quality Assessment Metric by Using Image View and Depth Information Over the Networking in IoT

It is accepted that image compression and transmission are essential in the image processing system and that errors occurred may introduce the degradation on the quality of the received image over the wireless transmission for intelligent Internet of things (IoT). Image quality assessment metric (QAM) is of fundamental significance to various image processing systems, and the goal of studying the QAM is to design an algorithm that can automatically evaluate the quality of the received image at the terminal display equipment in a perceptible way under the ubiquitous network circumstances. In this paper, focusing on the image compression and transmission, a joint full-reference (FR) QAM ( JQAM ) for evaluating the quality of a 3-D image is proposed based on the state-of-the-art physiological and psychological properties of the human visual system (HVS) for image transmission under the wireless networks. The major technical contribution of this paper is that the binocular perception (depth perception) and local image properties are taken into consideration. First, the luminance masking property and local image content information are calculated to establish image QAM (IQAM) to improve the abilities of current quality evaluation algorithms. Meanwhile, the information abstracted from the depth map is also utilized as side information (SI) to evaluate the depth map on quality assessment. Finally, IQAM and SI are combined to construct the proposed JQAM. Experimental results show that the proposed metric could achieve better correlation with the subjective quality scores compared with the relevant existing IQAMs, and it could be used to evaluate the quality of the 3-D image signal of the intelligent equipment for multimedia communication systems in IoT.

A novel and efficient method based on knight moves for securing the information contents of images — A parallel approach

Protection of multimedia information from unauthorized access demands a mechanism that provides security. In addition, securing the information contents in less time is a challenging issue. In this work, a novel and efficient parallel approach is proposed based on moves of knight pieces to secure the contents of an image in short span of time. The novelty of the approach lies in simulating the moves of knight pieces in parallel and generation of key sequence based on crossover operation. Further, in this approach, initialization of positions of knight pieces results in generation of key sequence. The proposed approach comprises three stages. In the first stage, a number of knight pieces which process in parallel are selected automatically. In second stage, random keys are generated based on the linear feedback shift register to select one of one point, two point and arithmetic crossover operation. Using crossover operation key sequence is generated. In third stage, exclusive OR operation is performed on the selected position of knight piece and generated key to produce the encrypted image. Experiments are carried out exhaustively on various types of images and performance of the proposed approach is measured in terms of parameters structural similarity index, feature similarity index, entropy and correlation coefficient. The proposed approach is compared with an existing parallel approach and the comparative analysis reveals that the proposed method outperforms in securing contents of images.

Large-area settlement pattern recognition from Landsat-8 data

The study presents an image processing and analysis pipeline that combines object-based image analysis with a Support Vector Machine to derive a multi-layered settlement product from Landsat-8 data over large areas. 43 image scenes are processed over large parts of Central Asia (Southern Kazakhstan, Kyrgyzstan, Tajikistan and Eastern Uzbekistan). The main tasks tackled by this work include built-up area identification, settlement type classification and urban structure types pattern recognition. Besides commonly used accuracy assessments of the resulting map products, thorough performance evaluations are carried out under varying conditions to tune algorithm parameters and assess their applicability for the given tasks. As part of this, several research questions are being addressed. In particular the influence of the improved spatial and spectral resolution of Landsat-8 on the SVM performance to identify built-up areas and urban structure types are evaluated. Also the influence of an extended feature space including digital elevation model features is tested for mountainous regions. Moreover, the spatial distribution of classification uncertainties is analyzed and compared to the heterogeneity of the building stock within the computational unit of the segments. The study concludes that the information content of Landsat-8 images is sufficient for the tested classification tasks and even detailed urban structures could be extracted with satisfying accuracy. Freely available ancillary settlement point location data could further improve the built-up area classification. Digital elevation features and pan-sharpening could, however, not significantly improve the classification results. The study highlights the importance of dynamically tuned classifier parameters, and underlines the use of Shannon entropy computed from the soft answers of the SVM as a valid measure of the spatial distribution of classification uncertainties.

Face description based on adaptive local weighted Gabor comprehensive histogram feature

Face recognition is an extensively research topic in pattern recognition and image processing fields due to its broad application prospects in many areas such as counter terrorism, access identification, electronic passport, e-government affairs, etc. Inspired by the Gabor phase information and local image information content, a novel face description algorithm using adaptive Local Weighted Gabor Comprehensive Histogram (LWGCH) is proposed. It consists of two components: Local Gabor Comprehensive Histogram (LGCH) and Contribution Map (CM). Actually, the adaptive local weighted Gabor comprehensive histogram is generated with LGCH weighed by CM calculated by information content model. Finally, Extensive experiments on ORL, YALE, CMUPIE and Yale B face databases validate the effectiveness of the proposed methods under various conditions of partial occlusion, complex illumination, different expressions and poses. Experimental results indicate that the proposed algorithm is a competitive and robust method compared with several state-of-the-art approaches.

Multi-source and Multi-feature Image Information Fusion Based on Compressive Sensing

Image fusion is a comprehensive information processing technique and its purpose is to enhance the reliability of the image via the processing of the redundant data among multiple images, improve the image definition and information content through fusion of the complementary information of multiple images so as to obtain the information of the objective or the scene in a more accurate, reliable and comprehensive manner. This paper uses the sparse representation method of compressive sensing theory, proposes a multi-source and multi-feature image information fusion method based on compressive sensing in accordance with the features of image fusion, performs sparsification processing on the source image with K-SVD algorithm and OMP algorithm to transfer from spatial domain to frequency domain and decomposes into low-frequency part and high-frequency park. Then it fuses with different fusion rules and the experimental results prove that the method of this paper is better than the traditional methods and it can obtain better fusion effects.

Ideal Binocular Disparity Detectors Learned Using Independent Subspace Analysis on Binocular Natural Image Pairs.

An influential theory of mammalian vision, known as the efficient coding hypothesis, holds that early stages in the visual cortex attempts to form an efficient coding of ecologically valid stimuli. Although numerous authors have successfully modelled some aspects of early vision mathematically, closer inspection has found substantial discrepancies between the predictions of some of these models and observations of neurons in the visual cortex. In particular analysis of linear-non-linear models of simple-cells using Independent Component Analysis has found a strong bias towards features on the horoptor. In order to investigate the link between the information content of binocular images, mathematical models of complex cells and physiological recordings, we applied Independent Subspace Analysis to binocular image patches in order to learn a set of complex-cell-like models. We found that these complex-cell-like models exhibited a wide range of binocular disparity-discriminability, although only a minority exhibited high binocular discrimination scores. However, in common with the linear-non-linear model case we found that feature detection was limited to the horoptor suggesting that current mathematical models are limited in their ability to explain the functionality of the visual cortex.

Spatial Angular Compounding of Photoacoustic Images.

Photoacoustic (PA) images utilize pulsed lasers and ultrasound transducers to visualize targets with higher optical absorption than the surrounding medium. However, they are susceptible to acoustic clutter and background noise artifacts that obfuscate biomedical structures of interest. We investigated three spatial-angular compounding methods to improve PA image quality for biomedical applications, implemented by combining multiple images acquired as an ultrasound probe was rotated about the elevational axis with the laser beam and target fixed. Compounding with conventional averaging was based on the pose information of each PA image, while compounding with weighted and selective averaging utilized both the pose and image content information. Weighted-average compounding enhanced PA images with the least distortion of signal size, particularly when there were large (i.e., 2.5 mm and 7 (°)) perturbations from the initial probe position. Selective-average compounding offered the best improvement in image quality with up 181, 1665, and 1568 times higher contrast, CNR, and SNR, respectively, compared to the mean values of individual PA images. The three presented spatial compounding methods have promising potential to enhance image quality in multiple photoacoustic applications.

Multimodal medical image fusion using Butterworth high pass filter and Cross bilateral filter

Multimodal Medical Image fusion is a prominent area of interest. Medical image fusion is the process of combining images from different modalities. It improves imaging quality and reduces the redundant information. The main aim of Medical Image fusion is in having better quality of fused image for the diagnostic purposes. Image fusion improves capability and reliability of images. In medical background, sharpness of fused image is the basic criteria of quality. In this paper, quality of fused image can be enhanced by using combination of Butterworth High Pass filter and Cross Bilateral filter. Cross bilateral filter is a nonlinear filter, which takes both range domain and spatial domain filtering into account. It is an edge preserving filter, which fuse images by taking weighted average of source image pixels. For better quality of fused results, the input images are sharpened using high order, Butterworth high pass filter and then images are fused with Cross Bilateral filter. Results show that the modified image fusion framework is effective in preserving fine details, information content and contrast of image.