Different Kinds Of Images Research Articles

Incorporating global multiplicative decomposition and local statistical information for brain tissue segmentation and bias field estimation

Medical image is a cornerstone of modern healthcare providing unique diagnostic. However, intensity nonuniformity is quite often found in medical images and unavoidably poses many challenges for precise image segmentation. In this paper, we present an incorporating global multiplicative decomposition and local statistical information level set technique for tissue segmentation and bias estimation that handles both high noise and intensity nonuniformity. An image can be factored into two multiplicative parts (namely, bias-free image and bias field), which are used to capture global intensity statistics. At the same time, our technique considers statistical information with not only the mean but also the variance. Pixel intensity generally fluctuates around its mean in a local region. The variance can adjust the disagreement of each pixel to its mean, and is explored to overcome the effects of intensity nonuniformity. Finally, the level set energy formulation is in the form of the global multiplicative decomposition and local statistical information. To verify the availability of our technique, we have thoroughly experimented on composite and real images. Our techniques are also applied to the lesion regions of brains. Experimental results display that our technique can segment different kinds of images with high noise and intensity nonuniformity more accurately, and outperforms other solutions in comparison.

An innovative technique for image encryption using tri-partite graph and chaotic maps

In this article, the concept of a complete 3-Partite graph is used to substitute the pixels of a color image to achieve encryption. Chen’s chaotic system is deployed to generate vertices of a tri-partite directed graph and then paths are established between these vertices. These paths will serve to perform the substitution of individual pixels. The seeds for the chaotic maps are manipulated by the hash value of the plain image to hinder chosen plaintext attack. The inter and intra correlation of pixels of a three color image in one-dimensional vector is distorted using the non-linear system of equations. The different chaotic maps having divergent features are employed to add up complexity in encryption technique. The extensive experiments are applied on different kinds of images and results are compiled. The results show that the proposed system has a strong robustness against different attacks and prove to be an excellent candidate to encrypt colored digital images. It has high scores for the Number of Pixel Change Rate (NPCR), Unified Average Cipher Intensity (UACI), entropy values, low values for Mean Absolute Error (MAE), Chi-Square and variance of histograms for encrypted images. The palpable lead of proposed system has resilience against transmission impairments such as Gaussian, Salt & Pepper and clipping.

Design and application of an S-box using complete Latin square

Since a substitution box (S-box) is the nonlinearity part of a symmetric key encryption scheme, it directly determines the performance and security level of the encryption scheme. Thus, generating S-box with high performance and efficiency is attracting. This paper proposes a novel method to construct S-box using the complete Latin square and chaotic system. First, a complete Latin square is generated using the chaotic sequences produced by a chaotic system. Then an S-box is constructed using the complete Latin square. Performance analyses show that the S-box generated by our proposed method has a high performance and can achieve strong ability to resist many security attacks such as the linear attack, differential attack and so on. To show the efficiency of the constructed S-box, this paper further applies the S-box to image encryption application. Security analyses show that the developed image encryption algorithm is able to encrypt different kinds of images into cipher images with uniformly distributed histograms. Performance evaluations demonstrate that it has a high security level and can outperform several state-of-the-art encryption algorithms.

Detecting Adversarial Image Examples in Deep Neural Networks with Adaptive Noise Reduction

Recently, many studies have demonstrated deep neural network (DNN) classifiers can be fooled by the adversarial example, which is crafted via introducing some perturbations into an original sample. Accordingly, some powerful defense techniques were proposed. However, existing defense techniques often require modifying the target model or depend on the prior knowledge of attacks. In this paper, we propose a straightforward method for detecting adversarial image examples, which can be directly deployed into unmodified off-the-shelf DNN models. We consider the perturbation to images as a kind of noise and introduce two classic image processing techniques, scalar quantization and smoothing spatial filter, to reduce its effect. The image entropy is employed as a metric to implement an adaptive noise reduction for different kinds of images. Consequently, the adversarial example can be effectively detected by comparing the classification results of a given sample and its denoised version, without referring to any prior knowledge of attacks. More than 20,000 adversarial examples against some state-of-the-art DNN models are used to evaluate the proposed method, which are crafted with different attack techniques. The experiments show that our detection method can achieve a high overall F1 score of 96.39% and certainly raises the bar for defense-aware attacks.

Entropy estimation for robust image segmentation in presence of non Gaussian noise

In this work we introduce a new approach for robust image segmentation. The idea is to combine two strategies within a Bayesian framework. The first one is to use a Markov Random Field (MRF), which allows to introduce prior information with the purpose of preserve the edges in the image. The second strategy comes from the fact that the probability density function (pdf) of the likelihood function is non Gaussian or unknown, so it should be approximated by an estimated version, and for this, it is used the classical non-parametric or kernel density estimation. This two strategies together lead us to the definition of a new maximum a posteriori (MAP) approach based on the minimization of the entropy of the estimated pdf of the likelihood function and the MRF at the same time, named MAP entropy estimator (MAPEE). Some experiments were conducted for different kind of images degraded with impulsive noise and other non-Gaussian distributions, where the segmentation results are very satisfactory comparing them with respect to recent robust approaches based on the fuzzy c-means (FCM) segmentation.

Adaptive deep feature aggregation using Fourier transform and low-pass filtering for robust object retrieval

With the rapid development of deep learning techniques, convolutional neural networks (CNN) have been widely investigated for the feature representations in the image retrieval task. However, the key step in CNN-based retrieval, i.e., feature aggregation has not been solved in a robust and general manner when tackling different kinds of images. In this paper, we present a deep feature aggregation method for image retrieval using the Fourier transform and low-pass filtering, which can adaptively compute the weights for each feature map with discrimination. Specifically, the low-pass filtering can preserve the semantic information in each feature map by transforming images to the frequency domain. In addition, we develop three adaptive methods to further improve the robustness of feature aggregation, i.e., Region of Interests (ROI) selection, spatial weighting and channel weighting. Experimental results demonstrate the superiority of the proposed method in comparison with other state-of-the-art, in achieving robust and accurate object retrieval under five benchmark datasets.

Analysis on the Image Project of Hubei Local Cities under the Computer Operation: Based on the News Data of “the Hubei Daily” in 2019

The construction of the image of city is not a spontaneous process, it has strong relationship with media under the computer operation. This study collected the news reports of Xiangyang, Yichang and Jingzhou in the Hubei Daily in 2019, and conducted an in-depth analysis of the media images of these three cities by the computer calculation. It is found that Xiangyang, Yichang and Jingzhou were represented into different kinds of image, and especially, there were significant differences in the theme of reports. Based on the results, it is advisable for each city to create unique resources and to present personalized images. Meanwhile, it is also necessary to take use of the computer operation, so that a much more scientific, systematic and reasonable image project of cities could be established.

Multi-column network for cell counting

Cell counting is a fundamental but crucial task for microscopic analysis. In this paper, we present a method that can count cells automatically and achieves good accuracy. The algorithm extends the U-net from the single-column to the multi-column to capture the features of cells with various sizes. The general convolutional layers in the U-net body are replaced by residual blocks to help the network converge better. Furthermore, a region-based loss function is designed to guide the model to slide into the proper local minima and avoid overfitting. Experimental results on three public datasets show that the proposed method can handle different kinds of images with promising accuracy. Compared with other state-of-the-art approaches, the proposed approach performs superiorly.

An Image Segmentation Method Based on Two-Dimensional Entropy and Chaotic Lightning Attachment Procedure Optimization Algorithm

Threshold segmentation has been widely used in recent years due to its simplicity and efficiency. The method of segmenting images by the two-dimensional maximum entropy is a species of the useful technique of threshold segmentation. However, the efficiency and stability of this technique are still not ideal and the traditional search algorithm cannot meet the needs of engineering problems. To mitigate the above problem, swarm intelligent optimization algorithms have been employed in this field for searching the optimal threshold vector. An effective technique of lightning attachment procedure optimization (LAPO) algorithm based on a two-dimensional maximum entropy criterion is offered in this paper, and besides, a chaotic strategy is embedded into LAPO to develop a new algorithm named CLAPO. In order to confirm the benefits of the method proposed in this paper, the other seven kinds of competitive algorithms, such as Ant–lion Optimizer (ALO) and Grasshopper Optimization Algorithm (GOA), are compared. Experiments are conducted on four different kinds of images and the simulation results are presented in several indexes (such as computational time, maximum fitness, average fitness, variance of fitness and other indexes) at different threshold levels for each test image. By scrutinizing the results of the experiment, the superiority of the introduced method is demonstrated, which can meet the needs of image segmentation excellently.

Building Damage Detection via Superpixel-Based Belief Fusion of Space-Borne SAR and Optical Images

Space-borne synthetic aperture radar (SAR) and optical sensors are important tools for building damage detection. Fusion of SAR and optical images improves detection performance. However, when the resolutions of the two different kinds of images differ, the performance of the existing pixel-level fusion methods deteriorates significantly due to interpolation-induced distortion. To solve this problem, this paper presents a new superpixel-based belief fusion (SBBF) model for building damage detection. The superpixels on the SAR and optical images are identified by the segmentation on the pre-earthquake optical image to perform the fusion on the superpixel-level instead of the pixel-level in existing methods. Then in the fusion stage, different from the commonly used direct fusion methods that do not consider the reliability in the fusion process, a novel belief fusion method that employs a basic belief assignment (BBA) to incorporate different reliabilities of superpixels is proposed to improve the accuracy of building damage detection. For each superpixel, the BBA is assigned based on the influence of noise and resolutions. The United Nations Operational Satellite Applications Programme (UNOSAT) datasets corresponding to the 2010 Haiti earthquake and the 2011 Tōhoku earthquake, are used to evaluate the performance of the proposed method. The experimental results show that the proposed method achieves significantly better performance than existing separate SAR or optical images based methods, and the existing pixel-level fusion methods.

An efficient level set method based on global statistical information for image segmentation

In this paper, an improved region-based active contour model in a novel variational level set formulation employing global information constraints is proposed for image segmentation. Using the image global characteristics, the proposed model can accurately segment objects with weak or blurred boundaries in the presence of noise or intensity inhomogeneity and achieve robustness against different kinds of images. We present a global intensity fitting energy functional based on the differences between the original image intensity and the global intensity means. This energy is then integrated into a geodesic variational level set formulation, from which a curve evolution equation is derived for energy minimization. The level set function is regularized by the Gaussian filter which keeps it smooth and eliminates the reinitialization. Experimental results on different images demonstrate the performance of our method in terms of accuracy and robustness. Compared with the well-known active contour models, our method is less sensitive to the initial contour and more computationally efficient.

GVFOM: a novel external force for active contour based image segmentation

The GVF snake is effective on converging into concave areas and being insensitive to initialization. However, it fails to converge to areas with deep and narrow concavities or preserve weak edges. In this paper, a novel external force called gradient vector flow over manifold (GVFOM) is proposed for active contours. The proposed model takes the GVF vector as a 2D manifold embedded into a 4D Euclidean space, leading to the generalization of the Laplacian operator in Euclidean Space to that over manifold, and the two components of the external force are couples with each other to improve the properties of the GVF snake. The GVFOM snake has been tested with different kinds of images, and experimental results and comparison manifest that the GVFOM snake has better performance than the GVF and other state-of-the-art snakes on object separation, deep and narrow concavity convergence, weak edge protection, noise robustness while keeping some desirable properties of the GVF model such as initialization insensitivity and large capture range.

Learning Multi-level Deep Representations for Image Emotion Classification

In this paper, we propose a new deep network that learns multi-level deep representations for image emotion classification (MldrNet). Image emotion can be recognized through image semantics, image aesthetics and low-level visual features from both global and local views. Existing image emotion classification works using hand-crafted features or deep features mainly focus on either low-level visual features or semantic-level image representations without taking all factors into consideration. The proposed MldrNet combines deep representations of different levels, i.e. image semantics, image aesthetics, and low-level visual features to effectively classify the emotion types of different kinds of images, such as abstract paintings and web images. Extensive experiments on both Internet images and abstract paintings demonstrate the proposed method outperforms the state-of-the-art methods using deep features or hand-crafted features. The proposed approach also outperforms the state-of-the-art methods with at least 6% performance improvement in terms of overall classification accuracy.

Unsupervised Greenhouse Tomato Plant Segmentation Based on Self-Adaptive Iterative Latent Dirichlet Allocation from Surveillance Camera

It has long been a great concern in deep learning that we lack massive data for high-precision training sets, especially in the agriculture field. Plants in images captured in greenhouses, from a distance or up close, not only have various morphological structures but also can have a busy background, leading to huge challenges in labeling and segmentation. This article proposes an unsupervised statistical algorithm SAI-LDA (self-adaptive iterative latent Dirichlet allocation) to segment greenhouse tomato images from a field surveillance camera automatically, borrowing the language model LDA. Hierarchical wavelet features with an overlapping grid word document design and a modified density-based method quick-shift are adopted, respectively, according to different kinds of images, which are classified by specific proportions between fruits, leaves, and the background. We also utilize the feature correlation between several layers of the image to make further optimization through three rounds of iteration of LDA, with updated documents to achieve finer segmentation. Experiment results show that our method can automatically label the organs of the greenhouse plant under complex circumstances, fast and precisely, overcoming the difficulty of inferior real-time image quality caused by a surveillance camera, and thus obtain large amounts of valuable training sets.

A Hybride Active Contour Model Driven by Global and Local Image Information

In this paper, a novel active contour model based on hybrid image fitting energy which utilizes both global and local image information is proposed. Two fitting images are constructed to approximate the original image and the square of the original image. Both global and local image information are incorporated into these two fitting images. Based on these two fitting images, a hybrid image fitting energy, which is then minimized in a variational level set framework to guide the evolving contours to the desired boundaries. The proposed approach is validated by experiments on both synthetic and real images. The experiments demonstrate that the proposed model is more efficient and robust for segmenting different kinds of images compared with several typical active contour models.

Image Encryption Using Josephus Problem and Filtering Diffusion

Image encryption is an efficient visual technology to protect private images. This paper develops an image encryption algorithm utilizing the principles of the Josephus problem and the filtering technology. The encryption algorithm follows the classical diffusion and confusion structure. The principle of Josephus problem is used to shuffle the image pixels to different positions to achieve the confusion property. Using a randomly generated filter, the filtering technology can spread slight changes of the original image to all pixels of the cipher image to obtain diffusion property. The simulation results show that the developed image encryption algorithm is able to encrypt different kinds of images into cipher images with uniform distribution. The security analysis demonstrates that it has an extremely sensitive secret key, can resist various security attacks, and has a better performance than several advanced image encryption algorithms.

Comment pouvons-nous imaginer des choses que nous n’avons jamais vues ? À propos de la lettre 7 d’Augustin a Nebridius

In Letter 6 of the Augustinian corpus, Nebridius asked Augustine if the images of the imagination are not a priori, which would explain our ability to imagine things that we have never seen. In his answer, which is one of his most comprehensive analyses of the imagination, Augustine shows that our imaginative impressions are fundamentally dependent on the senses, and significantly, he defines – as Plotinus before him – the image as a «blow» (plaga) received from the senses. Under these conditions, how can we account for the fact that we sometimes imagine things that we have never perceived? To solve this problem, Augustine establishes a tripartition of the images, according to whether they are «impressed» by things we sense (sensis rebus), things we fancy (putatis), or things we reason (ratis). In the first case, we remember our perceptions. The formation of the other two types of images can be explained by the reconfiguration of memories, according to a process which is quickly presented. This article addresses three difficult points: (1) the demonstration by a reductio ad absurdum of the fundamental dependence of imagination on vision (§3); (2) the classification of the different kinds of images and more particularly the nature of the images of the third kind; (3) the final argument against the existence of a priori images, which apparently involves the soul of the world.

Image segmentation for somatic cell of milk based on niching particle swarm optimization Otsu

Aiming at the issue that it is easy to cause visual fatigue to count the quantity of milk somatic cells by microscope artificially, this paper raised automatic detection methods of counting milk somatic cells. To improve the quality of milk somatic cell's image, filtering and strengthening images with the method of DFT (Discrete Fourier Transformation). In order to increase the accuracy and speed of segmentation for somatic cell of milk images, and adjust the rapid testing requirement, it came up with the optimal threshold of image segmentation method based on niching particle swarm optimization Otsu(maximum class square error method). This method overcame the disadvantage of easily trapping in local solution and low rate in later convergence, improved the global optimization ability of the algorithmic. Using niche particle swarm optimization to optimize fitness function, it got the best segmentation threshold of Otsu, which could be used for image segmentation. At last, this paper provided handling methods for cell overlap and adhesion, through segmentation experiments using three different kinds of images of dyed milk somatic cell. Experiments showed that the methods raised in this paper are workable.

A novel pseudo-random coupled LP spatiotemporal chaos and its application in image encryption**Project supported by the National Natural Science Foundation of China (Grant Nos. 61672124, 61370145, and 61173183), the Password Theory Project of the 13th Five-Year Plan National Cryptography Development Fund, China (Grant No. MMJJ20170203), the Program for New Century Excellent Talents in Fujian Province University, and the Natural Science

In this paper, first, we investigate a novel one-dimensional logistic-PWLCM (LP) modulation map which is derived from the logistic and PWLCM maps. Second, we propose a novel PCLML spatiotemporal chaos in pseudo-random coupling method that can accelerate the system behavior of the fully spatial chaos. Here, because the better chaotic properties include a wide range of parameter settings and better ergodicity than a logistic map, the LP is used in PCLML as f(x). The Kolmogorov–Sinai entropy density and universality and the bifurcation diagram are employed to investigate the chaotic behaviors of the proposed PCLML model. Finally, we apply the LP and PCLML chaotic systems to image encryption to improve the effectiveness and security of the encryption scheme. By combining self-generating matrix model M and dynamic substitution box (S-Box) methods, we design a new image encryption algorithm. Numerical simulations and security analysis have been carried out to demonstrate that the proposed algorithm has a high security level and can efficiently encrypt several different kinds of images into random-like images.

A comprehensive survey on content based image retrieval system and its application in medical domain

Content Based Image Retrieval (CBIR) is an important and widely used technique for retrieval of different kinds of images from large database. Collection of information in database are available in different formats such as text, image, graph, chart etc. Here, our focus is on information which is available in the form of images. Searching and retrieval of the image from a large amount of database is difficult problem because it uses the image visual information such as shape, text and color for indexing and representation of an image. For efficient CBIR system, there is a need to develop different kinds of retrieval methods using feature extraction, similarity matching etc. Text Based Image Retrieval systems are used in many hospitals, but for large databases these are inefficient. To solve this problem, CBIR systems are proposed to retrieve matching images from database using automated feature extraction method. At present, medical imaging field finds extensive growth in the generation and evaluation of various types of medical images which are high inconsistency, usually fused and the combination of various minor composition structures. For easy retrieval, need to be development of feature extraction and image classification methods. Different methods are used for different kinds of medical images. The Radiology department and Cardiology department are the largest producers of medical images and the patient abnormal images can be stored with the normal images. CBIR uses query image as input and it retrieves the images, which are similar to the query more efficiently and effectively. This paper provides a comprehensive Survey about CBIR system and its one of the major application in medical domain.