Set Of Sample Images Research Articles

A Super Encryption Approach for Enhancing Digital Security using Column Transposition - Hill Cipher for 3D Image Protection

Image encryption is an indispensable technique in the realm of information security, serving as a pivotal mechanism to safeguard visual data against unauthorized access and potential breaches. This study scrutinizes the effectiveness of merging columnar transposition with the Hill Cipher methodologies, unveiling specific metrics from a curated set of sample images. Notably, employing column transposition with the key "JAYA" and the Hill Cipher with the key "UDINUSSMG," the encrypted images underwent rigorous evaluation. 'Lena.png' demonstrated an MSE of 513.32 with a PSNR of 7.89 dB, while 'Peppers.png' and 'Baboon.png' recorded MSE values of 466.67 and 423.92, respectively, with corresponding PSNR figures of 7.12 dB and 7.31 dB. Across all samples, a consistent BER of 50.00% indicated uniform error propagation, while entropy values settled uniformly at 7.9999, highlighting consistent data complexity. While the findings underscore a consistent error rate and complexity, there's a compelling need for further refinement to enhance image quality and security. Moreover, the study proposes future research avenues exploring a three-layer super encryption paradigm, amalgamating columnar transposition, Hill Cipher, and other robust algorithms. This approach aims to fortify encryption methodologies against evolving threats and challenges in data protection, offering heightened resilience and efficacy in safeguarding sensitive information.

Person Identification System Using Periocular Biometrics Based on Hybrid Optimal Dense Capsule Network

Person identification using periocular images has emerged as a challenging scenario in efficient biometric analysis, particularly under less constrained environments. Accurate recognition is significant in rendering effective measures during the COVID-19 pandemic. In this research paper, the person identification process is performed based on a deep learning model. Several effectual methods have already been developed, but certain drawbacks still exist, like deteriorated image quality, high computational cost, increased error, less training ability, a requirement of high storage space and accuracy rate degradation. Hence, the proposed work introduces a Hybrid Optimal Dense Capsule network-based Periocular biometric system (HodCP) to conquer these demerits. The proposed work involves pre-processing, dimensionality reduction, hybrid feature extraction and Image matching. The pre-processing step is undertaken using Parabolic Contrast Enhancement (PCE) to balance the image contrast and enhance the image quality. Then the Two-Dimensional Principal Component Analysis (2D_PCA) is employed to minimize the image dimensionality. Deep features are extracted in the hybrid feature extraction process using Dense Convolutional-121 Capsule Network (DenseCapsNet). The net loss and hyperparameter tuning are performed through African Vultures Optimization (AVO) algorithm. Finally, image matching is performed using Weighted Distance Similarity (WDS), which identifies the similarity between the query image and a set of image samples based on the distance score. The simulation tool used for analyzing better performance is PYTHON. The data required to process the proposed work are collected from four benchmark datasets. The proposed work provides a better accuracy rate of CASIA-Iris-Mobile-V1.0 (99.01%), UBIPr (99.12%), Facemask detection dataset (98.67%) and Glasses versus without glasses dataset (98.83%), which is superior to the existing methods.

Production of German Picture Postcards at the Western Front 1915–1916 as Exemplified by the Imagery of the Church Bell of Marquillies (Département du Nord, France)

During World War I the soldiers’ life at and behind the frontline was captured by personal photography. While heavily regulated and censored on the allied side, conditions were more relaxed for German soldiers, and for German officers, in particular. Drawing on a large sample set of images of the same subject matter, a French church bell with a patriotic, anti-German inscription, this paper surveys the private production of picture postcards by German soldiers. Initially photographed by a range of individuals, some images were eventually produced as printed lithographed postcards by regional German publishers. The processes and limitations of the personal versus commercial production of picture postcards are discussed.

Convolutional Neural Network Feature Extraction Using Covariance Tensor Decomposition

This work describes a new method to extract image features using tensor decomposition to model data. Given a set of sample images, we extract patches from images, compute the covariance tensor for all patches, decompose with the Tucker model, and obtain the most critical features from a tensor core. To extract features, we factorize the covariance tensor (CovTen) into its core and propose a new interpretation of the resultant tensor structure, which holds relevant features in a block-wise arrangement (also named filters, weights, or kernels). This tensorial representation allows preserving the spatial structure, learning multichannel filters, and establishing linear dependence between dimensions, reducing the dimensional complexity (the curse of dimensionality). Thus, the proposed method generates filters by a single feed-forward step using a few samples per class as low as 1. Besides, in kernel generation, labels are not needed. The obtained features were extensively tested using a convolutional neural network for classification. All tests were conducted under the VGG architecture conventions. The experiments helped us identify the proposed method’s advantages versus traditional convolutional neural networks in inference capacity and kernels initialization. We also performed experiments to select hyperparameters (nonLinearity, max pooling, samples, filter size) according to their performance. The inference capacity results showed an increased classification accuracy around 67% with CIFAR 10, 64% with CIFAR 100, and 98% with MNIST, using 10,100,1000 samples with a single feed-forward training. On the other hand, the initialization experiments showed the feature extraction capability versus available initializers (He random, He uniform, Glorot, random), confirming linear tensor constraints’ usefulness to generate features. Using the method as kernel initializer returns comparable findings with state of the art around 91% with CIFAR 10, 72% with CIFAR 100, and 99% with MNIST.

A Hybrid Approach for Semantic Image Annotation

In this study, a framework that generates natural language descriptions of images within a controlled environment is proposed. Previous work on neural networks mostly focused on choosing the right labels and/or increasing the number of related labels to depict an image. However, creating a textual description of an image is a completely different phenomenon, structurally, syntactically, and semantically. The proposed semantic image annotation framework presents a novel combination of deep learning models and aligned annotation results derived from the instances of the ontology classes to generate sentential descriptions of images. Our hybrid approach benefits from the unique combination of deep learning and semantic web technologies. We detect objects from unlabeled sports images using a deep learning model based on a residual network and a feature pyramid network, with the focal loss technique to obtain predictions with high probability. The proposed framework not only produces probabilistically labeled images, but also the contextual results obtained from a knowledge base exploiting the relationship between the objects. The framework’s object detection and prediction performances are tested with two datasets where the first one includes individual instances of images containing everyday scenes of common objects and the second custom dataset contains sports images collected from the web. Moreover, a sample image set is created to obtain annotation result data by applying all framework layers. Experimental results show that the framework is effective in this controlled environment and can be used with other applications via web services within the supported sports domain.

Cellbow: a robust customizable cell segmentation program

BackgroundTime‐lapse live cell imaging of a growing cell population is routine in many biological investigations. A major challenge in imaging analysis is accurate segmentation, a process to define the boundaries of cells based on raw image data. Current segmentation methods relying on single boundary features have problems in robustness when dealing with inhomogeneous foci which invariably happens in cell population imaging.MethodsCombined with a multi‐layer training set strategy, we developed a neural‐network‐based algorithm — Cellbow.ResultsCellbow can achieve accurate and robust segmentation of cells in broad and general settings. It can also facilitate long‐term tracking of cell growth and division. To facilitate the application of Cellbow, we provide a website on which one can online test the software, as well as an ImageJ plugin for the user to visualize the performance before software installation.ConclusionCellbow is customizable and generalizable. It is broadly applicable to segmenting fluorescent images of diverse cell types with no further training needed. For bright‐field images, only a small set of sample images of the specific cell type from the user may be needed for training.

Corn disease recognition based on the Convolutional Neural Network with a small sampling size

Crop disease management influences yield and quality, yet identifying corn diseases is still difficult. High labor costs, small number of sample, and uneven disease distributions contribute to the difficulty. We propose an improved Convolutional Neural Network (CNN) model based on the transfer learning method for disease identification. The sample image set was enhanced by rotation and roll-over, then the migrated MobileNetV2 model was used to train the image data set for corn diseases. The Focal Loss function was used to improve the neural network loss function, and the Softmax classification method was used for corn disease image recognition. The training set accuracy, validation set accuracy, weight, run time, and the number of parameter in six models were experimentally compared. The verification set accuracy rates were 93.88% (AlexNet), 95.48% (GoogleNet), 91.69% (Vgg16), 97.67% (RestNet34), 96.21% (MobileNetV2), and 97.23% (migrated MobileNetV2). The migrated MobileNetV2 was 97.23% accurate and weighed 8.69 MB. Confounding the MobileNetV2 model improved the recognition accuracy by 1.02% and reduced the training speed by 6 350 seconds compared to the unconfounded model. The migrated MobileNetV2 model had the best corn disease recognition ability with a small sampling size; improved convergence speed, reduced model calculations, and greatly improved the recognition time.

Training the Image Classifier with and without Data Augmentation

The main objective of this paper is to train the image classifier using Convolutional Neural Networks with tensorflow architecture. The proposed paper focus on systematic approaches in classifying the sample set of images using Convolutional Neural Networks. The CNN model with activation function thus classifies the dataset into two categories exactly like human. Thus, the paper highlights the importance of augmentation by comparing their accuracies.

Application of Principal Component Analysis and Adaptive Median Filter to Improve Real-Time Prostate Capsula Detection

This study investigated the potential for using Principal Component Analysis (PCA) and Adaptive Median Filter (AMF) to improve real-time prostate capsula detection with the traditional Region-based Fully Convolutional Network (R-FCN), Faster Region-based Convolutional Neural Network (Faster R-CNN), You Only Look Once-Version 3 (YOLOv3) and Single Shot Multibox Detector (SSD) algorithms. The processing steps included data augmentation (rotation, vertical flip, and horizontal flip) to increase the size of the dataset from 149 to 596 images, PCA-based feature extraction, AMF-based image denoising and a training phase incorporating the sample image set. The data were then used to test a series of combined methods that were applied to the detection of prostate capsula (PC). The results showed that application of PCA and AMF to Faster R-CNN increased the mean average precision (mAP) for the PC images by 9.4%. The application of PCA and AMF to R-FCN, YOLOv3 and SSD increased the mAP by 7.22%, 7.14% and 3.29% for the same dataset, respectively. This study represents the first application of PCA and AMF to traditional object detection algorithms, such as R-FCN, Faster R-CNN, YOLOv3, or SSD, and the improved mAP results suggest that this approach is a robust tool for improving multiple network architectures.

A Belief-Theoretical Approach to Example-Based Pose Estimation

In example-based human pose estimation, the configuration of an evolving object is sought given visual evidence, having to rely uniquely on a set of sample images. We assume here that, at each time instant of a training session, a number of feature measurements is extracted from the available images, while ground truth is provided in the form of the true object pose. In this scenario, a sensible approach consists in learning maps from features to poses, using the information provided by the training set. In particular, multivalued mappings linking feature values to set of training poses can be constructed. To this purpose we propose a belief modeling regression (BMR) approach in which a probability measure on any individual feature space maps to a convex set of probabilities on the set of training poses, in a form of a belief function. Given a test image, its feature measurements translate into a collection of belief functions on the set of training poses which, when combined, yield there an entire family of probability distributions. From the latter either a single central pose estimate or a set of extremal ones can be computed, together with a measure of how reliable the estimate is. Contrarily to other competing models, in BMR the sparsity of the training samples can be taken into account to model the level of uncertainty associated with these estimates. We illustrate BMR's performance in an application to human pose recovery, showing how it outperforms our implementation of both relevant vector machine and Gaussian process regression. Finally, we discuss motivation and advantages of the proposed approach with respect to its most direct competitors.

A simple ImageJ macro tool for analyzing mitochondrial network morphology in mammalian cell culture

Mitochondria exist in a dynamic cycle of fusion and fission whose balance directly influences the morphology of the ‘mitochondrial network’, a term that encompasses the branched, reticular structure of fused mitochondria as well as the separate, punctate individual organelles within a eukaryotic cell. Over the past decade, the significance of the mitochondrial network has been increasingly appreciated, motivating the development of various approaches to analyze it. Here, we describe the Mitochondrial Network Analysis (MiNA) toolset, a relatively simple pair of macros making use of existing ImageJ plug-ins, allowing for semi-automated analysis of mitochondrial networks in cultured mammalian cells. MiNA is freely available at https://github.com/StuartLab. The tool incorporates optional preprocessing steps to enhance the quality of images before converting the images to binary and producing a morphological skeleton for calculating nine parameters to quantitatively capture the morphology of the mitochondrial network. The efficacy of the macro toolset is demonstrated using a sample set of images from SH-SY5Y, C2C12, and mouse embryo fibroblast (MEF) cell cultures treated under different conditions and exhibiting hyperfused, fused, and fragmented mitochondrial network morphologies.

Using Non-symmetry and Anti-packing Representation Model for Object Detection

In this paper, we present a non-symmetry and anti-packing object pattern representation model (NAM) for object detection. A set of distinctive sub-patterns (object parts) is constructed from a set of sample images of the object class; object pattern are then represented using sub-patterns, together with spatial relations observed among the sub-patterns. Many feature descriptors can be used to describe these sub-patterns. he NAM model codes the global geometry of object category, and the local feature descriptor of sub-patterns deal with the local variation of object. By using Edge Direction Histogram (EDH) features to describe local sub-pattern contour shape within an image, we found that richer shape information is helpful in improving recognition performance. Based on this representation, several learning classifiers are used to detect instances of the object class in a new image. The experimental results on a variety of categories demonstrate that our approach provides successful detection of the object within the image.

Evaluating Image Recognition Efficiency using a Self-Organizing Map

Recognition and classification of images is an extremely topical interdisciplinary area that covers image processing, computer graphics, artificial intelligence, computer vision, and pattern recognition, resulting in many applications based on contemporary mobile devices. Developing reliable recognition schemes is a difficult task to accomplish. It depends on many factors, such as illumination, acquisition quality and the database images, in particular, their diversity. In this paper we study how the data diversity affects decision making in image recognition, presenting a database driven classificationerror predictor. The predictor is based on a hybrid approach that combines a self-organizing map together with a probabilistic logical assertion method. By means of a clustering approach, the model provides fast and efficient assessment of the image database heterogeneity and, as expected, indicates that such heterogeneity is of paramount importance for robust recognition. The practicality of the model is demonstrated using a set of image samples collected from a standard traffic sign database publicly available by the UK Department for Transport.

TU-FG-209-12: Treatment Site and View Recognition in X-Ray Images with Hierarchical Multiclass Recognition Models

Purpose: To investigate an approach of automatically recognizing anatomical sites and imaging views (the orientation of the image acquisition) in 2D X-ray images. Methods: A hierarchical (binary tree) multiclass recognition model was developed to recognize the treatment sites and views in x-ray images. From top to bottom of the tree, the treatment sites are grouped hierarchically from more general to more specific. Each node in the hierarchical model was designed to assign images to one of two categories of anatomical sites. The binary image classification function of each node in the hierarchical model is implemented by using a PCA transformation and a support vector machine (SVM) model. The optimal PCA transformation matrices and SVM models are obtained by learning from a set of sample images. Alternatives of the hierarchical model were developed to support three scenarios of site recognition that may happen in radiotherapy clinics, including two or one X-ray images with or without view information. The performance of the approach was tested with images of 120 patients from six treatment sites – brain, head-neck, breast, lung, abdomen and pelvis – with 20 patients per site and two views (AP and RT) per patient. Results: Given two images in known orthogonal views (AP and RT), the hierarchical model achieved a 99% average F1 score to recognize the six sites. Site specific view recognition models have 100 percent accuracy. The computation time to process a new patient case (preprocessing, site and view recognition) is 0.02 seconds. Conclusion: The proposed hierarchical model of site and view recognition is effective and computationally efficient. It could be useful to automatically and independently confirm the treatment sites and views in daily setup x-ray 2D images. It could also be applied to guide subsequent image processing tasks, e.g. site and view dependent contrast enhancement and image registration. The senior author received research grants from ViewRay Inc. and Varian Medical System.

High-performance on-road vehicle detection with non-biased cascade classifier by weight-balanced training

In this paper, we propose a cascade classifier for high-performance on-road vehicle detection. The proposed system deliberately selects constituent weak classifiers that are expected to show good performance in real detection environments. The weak classifiers selected at a cascade stage using AdaBoost are assessed for their effectiveness in vehicle detection. By applying the selected weak classifiers with their own confidence levels to another set of image samples, the system observes the resultant weights of those samples to assess the biasing of the selected weak classifiers. Once they are estimated as biased toward either positive or negative samples, the weak classifiers are discarded, and the selection process is restarted after adjusting the weights of the training samples. Experimental results show that a cascade classifier using weak classifiers selected by the proposed method has a higher detection performance.

FEATURE EXTRACTION THROUGH CROSS-PHASE CONGRUENCY FOR FACIAL EXPRESSION ANALYSIS

Human face analysis has attracted a large number of researchers from various fields, such as computer vision, image processing, neurophysiology or psychology. One of the particular aspects of human face analysis is encompassed by facial expression recognition task. A novel method based on phase congruency for extracting the facial features used in the facial expression classification procedure is developed. Considering a set of image samples comprising humans expressing various expressions, this new approach computes the phase congruency map between the samples. The analysis is performed in the frequency space where the similarity (or dissimilarity) between sample phases is measured to form discriminant features. The experiments were run using samples from two facial expression databases. To assess the method's performance, the technique is compared to the state-of-the art techniques utilized for classifying facial expressions, such as Principal Component Analysis (PCA), Independent Component Analysis (ICA), Linear Discriminant Analysis (LDA), and Gabor jets. The features extracted by the aforementioned techniques are further classified using two classifiers: a distance-based classifier and a Support Vector Machine-based classifier. Experiments reveal superior facial expression recognition performance for the proposed approach with respect to other techniques.

Light source estimation of outdoor scenes for mixed reality

Illumination consistency is important for photorealistic rendering of mixed reality. However, it is usually difficult to acquire illumination conditions of natural environments. In this paper, we propose a novel method for evaluating the light conditions of a static outdoor scene without knowing its geometry, material, or texture. In our method, we separate respectively the shading effects of the scene due to sunlight and skylight through learning a set of sample images which are captured with the same sun position. A fixed illumination map of the scene under sunlight or skylight is then derived reflecting the scene geometry, surface material properties and shadowing effects. These maps, one for sunlight and the other for skylight, are therefore referred to as basis images of the scene related to the specified sun position. We show that the illumination of the same scene under different weather conditions can be approximated as a linear combination of the two basis images. We further extend this model to estimate the lighting condition of scene images under deviated sun positions, enabling virtual objects to be seamlessly integrated into images of the scene at any time. Our approach can be applied for online video process and deal with both cloudy and sun shine situations. Experiment results successfully verify the effectiveness of our approach.

Near real-time classification of optical coherence tomography data using principal components fed linear discriminant analysis

An optical coherence tomography (OCT) prediction algorithm is designed and tested on a data set of sample images (taken from vegetables and porcine tissues) to demonstrate proof of concept. Preprocessing and classification of data are fully automated, at a rate of 60,000 A-scansmin on a standard computer and can be considered to deliver in near real-time. A data set consisting of nine groups was classified correctly in 82% of cases after cross-validation. Sets of fewer groups reach higher rates. The algorithm is able to distinguish groups with strong visual similarity among several groups of varying resemblance. Surface recognition and normalizing to the surface are essential for this approach. The mean divided by the standard deviation is a suitable descriptor for reducing a set of surface normalized A-scans. The method enables grouping of separate A-scans and is therefore straightforward to apply on 3-D data. OCT data can reliably be classified using principal component analysis combined with linear discriminant analysis. It remains to be shown whether this algorithm fails in the clinical setting, where interpatient variation can be greater than the deviations that are investigated as a disease marker.

Band Selection in Multispectral Images by Minimization of Dependent Information

<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> In this paper, a band selection technique for hyperspectral image data is proposed. Supervised feature extraction techniques allow a reduction of the dimensionality to extract relevant features through a labeled training set. This implies an analysis of the existing class distributions, which usually means, in the case of hyperspectral imaging, a large number of samples, making the labeling process difficult. A possible alternative could be the use of information measures, which are the basis of the proposed method. The present approach basically behaves as an unsupervised feature selection criterion, to obtain the relevant spectral bands from a set of sample images. The relations of information content between spectral bands are analyzed, leading to the proposed technique based on the minimization of the dependent information between spectral bands, while trying to maximize the conditional entropies of the selected bands. </para>

Community design of a light rail transit-oriented development using casewise visual evaluation (CAVE)

This paper proposes the casewise visual evaluation or CAVE, methodology and discusses its application to the participatory design of a transit-oriented development (TOD) in Louisville, Kentucky. CAVE is a fuzzy logic-based non-linear visual preference modeling system designed to provide design element guidance from composite visual scenarios under conditions of sparse data. The context of application in a low-income urban neighborhood is detailed. An architectural expert's design vocabulary allows model input and output to be structured. A small set of image samples was scored for preference using anonymous electronic polling in distributed neighborhood forums. Using fuzzy set theoretic software a community preference knowledge base (PKB) was built and interrogated. Four critical TOD design dimensions were selected: height, typology, density, and open space type. Preferred TOD design combinations were identified using the PKB and discussed. This project shows that CAVE can provide context-specific guidance for urban designers and that its strengths in effectively devolving design input and capturing local preferences are recognized by the community. The paper highlights the necessity for advanced geovisual analytic methods to be embedded into a structured public involvement (SPI) process.