Large Size Images Research Articles

Improving the Efficiency and the Accuracy of 2D Gel Electrophoresis Spot Detection Using Graphics Processing Units

Background: Proteomics was built around two-dimensional (2D) gel electrophoresis. Accurately analyzing the images generated from 2D gel electrophoresis for spot detection is a timeconsuming process especially for high-resolution and large images. Objective: In this paper, we present an accurate GPU-accelerated software tool for the detection and quantification of protein spots in 2D gel electrophoresis images. Method: We adopt pixel-based approach that employs wavelet relational fuzzy C-means clustering and distance transform to detect and quantify the protein spots. This pixel-based spot detection approach is more accurate than the contour-based approaches; however it is compute-intensive. So, along with algorithmic optimizations, we present the mapping and optimization of the pixel-based spot detection algorithm onto graphics processing units (GPUs); including NVIDIA and AMD GPUs. Results: This approach is proved to exhibit better spot detection in quantitative comparisons with the commercial software tools. Specifically, it achieves a degree of improvement in F-measure of 21.237% and 11.716% on the average compared to Delta2D and Melanie, respectively. We carry out experiments on images of large size and high resolution for healthy and diseased samples. Our implementation has accomplished up to five orders of magnitude speedup compared to the single-threaded MATLAB implementation. Conclusion: We proposed an accurate and efficient tool for detecting and quantifying the protein spots in 2D Gel Electrophoresis images. Our tool outperforms commercial software tools in accuracy of detecting protein spots while achieving significantly better performance than single-threaded MATLAB implementation by utilizing the GPU accelerators. Keywords: Image processing, 2D gel electrophoresis, heterogeneous computing, parallel computing, GPU, OpenCL.

Büyükten Küçüğe Oto-kodlayıcılar ile dişlerin konumlandırılması*

Localization of teeth is a prerequisite task for most of the computerized methods for dental images such as medical diagnosis and human identification. Classical deep learning architectures like convolutional neural networks and auto-encoders seem to work well for tooth detection, however, it is non-trivial because of the large image size. In this study, a coarse-to-fine stacked auto-encoder architecture is presented for detection of teeth in dental panoramic images. The proposed architecture involves cascaded stacked auto-encoders where sizes of the input patches increase with the successive steps. Only the detected candidate tooth patches are fed into the successive layers, thus the irrelevant patches are eliminated. The proposed architecture decreases the cost of detection process while providing precise localization. The method is tested and validated on a dataset containing 206 dental panoramic images and the results are promising.

Indexing near-duplicate images in web search using minhash algorithm

Near-duplicate images cause problems of redundancy and copyright infringement in large image collections. The trouble is minor in the web, where appropriation of images without acknowledgment of source is prevalent. Near duplicates can be exact copies or else differ slightly in their visual content. Near-duplicate detection has received substantial attention over the past few years due to the applications in copyright enforcement, organizing large size image databases, increasing focus on image search, redundancy elimination of logos, managing storage space by removing duplication, etc. In the paper, a method has been proposed for Indexing Near-Duplicate Images in the Web Search. First image enhancement is done in user query image then features are extracted based on SURF (Speeded up Robust Features) that is to extract the local invariant features of each image. After this similarity measure is calculated among the feature extracted images using min-hash algorithm. Finally, Locality Sensitive Hashing (LSH) is used for indexing near duplicate images based on user query. We demonstrate that our indexing approach is highly effective for collections of up to a few hundred thousand images.

Classification of Content based Medical Image Retrieval Using Texture and Shape feature with Neural Network

Medical image classification and retrieval systems have been finding extensive use in the areas of image classification according to imaging modalities, body part and diseases. One of the major challenges in the medical classification is the large size images leading to a large number of extracted features which is a burden for the classification algorithm and the resources. In this paper, a novel approach for automatic classification of fundus images is proposed. The method uses image and data pre-processing techniques to improve the performance of machine learning classifiers.<em> </em>Some predominant image mining algorithms such as Classification, Regression Tree (CART), Neural Network, Naive Bayes (NB), Decision Tree (DT) K-Nearest Neighbor. The performance of MCBIR systems using texture and shape features efficient. . The possible outcomes of a two class prediction be represented as True positive (TP), True negative (TN), False Positive (FP) and False Negative (FN).

Realization of software based imaging energy analyzer on GPU

Here, the realization of the Filtering the Effect of Chromatic Aberration (FECA) method is presented as Software Based Imaging Energy Analyzer (SBIEA) on an NVIDA Tesla K40 GPU. This method makes possible the correction of chromatic aberration and, therefore, spectrometry, as well as, real- and k-space monochromatic imaging by rapidly calculated spectral image sequences of monochromatic images in light and charged particle optics without the application of additional energy filters. The GPU accelerated realization of this method provides a good solution with reasonable calculation time on large size image sequences and opens new direction toward the better quality monochromatic real- and k-space imaging, as well as, the developments of software based instrumentation. The presented GPU accelerated realization of the FECA-SBIEA method provides promising alternative solution for making fast and accurate monochromatic spectral imaging that can be better than the usually applied electrostatic and magnetic analyzers due to the overlapping effect of different energy images especially in the case of large acceptance angle optics.

Leveraging content similarity among VMI files to allocate virtual machines in cloud

To meet a myriad of customers’ demands, a large number of virtual machines (VMs) have to be provisioned simultaneously in cloud data centers. Provisioning is usually time consuming due to the large size of virtual machine image (VMI) file that needs to be transferred via networks. To address this issue, researchers attempt to leverage the content similarity among different VMI files to reduce the volume of transferred data. In the VM provisioning, the VM packing problem that minimizes the number of physical machines is another important issue. In this paper, our goal is to find a solution that tries to pack VMs to the minimum number of PMs as well as significantly reduces the total amount of transferred data. We formally define the problem of VM packing and minimizing the data transferring in the VM provisioning, named RTVD-VA. We first propose an approximation algorithm to minimize the amount of transferred VMI data when provisioning K VMs with the same size to a single physical machine. We then extend the algorithm to address the scenario of multiple PMs when using the minimum number of PMs. Based on the above two approximation algorithms, we propose a heuristic algorithm, namely Balance-Placement, to solve the problem in general cases. Our simulation results show that Balance-Placement outperforms existing solutions like PSO and Greedy-Cache and achieves the least amount of transferred data and the minimum number of used PMs in most scenarios.

Segmentation and classification of hyperspectral images using CHV pattern extraction grid

Recently, most critical challenge tasks in remote sensing applications are the segmentation and classification of hyperspectral images (HSI). Data dependency and relation among the frequency bands are the major drawbacks in the traditional HSI segmentation and classification techniques for large-size images. To segment and classify the regions in HSI, the clear description of the edge information is necessary. The presence of noise needs to be removed prior to the clear edge information extraction. To alleviate such issues, the new way of pattern extraction is proposed in this paper. Initially, the fuzzy-based adaptive median filtering removes the noise present in the image which is the prior step for clear information extraction. The integration of circular local binary pattern with the sorted local horizontal vector (CHV) patterns extracts the clear edge information necessary for classification. The intensity values from the color-based feature extraction and the CHV pattern are used to construct the relevance vector machine kernel with the limits. The comparative analysis between the proposed CHV-based pattern extraction grid with the existing techniques regarding the various metrics such as accuracy, sensitivity, specificity, rate variations and coefficient variations assures the effectiveness of proposed work in remote sensing applications.

Massively parallel palmprint identification system using GPU

Automated human authentication is becoming increasingly important in today’s world due to increased need of security and surveillance applications deployed in almost all premises and installations. In this regard, palmprint biometric based identification has gained a lot of attention in recent years. However, due to large size of palmprint images and presence of principal lines, wrinkles, creases, and other noises, there are large number of inaccurate minutiae present. The computational requirement of palmprint identification is also quite large and it takes a lot of time to find identity of a palmprint in large database. In this study, a novel palmprint identification solution has been proposed that increases the accuracy of minutia detection based on improved frequency estimation and a novel region-quality based minutia extraction algorithm. Furthermore, a novel, efficient and highly accurate minutiae based encoding and matching algorithm is proposed that is designed to achieve maximum parallelism, and it is further accelerated using graphical processing unit. The results of the proposed palmprint identification demonstrate high accuracy and much faster identification speeds in comparison with current state of the art. Therefore, it can be considered as a robust, efficient and practical solution for palmprint based identification systems.

Enhancement of the Box-Counting Algorithm for fractal dimension estimation

The box-counting (BC) method is frequently used as a measure of irregularity and roughness of fractals with self-similarity property due to its simplicity and high reliability. It requires a proper choice of the number of box sizes, corresponding sizes, and size limits to guarantee the accuracy of the fractal dimension estimation. Most of the existing BC methods utilize the geometric-step method, which causes a lack of fitting data points and wasted pixels for images of large size and/or arbitrary size. This paper presents a BC algorithm in combination with a novel sampling method and fractional box-counting method which will allow us to overcome some of limitations evident in the conventional BC method. The new sampling method introduces a partial competition based on the coverage of box sizes and takes more number of box sizes than the geometric-step method. To circumvent the border problem occurring for images of arbitrary size, the fractional box-counting method allows the number of the boxes to be real, rather than integer. To show its feasibility, the proposed method is applied to a set of fractal images of exactly known fractal dimension.

Classification of large-sized hyperspectral imagery using fast machine learning algorithms

We present a framework of fast machine learning algorithms in the context of large-sized hyperspectral images classification from the theoretical to a practical viewpoint. In particular, we assess the performance of random forest (RF), rotation forest (RoF), and extreme learning machine (ELM) and the ensembles of RF and ELM. These classifiers are applied to two large-sized hyperspectral images and compared to the support vector machines. To give the quantitative analysis, we pay attention to comparing these methods when working with high input dimensions and a limited/sufficient training set. Moreover, other important issues such as the computational cost and robustness against the noise are also discussed.

Experimental analysis of image encryption using elgamal and block-substitution method for color images

This paper presents an encryption technique for color images. In this method byte code is extracted from the color image which is converted into binary data. Cipher text is generated by applying Block substitution encryption method on the obtained binary data. The effectiveness of the proposed method has been estimated by computing chi-square value. Obtained results show that the encryption method is suitable for both symmetric and asymmetric images of larger size.

Análisis descriptivo del fotoperiodismo narrativo en los diarios digitales Folha de Sao Paulo y The Guardian

Ante los escasos estudios existentes en este campo, el presente trabajo desarrolla un análisis de los nuevos productos de fotoperiodismo narrativo en prensa digital, sus componentes y aspectos sustantivos, centrado en los diarios digitales Folha de Sao Paulo y The Guardian. La muestra consta de 35 piezas con un total de 899 fotografías, de las cuales 351 (39,1%) corresponden a Folha de Sao Paulo y 548 (60,9%) a The Guardian. Apoyándose en la metodología del Análisis de contenido, se emplea una ficha de diseño propio, con indicadores poco contemplados en trabajos sobre fotografía, como diseño estructural, funcionalidad o integración de contenidos multimedia. Los resultados indican que estos productos presentan formatos y configuraciones diferentes, poseen una estructura clara, extensión media-alta y están dotados de funcionalidades sencillas. La buena jerarquización, variedad, gran tamaño y calidad de las imágenes otorga un alto impacto visual. Los elementos textuales complementan y aclaran el sentido lógico del relato. La incorporación de contenidos audiovisuales y links es discreta, pero bien contextualizada. Todo ello supone un notable avance estético-comunicativo respecto a los modos convencionales de tratamiento de la fotografía en la prensa digital.

Large size single image fast defogging and the real time video defogging FPGA architecture

Since most image defogging methods require complex image filtering computation, they cannot work effectively under large size real time image and video scenarios. In this work, targeting this problem, a large size single image computation acceleration bilateral filtering based defogging (CABFD) scheme is presented. And aiming for large size video real time defogging on smart TV, a simplified filtering alternative and the corresponding FPGA defogging architecture are also introduced. The experiments and the comparisons show that the proposed large size image fast defogging approach is effective and practical. And the proposed FPGA defogging architecture can be directly applied to realize Full HD (1920 × 1080) video displaying with real time synchronous defogging.

Large scale tissue histopathology image classification, segmentation, and visualization via deep convolutional activation features

BackgroundHistopathology image analysis is a gold standard for cancer recognition and diagnosis. Automatic analysis of histopathology images can help pathologists diagnose tumor and cancer subtypes, alleviating the workload of pathologists. There are two basic types of tasks in digital histopathology image analysis: image classification and image segmentation. Typical problems with histopathology images that hamper automatic analysis include complex clinical representations, limited quantities of training images in a dataset, and the extremely large size of singular images (usually up to gigapixels). The property of extremely large size for a single image also makes a histopathology image dataset be considered large-scale, even if the number of images in the dataset is limited.ResultsIn this paper, we propose leveraging deep convolutional neural network (CNN) activation features to perform classification, segmentation and visualization in large-scale tissue histopathology images. Our framework transfers features extracted from CNNs trained by a large natural image database, ImageNet, to histopathology images. We also explore the characteristics of CNN features by visualizing the response of individual neuron components in the last hidden layer. Some of these characteristics reveal biological insights that have been verified by pathologists. According to our experiments, the framework proposed has shown state-of-the-art performance on a brain tumor dataset from the MICCAI 2014 Brain Tumor Digital Pathology Challenge and a colon cancer histopathology image dataset.ConclusionsThe framework proposed is a simple, efficient and effective system for histopathology image automatic analysis. We successfully transfer ImageNet knowledge as deep convolutional activation features to the classification and segmentation of histopathology images with little training data. CNN features are significantly more powerful than expert-designed features.

A Fast Reliable Image Quality Predictor by Fusing Micro- and Macro-Structures

A fast reliable computational quality predictor is eagerly desired in practical image/video applications, such as serving for the quality monitoring of real-time coding and transcoding. In this paper, we propose a new perceptual image quality assessment (IQA) metric based on the human visual system (HVS). The proposed IQA model performs efficiently with convolution operations at multiscales, gradient magnitude, and color information similarity, and a perceptual-based pooling. Extensive experiments are conducted using four popular large-size image databases and two multiply distorted image databases, and results validate the superiority of our approach over modern IQA measures in efficiency and efficacy. Our metric is built on the theoretical support of the HVS with lately designed IQA methods as special cases.

Block compressive sensing of image and video with nonlocal Lagrangian multiplier and patch-based sparse representation

Although block compressive sensing (BCS) makes it tractable to sense large-sized images and video, its recovery performance has yet to be significantly improved because its recovered images or video usually suffer from blurred edges, loss of details, and high-frequency oscillatory artifacts, especially at a low subrate. This paper addresses these problems by designing a modified total variation technique that employs multi-block gradient processing, a denoised Lagrangian multiplier, and patch-based sparse representation. In the case of video, the proposed recovery method is able to exploit both spatial and temporal similarities. Simulation results confirm the improved performance of the proposed method for compressive sensing of images and video in terms of both objective and subjective qualities.

Acceleration of super-resolution for multispectral images using self-example learning and sparse representation

Super-resolution obtains a new high resolution image from single or multiple low-resolution images for the same scene. Recently compressive sensing has been successfully used in signal recovery. This paper investigates the potential reduction in execution time by selecting tasks that can be parallelized using general purpose computing on graphics processing units (GPGPU) and Compute Unified Device Architecture (CUDA). The self example based super-resolution method via sparse representation and morphological component analysis is proposed for satellite images. Orthogonal Matching Pursuit (OMP) is used in the high resolution image reconstruction phase. The complexity of each module in the OMP algorithm is analyzed and its bottlenecks are identified at the projection module and the least squares module. The projection module is accelerated by adopting a GPU tiled matrix vector multiplication. To speedup the least square module, a GPU implementation of the Jordan matrix inverse algorithm is adopted. Different experiments have been carried out on synthetic and satellite images. Extensive experimental comparisons were conducted with state-of-the-art super-resolution algorithms to validate the effectiveness of the proposed approach. The proposed GPU implementation for OMP is tested on NVS 5200M GPU on Intel ® Core(TM) i7 CPU. The GPU implementation accelerates the speedup compared to the CPU sequential implementation from 20× for small images to more than 40× for large image sizes.

Emotional textile image classification based on cross-domain convolutional sparse autoencoders with feature selection

We aim to apply sparse autoencoder-based unsupervised feature learning to emotional semantic analysis for textile images. To tackle the problem of limited training data, we present a cross-domain feature learning scheme for emotional textile image classification using convolutional autoencoders. We further propose a correlation-analysis-based feature selection method for the weights learned by sparse autoencoders to reduce the number of features extracted from large size images. First, we randomly collect image patches on an unlabeled image dataset in the source domain and learn local features with a sparse autoencoder. We then conduct feature selection according to the correlation between different weight vectors corresponding to the autoencoder’s hidden units. We finally adopt a convolutional neural network including a pooling layer to obtain global feature activations of textile images in the target domain and send these global feature vectors into logistic regression models for emotional image classification. The cross-domain unsupervised feature learning method achieves 65% to 78% average accuracy in the cross-validation experiments corresponding to eight emotional categories and performs better than conventional methods. Feature selection can reduce the computational cost of global feature extraction by about 50% while improving classification performance.

Fast Linearized Augmented Lagrangian Method for Euler's Elastica Model

AbstractRecently, many variational models involving high order derivatives have been widely used in image processing, because they can reduce staircase effects during noise elimination. However, it is very challenging to construct efficient algorithms to obtain the minimizers of original high order functionals. In this paper, we propose a new linearized augmented Lagrangian method for Euler's elastica image denoising model. We detail the procedures of finding the saddle-points of the augmented Lagrangian functional. Instead of solving associated linear systems by FFT or linear iterative methods (e.g., the Gauss-Seidel method), we adopt a linearized strategy to get an iteration sequence so as to reduce computational cost. In addition, we give some simple complexity analysis for the proposed method. Experimental results with comparison to the previous method are supplied to demonstrate the efficiency of the proposed method, and indicate that such a linearized augmented Lagrangian method is more suitable to deal with large-sized images.

An Adaptive CAD System to Detect Microcalcification in Compressed Mammogram Images

Microcalcifications (MC) in mammogram images are an early sign for breast cancer and their early detection is vital to improve its prognosis. Since MC appears as small dot in the mammogram image with size less than 1 mm and maybe easily overlooked by the radiologist, the Computer Aided Diagnosis (CAD) approach can assist the radiologist to improve their diagnostic accuracy. On the other hand, the mammogram images are a high resolution image with large image size which makes difficult the image transfer through the media. Therefore, in this paper, two image compressions techniques which are Discrete Cosine Transform (DCT) with entropy coding and Singular Value Decomposition (SVD) were investigated to reduce the mammogram image size. Then a novel adaptive CAD system is used to test the quality of the processed image based on true positive (TP) ratio and number of detected false positive (FP) regions in the mammogram image. The proposed adaptive CAD system used the visual appearance of MC in the mammogram to detect a potential MC regions. Then five texture features are implemented to reduce number of detected FP regions in the mammogram images. After implementing the adaptive CAD system on 100 mammogram images from USF and MIAS databases, it was found that the DCT can reduce the image size with a high quality since the ratio of TP is 87.6% with 11 FP/regions while in SVD the TP ratio is 79.1% with 26 FP/regions.