Mining-based associative image filtering using harmonic mean

With the development of IT convergence technologies, users can now more easily access useful information. These days, diverse and far-reaching information is being rapidly produced and distributed instantly in digitized format. Studies are continuously seeking to develop more efficient methods of delivering information to a greater number of users. Image filtering, which extracts features of interest from images, was developed to address the weakness of collaborative filtering, which is limited to superficial data analysis. However, image filtering has its own weakness of requiring complicated calculations to obtain the similarity between images. In this study, to resolve these problems, we propose associative image filtering based on the mining method utilizing the harmonic mean. Using data mining’s Apriori algorithm, this study investigated the association among preferred images from an associative image group and obtained a prediction based on user preference mean. In so doing, we observed a positive relationship between the various image preferences and the various distances between images’ color histograms. Preference mean was calculated based on the arithmetic mean, geometric mean, and harmonic mean. We found through performance analysis that the harmonic mean had the highest accuracy. In associative image filtering, we used the harmonic mean in order to anticipate preferences. In testing accuracy with MAE utilizing the proposed method, this study demonstrated an improvement of approximately 12 % on average compared to previous collaborative image filtering.     

Iterative image reconstruction using modified non-local means filtering for limited-angle computed tomography

PurposeLimited-angle CT imaging is an effective technique to reduce radiation. However, existing image reconstruction methods can effectively reduce streak artifacts but fail to suppress those artifacts around edges due to incomplete projection data. Thus, a modified NLM (mNLM) based reconstruction method is proposed.MethodsSince the artifacts around edges mainly exist in local position, it is possible to restore the true pixels in artifacts using pixels located in artifacts-free regions. In each iteration, mNLM is performed on image reconstructed by ART followed by positivity constraint. To solve the problem caused by ART-mNLM that there is undesirable information that may appear in the image, ART-TV is then utilized in the following iterative process after ART-mNLM iterates for a number of iterations. The proposed algorithm is named as ART-mNLM/TV.ResultsSimulation experiments are performed to validate the feasibility of algorithm. When the scanning range is [0, 150°], our algorithm outperforms the ART-NLM and ART-TV with more than 40% and 29% improvement in terms of SNR and with more than 58% and 49% reduction in terms of MAE. Consistently, reconstructed images from real projection data also demonstrate the effectiveness of presented algorithm.ConclusionThis paper uses mNLM which benefits from redundancy of information across the whole image, to recover the true value of pixels in artifacts region by utilizing pixels from artifact-free regions, and artifacts around the edges can be mitigated effectively. Experiments show that the proposed ART-mNLM/TV is able to achieve better performances compared to traditional methods.     

Two-dimensional gel electrophoresis image registration using block-matching techniques and deformation models

Block-matching techniques have been widely used in the task of estimating displacement in medical images, and they represent the best approach in scenes with deformable structures such as tissues, fluids, and gels. In this article, a new iterative block-matching technique—based on successive deformation, search, fitting, filtering, and interpolation stages—is proposed to measure elastic displacements in two-dimensional polyacrylamide gel electrophoresis (2D–PAGE) images. The proposed technique uses different deformation models in the task of correlating proteins in real 2D electrophoresis gel images, obtaining an accuracy of 96.6% and improving the results obtained with other techniques. This technique represents a general solution, being easy to adapt to different 2D deformable cases and providing an experimental reference for block-matching algorithms.     

BLeafNet: A Bonferroni mean operator based fusion of CNN models for plant identification using leaf image classification

Plants, the only natural source of oxygen, are the most important resources for every species in the world. A proper identification of plants is important for different fields. The observation of leaf characteristics is a popular method as leaves are easily available for examination. Researchers are increasingly applying image processing techniques for the identification of plants based on leaf images. In this paper, we have proposed a leaf image classification model, called BLeafNet, for plant identification, where the concept of deep learning is combined with Bonferroni fusion learning. Initially, we have designed five classification models, using ResNet-50 architecture, where five different inputs are separately used in the models. The inputs are the five variants of the leaf grayscale images, RGB, and three individual channels of RGB - red, green, and blue. For fusion of the five ResNet-50 outputs, we have used the Bonferroni mean operator as it expresses better connectivity among the confidence scores, and it also obtains better results than the individual models. We have also proposed a two-tier training method for properly training the end-to-end model. To evaluate the proposed model, we have used the Malayakew dataset, collected at the Royal Botanic Gardens in New England, which is a very challenging dataset as many leaves from different species have a very similar appearance. Besides, the proposed method is evaluated using the Leafsnap and the Flavia datasets. The obtained results on both the datasets confirm the superiority of the model as it outperforms the results achieved by many state-of-the-art models.     

Ultrasound image enhancement: A review

Medical ultrasound imaging uses pulsed acoustic waves that are transmitted and received by a hand-held transducer. This is a mature technology that it is widely used around the world. Among its advantages are that it is cost-effective, flexible, and does not require ionizing radiation. However, the image quality is affected by degradation of ultrasound signals when propagating through biological tissues. Many efforts have been done in the last three decades to improve the quality of the images. This paper reviews some of the most important methods for ultrasound enhancement. We classified these techniques into two groups: preprocessing and post-processing, analyzed their benefits and limitations, and presented our beliefs about where ultrasound research could be directed to, in order to improve its effectiveness and broaden its applications.     

Elimination of biological and physical artifacts in abdomen and brain computed tomography procedures using filtering techniques

IntroductionMedical images are usually affected by biological and physical artifacts or noise, which reduces image quality and hence poses difficulties in visual analysis, interpretation and thus requires higher doses and increased radiographs repetition rate.ObjectivesThis study aims at assessing image quality during CT abdomen and brain examinations using filtering techniques as well as estimating the radiogenic risk associated with CT abdomen and brain examinations.Materials and MethodsThe data were collected from the Radiology Department at Royal Care International (RCI) Hospital, Khartoum, Sudan. The study included 100 abdominal CT images and 100 brain CT images selected from adult patients. Filters applied are namely: Mean filter, Gaussian filter, Median filter and Minimum filter. In this study, image quality after denoising is measured based on the Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and the Structural Similarity Index Metric (SSIM).ResultsThe results show that the images quality parameters become higher after applications of filters. Median filter showed improved image quality as interpreted by the measured parameters: PSNR and SSIM, and it is thus considered as a better filter for removing the noise from all other applied filters.DiscussionThe noise removed by the different filters applied to the CT images resulted in enhancing high quality images thereby effectively revealing the important details of the images without increasing the patients’ risks from higher doses.ConclusionsFiltering and image reconstruction techniques not only reduce the dose and thus the radiation risks, but also enhances high quality imaging which allows better diagnosis.     

Fingerprint matching using recurrent autoassociative memory

An efficient method for fingerprint searching using recurrent autoassociative memory is proposed. This algorithm uses recurrent autoassociative memory, which uses a connectivity matrix to find if the pattern being searched is already stored in the database. The advantage of this memory is that a big database is to be searched only if there is a matching pattern. Fingerprint comparison is usually based on minutiae matching, and its efficiency depends on the extraction of minutiae. This process may reduce the speed, when large amount of data is involved. So, in the proposed method, a simple approach has been adopted, wherein first determines the closely matched fingerprint images, and then determines the minutiae of only those images for finding the more appropriate one. The gray level value of pixels along with its neighboring ones are considered for the extraction of minutiae, which is more easier than using ridge information. This approach is best suitable when database size is large.     

Micro-CT imaging of rat lung ventilation using continuous image acquisition during xenon gas contrast enhancement.

We measured ventilation (V) in seven anesthetized, mechanically ventilated, supine Wistar rats. Images of the whole lung were continuously acquired using a dynamic, flat-panel volumetric micro-computed tomography (micro-CT) scanner during ventilation with a xenon/oxygen (Xe-O(2)) gas mixture. Forty time-resolved volumes consisting of eighty 0.45-mm-thick slices (covering the entire lung) were acquired in 40 s, using a gantry rotation rate of one rotation per second. The animals were ventilated at a respiratory rate of 60 breaths/min, matching the gantry rotation rate, and imaged without suspending ventilation. A previously published theoretical model was modified slightly and used to calculate the whole lung ventilation from volumes of interest generated by seeded region growing. Linear regression of calculated whole lung ventilation volumes vs. expected tidal volumes yielded a slope of 1.12 +/- 0.11 (slope +/- SE) and a y-intercept of -1.56 +/- 0.42 ml (y-intercept +/- SE) with 95% confidence intervals of 0.83 to 1.40 and -2.6 to -0.5 ml, respectively. The same model was used to calculate the regional ventilation in axial slices for each animal. Voxels were fit to the model to yield a map of V, which displayed an anterior/posterior gravitational gradient of (-3.9 +/- 1.8) x 10(-6) mlxs(-1)xcm(-1) for slices immediately superior to the diaphragm and (-6.0 +/- 2.4) x 10(-6) mlxs(-1)xcm(-1) for slices at the midlevel of the heart (mean +/- SD). Thus continuous Xe-enhanced computed tomography enables the noninvasive determination of regional V with the temporal and spatial resolution necessary for rats.     

Empirical mode decomposition based filtering techniques for power line interference reduction in electrocardiogram using various adaptive structures and subtraction methods

Electrocardiogram (ECG) is a vital sign monitoring measurement of the cardiac activity. One of the main problems in biomedical signals like electrocardiogram is the separation of the desired signal from noises caused by power line interference, muscle artifacts, baseline wandering and electrode artifacts. Different types of digital filters are used to separate signal components from unwanted frequency ranges. Adaptive filter is one of the primary methods to filter, because it does not need the signal statistic characteristics. In contrast with Fourier analysis and wavelet methods, a new technique called EMD, a fully data-driven technique is used. It is an adaptive method well suited to analyze biomedical signals. This paper foregrounds an empirical mode decomposition based two-weight adaptive filter structure to eliminate the power line interference in ECG signals. This paper proposes four possible methods and each have less computational complexity compared to other methods. These methods of filtering are fully a signal-dependent approach with adaptive nature, and hence it is best suited for denoising applications. Compared to other proposed methods, EMD based direct subtraction method gives better SNR irrespective of the level of noises.     

Angle-distance image matching techniques for protein structure comparison

Proteins that contain similar structural elements often have analogous functions regardless of the degree of sequence similarity or structure connectivity in space. In general, protein structure comparison (PSC) provides a straightforward methodology for biologists to determine critical aspects of structure and function. Here, we developed a novel PSC technique based on angle-distance image (A-D image) transformation and matching, which is independent of sequence similarity and connectivity of secondary structure elements (SSEs). An A-D image is constructed by utilizing protein secondary structure information. According to various types of SSEs, the mutual SSE pairs of the query protein are classified into three different types of sub-images. Subsequently, corresponding sub-images between query and target protein structures are compared using modified cross-correlation approaches to identify the similarity of various patterns. Structural relationships among proteins are displayed by hierarchical clustering trees, which facilitate the establishment of the evolutionary relationships between structure and function of various proteins.Four standard testing datasets and one newly created dataset were used to evaluate the proposed method. The results demonstrate that proteins from these five datasets can be categorized in conformity with their spatial distribution of SSEs. Moreover, for proteins with low sequence identity that share high structure similarity, the proposed algorithms are an efficient and effective method for structural comparison.     

Hydrophobic docking: A proposed enhancement to molecular recognition techniques

In the classical procedures for predicting the structure of protein complexes two molecules are brought in contact at multiple relative positions, the extent of complementarity (geometric and/or energy) at the surface of contact is assessed at each position, and the best fits are retrieved. In view of the higher occurrence of hydrophobic groups at contact sites, their contribution results in more intermolecular atom–atom contacts per unit area for correct matches than for false positive fits. The hydrophobic groups are also potentially less flexible at the surface. Thus, from a practical point of view, a partial representation of the molecules based on hydrophobic groups should improve the quality of the results in finding molecular recognition sites, as compared to full representation. We tested this proposal by applying the idea to an existing geometric fit procedure and compared the results obtained with full vs. hydrophobic representations of molecules in known molecular complexes. The hydrophobic docking yielded distinctly higher signal-to-noise ratio so that the correct match is discriminated better from false positive fits. It appears that nonhydrophobic groups contribute more to false matches. The results are discussed in terms of their relevance to molecular recognition techniques as compared to energy calculations. © 1994 Wiley-Liss, Inc.     

Multispectral/hyperspectral image enhancement for biological cell analysis.

BACKGROUND: Microscopes form projected images from illuminated objects, such as cellular tissue, which are recorded at a distance through the optical system's field of view. A telescope on a satellite or airplane also forms images with a similar optical projection of objects on the ground. Typical visible illuminations form a displayed set of three-color channels (Red Green Blue [RGB]) that are combined from three image sensor arrays (e.g., focal plane arrays) into a single pixel coding for each color present in the image. Analysis of these RGB color images develops a qualitative image representation of the objects. METHODS: Independent component analysis (ICA) is used for analysis and enhancement of multispectral images, and compared with the similar and widely used principal component analysis. RESULTS: The data examples indicate that the ICA enhancement, and the resulting RGB image combination display, can be useful in processing datacubes of cellular data where isolation of unknown subtle image elements representing objects is desired. CONCLUSIONS: ICA image enhancement can aid processing of datacubes of cellular data by clarifying subtle image elements. These parallelizable algorithms can be implemented for real-time, online analysis.     

Detection and classification of chilli leaf disease using a squeeze-and-excitation-based CNN model

Chilli leaf disease has a destructive effect on the chilli crop yield. Chilli leaf disease can result in a significant decrease in both the quantity and quality of the chilli crop. Early detection, perfect identification and accurately diagnosing the disease will aid in increasing the profit of the cultivator. However, after a comprehensive survey investigation, we discovered that no studies have been previously conducted to compare the classification performance of machine learning and deep learning for the chilli leaf disease classification problem. In this study, five main leaf diseases i.e. down curl of a leaf, Geminivirus, Cercospora leaf spot, yellow leaf disease, and up curl disease were identified, and images were captured using a digital camera and are labelled. These diseases were classified using 12 different pretrained deep learning networks (AlexNet, DarkNet53, DenseNet201, EfficientNetb0, InceptionV3, MobileNetV2, NasNetLarge, ResNet101, ShuffleNet, SqueezeNet, VGG19, and XceptionNet) using chilli leaf data with and without augmentation using deep learning transfer. Performance metrics such as accuracy, recall, precision, F1-score, specificity, and misclassification were calculated for each network. VGG19 had the best accuracy (83.54%) without augmentation, and DarkNet53 had the best result (98.82%) with augmentation among all pretrained deep learning networks in our self-built chilli leaf dataset. The result was enhanced by designing a squeeze-and-excitation-based convolutional neural network (SECNN) model. The model was tested on a chilli leaf dataset with different input sizes and mini-batch sizes. The proposed model produced the best accuracy of 98.63% and 99.12% without and with augmentation, respectively. The SECNN model was also tested on different datasets from the PlantVillage data, including apple, cherry, corn, grape, peach, pepper, potato, strawberry, and tomato leaves, separately and with the chilli dataset. The proposed model achieved an accuracy of 99.28% in classifying 43 different classes of plant leaf datasets.     

Cryopreservation and image enhancement of juvenile and adult dentine mineral

The inorganic component of bone and related hard tissues is generally described as sheets of uniform needle- and plate-like crystals. However, cryofixation has become the method of choice for ultrastructural studies of bone mineral when ladder-like arrangements of filaments contained within deformable microspheres about 1µm in diameter are apparently the prime structural feature and are consistent with the optical image. The same methodology has now been applied to mature human dentine in caries-free juvenile and adult teeth. These were fixed, sliced, stained for mineral and examined optically or were snap frozen, fragmented under liquid nitrogen, freeze-substituted with methanol or acetone and embedded without thawing in Lowicryl K4M for electron microscopy. Others were processed by traditional transmission electron microscopy methods. To obtain maximum resolution, the electron micrographs were photographically printed as negatives and image-enhanced by digitisation using a Polaroid Sprint Scan 45 and laser printer. In both optical and cryopreparations of juvenile and adult dentine, mineral microspheres up to 1µm in diameter, were present in the dentinal tubules and peritubular dentine. Within these objects, the mineral was primarily in the form of sinuous electron dense filaments, 5nm thick, which had a characteristic periodicity. In these preparations needle-like and plate-like structures were rare. In contrast, after traditional transmission electron microscopy preparation although similar filamentous structures remained, the mineral more generally had the familiar form of needles measuring approximately 50nm in the long axis. The cryopreserved calcified filaments were apparently particularly densely distributed in the intertubular dentine where their parallel ladder-like arrays often formed highly orientated struts and stays. It was concluded that early dentine mineral has the form of filamentous microspheres and as in bone (and other calcifying tissues and cells) has no specific association with collagen. It was also concluded that these structures compact and deform with maturity into a sub-structural framework which may relate to powerful biomechanical forces transmitted through the tissue. Needle- or plate-like mineral is probably rare in vivo in dentine, only becoming commonplace after extensive chemical processing.     

Effect of striate visual cortex topography on the parameters of image filtering

A model of spatial-frequency filtering at the level of 4C layer of the striate visual cortex is proposed and based on the well-known literature data. The evidence on conformable character of representation of the visual field on the primary visual cortex and the suggestions concerning uniformity of horizontal connections of cortical neurones serve as the ground of the model. A correspondence between predictions of the model and results of the experiments with shape perception and size discrimination has been obtained.     

Adaptive filtering for enhancement of the osteocyte cell network in 3D microtomography images

The osteocyte cell network in bone tissue is thought to orchestrate tissue adaptation and remodeling, thus holding responsibility for tissue quality. Previously, this structure has been studied mainly in 2D and its architecture and functions are not fully elucidated. The assessment of the osteocyte system is prerequisite for deeper understanding of bone remodeling and for advances in management of bone diseases. Our goal is to enable 3D isotropic imaging of bone at cellular level and to develop algorithms for quantitative image analysis of the cell network. We recently demonstrated accurate 3D imaging of this cell structure with synchrotron radiation tomography at submicrometric scale. Due to the limited spatial resolution of the imaging system and the constraints in terms of radiation dose, the images suffer from low signal to noise ratio and the detection of the cell dendrites is challenging. Here we detail a method for enhancement of the osteocyte network in human bone from 3D microtomography images. The approach combines Hessian-based 3D line enhancement and bilateral filtering. Our method enables extraction of the interconnected cells from noisy images, preserving the integrity of the cells and of their slender dendrites. Qualitative and quantitative results are presented.     

Ultrafast protein determinations using microwave enhancement

We present here microwave-based modifications of standard protein assays that dramatically reduce the time required to determine protein concentrations. Typical protein determinations involve incubation times ranging from 15–60 min. Microwave irradiation of specimens reduces this time requirement to 10–20 s without compromising accuracy or reliability. The remarkable speed with which protein determinations may be carried out using microwave enhancement greatly simplifies general laboratory procedures that depend on the estimation of protein concentrations. An erratum to this article is available at .     

Determination of the mechanical properties of DOPC:DOPS liposomes using an image procession algorithm and micropipette-aspiration techniques

Quantification of the mechanical properties of liposomes is critical in helping to predict their behavior during various applications such as targeted drug delivery, response to mechanical characterization or their interactions with isolated cytoskeletal elements. A numerical implementation of the Evans aspiration technique, and an image processing algorithm for measuring deformation of spherical DOPC:DOPS liposomes is presented. Liposomes were aspirated to pressures of ?10 mmHg (～?1300 Pa). The area expansion and Young's moduli of the liposomes were found to be 0.067 N m^?1 (67 ± 4 dyn/cm) and 15 ± 1 MPa.