Global Image Analysis Research Articles

Rot Corn Grain Classication by Color and Texture Analysis

Due to the constant increase in corn production and exportation volume, it becomes necessary a digital transformation and tasks automatization in this scenario. The technological artifacts are an important tool for agribusiness companies, once they can improve the controls, agility, efficacy and safety of the procedures. Although automatic operations are frequently used, some activities are still executed manually, such as the rot corn grains classification process. The classification aims to analyze the quality and characteristics of the grains according to a predefined commercial pattern, which are established by the companies that commercialize this cereal. According to the identified characteristics, the negotiation might be affected by price reduction or rejection. Therefore, performing the classification properly is essential to increase the profitability and quality of the corn sold by the companies. Thus, this work aims to introduce a methodology for automatic estimation of percentual range of rot grains by global image analysis of corn grain samples. To be closer to the real process, we diversified the rot percentage inside the images samples by weighing the grains instead of counting it. In this methodology, the images were collected by following a capturing pattern. Next, histograms of color and texture descriptors were computed to characterize the input images. Such histograms were submitted to supervised classifiers to estimate the corn grains percentual range. Several classifiers were tested (minimum distance classifier, SVM, Naive Bayes and Decision Tree) to categorize the corn grains percentual range. In these tests, SVM classifier improved by a boosting technique (AdaBoost) achieved an average accuracy up to 99.97%.

A NEW TECHNIQUE FOR OBJECT DETECTION AND TRACKING AND ITS APPLICATION TO ANALYSIS OF ROAD SCENE

Abstract. In this paper, a new technique for real-time object detection and tracking is presented. This technique is based on the geometrized histograms method (GHM) for segmenting and describing color images (frames of video sequences) and on the facilities for global image analysis provided by this method. Basic elements of the technique that make it possible to solve image understanding problems almost without using the pixel arrays of images are introduced and discussed.A real-time parallel software implementation of the developed technique is briefly discussed. This technique is applied to solving problems of road scene analysis. The application to finding small contrast objects in images, like traffic signals and signal zones of vehicles is given. The developed technique is applied also to detecting other vehicles in the frame. The results of processing different frame of videos of road scenes are presented and discussed.

Hierarchical Clustering for Image Classification in Dermatology: Towards Mobile Deploying.

In the context of increasing interest in computer-assisted diagnosis for skin lesion images and mobile applications to be used in real life settings, we propose a combined desktop-smartphone solution for dermatological image classification. Hierarchical agglomerative and divisive clustering are both implemented as methods of cluster analysis, with the RGB color histogram as descriptor for a global image analysis. The cosine similarity is employed for classifying the query image in one of the available clusters, characterized by their centroids. The solution has been tested with a public database of dermoscopic images, with an overall accuracy of 0.73, 95%CI (0.58;0.85).

Spatial frequency text filtering for local and global analysis

The interaction between the mechanisms of local and global image analysis at the level of the magnocellular and parvocellular channels of the human visual system was studied. Using wavelet filtering, the spatial frequency composition of texts presented to observers was varied. It was shown that gradual blurring of texts via wavelet filtering interferes with the work of the parvocellular system but simultaneously increases the contribution of the magnocellular system during reading. With an increase in the wavelet element scale, the parvocellular system receives insufficient information for effective work, and in this situation the magnocellular system determines the strategy of eye movements. In addition, the necessary frequency range that ensures the functioning of the reading process is provided.

A New Method of Global Image Analysis and Its Application in Understanding Road Scenes

In this paper, real-time algorithms for constructing the adjacency graph and the spatial geometric relation between contrast objects of color images are proposed, as well as methods of global image analysis based on them, within the scope of the theory developed by the author. Image analysis is conducted based on the graph of color bunches STG and the bipartite graph LRG of left and right contrast boundary curves (germs of contrast global objects) in STG, introduced by the author. An essential point is that in each layer of this graph a linearly ordered covering constituted of “basic” color bunches is selected. Based on this covering, a search lattice for solving global problems of image analysis is constructed. The obtained results are applied to finding complex objects in images. In particular, they are applied to the analysis of road scenes. The developed methods are implemented in the form of a program complex. The results of its operation on video sequences taken from a moving vehicle are presented and discussed. The application of the developed technique to the navigation of autonomous robots is also considered.

Sympathetic cardiac function in early sepsis: Noninvasive evaluation with [123I]-meta-iodobenzylguanidine (123I-MIBG) in vivo SPECT imaging

BackgroundSympathetic system abnormalities have been reported in sepsis-related cardiac dysfunction. The present study aimed at evaluating the potential of the norepinephrine radiolabeled analogue [123I]-meta-iodobenzylguanidine (123I-MIBG) for the noninvasive assessment of modifications in cardiac sympathetic activity occurring in lipopolysaccharide (LPS)-induced experimental acute sepsis by single-photon emission computed tomographic imaging (SPECT). Methods and ResultsSepsis was induced in male Wistar rats by intraperitoneal injection of 10 mg·kg−1 lipopolysaccharide (n = 16), whereas control animals (n = 7) were injected with vehicle (NaCl 0.9%). Echocardiography in LPS-injected animals (n = 8) demonstrated systolic and diastolic cardiac dysfunction. 123I-MIBG was injected 1 hour after LPS or vehicle administration (n = 8 and 7, respectively), and in vivo SPECT imaging was performed early and late (20 and 180 minutes) after tracer injection prior to animal euthanasia and ex vivo assessment of 123I-MIBG biodistribution. Global and 17-segment SPECT image analysis indicated that early 123I-MIBG activity was not affected by LPS treatment, whereas late cardiac tracer activity was significantly decreased in LPS-treated animals. Consequently, the cardiac washout of 123I-MIBG was significantly higher in LPS-treated (63.3% ± 4.0%) than that in control animals (56.7% ± 5.8%) (P < .05). ConclusionSepsis-induced modifications in cardiac sympathetic nervous system activity were evidenced by noninvasive in vivo 123I-MIBG SPECT imaging.

Biotransport kinetics and intratumoral biodistribution of malonodiserinolamide-derivatized [60]fullerene in a murine model of breast adenocarcinoma.

[60]Fullerene is a highly versatile nanoparticle (NP) platform for drug delivery to sites of pathology owing to its small size and both ease and versatility of chemical functionalization, facilitating multisite drug conjugation, drug targeting, and modulation of its physicochemical properties. The prominent and well-characterized role of the enhanced permeation and retention (EPR) effect in facilitating NP delivery to tumors motivated us to explore vascular transport kinetics of a water-soluble [60]fullerene derivatives using intravital microscopy in an immune competent murine model of breast adenocarcinoma. Herein, we present a novel local and global image analysis of vascular transport kinetics at the level of individual tumor blood vessels on the micron scale and across whole images, respectively. Similar to larger nanomaterials, [60]fullerenes displayed rapid extravasation from tumor vasculature, distinct from that in normal microvasculature. Temporal heterogeneity in fullerene delivery to tumors was observed, demonstrating the issue of nonuniform delivery beyond spatial dimensions. Trends in local region analysis of fullerene biokinetics by fluorescence quantification were in agreement with global image analysis. Further analysis of intratumoral vascular clearance rates suggested a possible enhanced penetration and retention effect of the fullerene compared to a 70 kDa vascular tracer. Overall, this study demonstrates the feasibility of tracking and quantifying the delivery kinetics and intratumoral biodistribution of fullerene-based drug delivery platforms, consistent with the EPR effect on short timescales and passive transport to tumors.

Development of a novel image analysis procedure to quantify biological porosity and illuvial clay in large soil thin sections

Among other driving forces, climate change may lead to significant modifications of soil properties through variations of the intensity and dynamics of a number of soil processes including the especially sensitive and ubiquitous processes of bioturbation and illuviation. Progress toward the quantification of these processes needs to be made as a first step in order to ascertain or predict the impact of climate change. In this study, we develop, and validate through an exhaustive accuracy assessment, a digital 2D image analysis method adapted to large soil thin sections, leading to the quantification, characterization and classification of pores and illuvial clay features considered diagnostic of bioturbation and illuviation, respectively. The need to consider large soil thin sections (14 x 6 cm) stems from observations that areas from 684 mm2 to more than 5 000 mm2 are needed to obtain representative measurements of fragments of illuvial clay (papules) and porosity associated with earthworms respectively. Whereas the soil heterogeneity in thin sections of such a large size prohibits the use of classical global and colorimetric image analysis procedures, we succeeded to quantify and characterize the porosity and illuvial clay features with accuracies as high as 96% for porosity and 92% for illuvial clay by carefully considering different levels of soil organization from aggregates to individual illuvial clay features. Quantification of the size and the shape of pores and of illuvial clay features makes it possible to develop morphological classifications distinguishing pores of biological origin (earthworms or roots) from others, or clay coatings and infillings from papules. All these data are particularly useful to better characterize underlying soil processes. Results suggest that the proposed methodology provides an accurate and representative quantification of biological porosity and illuvial clay features in large thin sections. We argue that the use of this approach could be extended to study and quantify bioturbation and illuviation intensities at the profile scale.

Follow-up of solar lentigo depigmentation with a retinaldehyde-based cream by clinical evaluation and calibrated colour imaging.

To assess an objective method evaluating the effects of a retinaldehyde-based cream (RA-cream) on solar lentigines; 29 women randomly applied RA-cream on lentigines of one hand and a control cream on the other, once daily for 3 months. A specific method enabling a reliable visualisation of the lesions was proposed, using high-magnification colour-calibrated camera imaging. Assessment was performed using clinical evaluation by Physician Global Assessment score and image analysis. Luminance determination on the numeric images was performed either on the basis of 5 independent expert's consensus borders or probability map analysis via an algorithm automatically detecting the pigmented area. Both image analysis methods showed a similar lightening of ΔL* = 2 after a 3-month treatment by RA-cream, in agreement with single-blind clinical evaluation. High-magnification colour-calibrated camera imaging combined with probability map analysis is a fast and precise method to follow lentigo depigmentation.

Global scene layout modulates contextual learning in change detection

Change in the visual scene often goes unnoticed – a phenomenon referred to as “change blindness.” This study examined whether the hierarchical structure, i.e., the global–local layout of a scene can influence performance in a one-shot change detection paradigm. To this end, natural scenes of a laid breakfast table were presented, and observers were asked to locate the onset of a new local object. Importantly, the global structure of the scene was manipulated by varying the relations among objects in the scene layouts. The very same items were either presented as global-congruent (typical) layouts or as global-incongruent (random) arrangements. Change blindness was less severe for congruent than for incongruent displays, and this congruency benefit increased with the duration of the experiment. These findings show that global layouts are learned, supporting detection of local changes with enhanced efficiency. However, performance was not affected by scene congruency in a subsequent control experiment that required observers to localize a static discontinuity (i.e., an object that was missing from the repeated layouts). Our results thus show that learning of the global layout is particularly linked to the local objects. Taken together, our results reveal an effect of “global precedence” in natural scenes. We suggest that relational properties within the hierarchy of a natural scene are governed, in particular, by global image analysis, reducing change blindness for local objects through scene learning.

Classification and Counting of Composite Objects in Traffic Scenes Using Global and Local Image Analysis

Object recognition algorithms often focus on determining the class of a detected object in a scene. Two significant phases are usually involved in object recognition. The first phase is the object representation phase, in which the most suitable features that provide the best discriminative power under constraints such as lighting, resolution, scale, and view variations are chosen to describe the objects. The second phase is to use this representation space to develop models for each object class using discriminative classifiers. In this paper, we focus on composite objects, i.e., objects with two or more simpler classes that are interconnected in a complicated manner. One classic example of such a scenario is a bicyclist. A bicyclist consists of a bicycle and a human who rides the bicycle. When we are faced with the task of classifying bicyclists and pedestrians, it is counterintuitive and often hard to come up with a discriminative classifier to distinguish the two classes. We explore global image analysis based on bag of visual words to compare the results with local image analysis, in which we attempt to distinguish the individual parts of the composite object. We also propose a unified naive Bayes framework and a combined histogram feature method for combining the individual classifiers for enhanced performance.

Novel anti‐wrinkle effect of cosmeceutical product with new retinyl retinoate microsphere using biodegradable polymer

The novel hybrid retinoid, retinyl retinoate, is a synthetic material that was designed to reduce the side effects of retinoic acid and to increase the stability of retinol. The formulation of the retinyl retinoate, however, is required to enhance skin permeation, and thus to increase the anti-wrinkle effect. To identify the efficacy of retinyl retinoate microsphere using biodegradable polymer as an anti-aging agent of cosmetics in treating females over 30 years old with periorbital wrinkles. The retinyl retinoate microsphere was prepared using the biodegradable polymer; polylactic acid (PLA). We also conducted two clinical studies with a total of 44 Korean women for 12 weeks. In the first clinical study, 20 patients completed a 12-week trial of cream A [3% PLA-retinyl retinoate (2%) microsphere] applied twice daily to the face. In the second clinical study, 24 patients completed a 12-week trial of cream B (0.06% retinyl retinoate) applied twice daily to the face. Efficacy was based on a global photodamage score, photographs, and image analysis using replicas and Visiometers every 4 weeks. The PLA-retinyl retinoate microsphere was more effective for the permeation of retinyl retinoate than retinyl retinoate in itself. The cream A, which contains 3% PLA-retinyl retinoate (2%) microsphere, showed a statistically significant improvement in facial wrinkles (P<0.05) in 20 volunteers after only 4 weeks of application in a clinical trial test. The visual wrinkle improvement and the maximum roughness improvement rate (R2) for cream A was 6.05%, 8.03% higher than that of cream B which contains 0.06% retinyl retinoate, after 4 weeks. Retinyl retinoate has a potent anti-wrinkle activity, and the PLA-retinyl retinoate microsphere could be a useful cosmeceutical product for anti-aging purposes.

Retinyl retinoate, a novel hybrid vitamin derivative, improves photoaged skin: a double‐blind, randomized‐controlled trial

All-trans-retinoic acid (RA) and all-trans-retinol (ROL) are not widely used as anti-wrinkle agents due to their irritancy and photo-stability, respectively. Therefore, the safety and photo-stability in the development of RA or ROL derivatives have been an important issue. To identify the efficacy of retinyl retinoate as an anti-aging agent of cosmetics in treating females over 30 years old with periorbital wrinkles. The clinical study was a prospective, double-blind, randomized, and controlled study with a total of 11 Korean women. At every 4 weeks, the effectiveness was assessed with a global photodamage score, photographs, and image analysis using replicas and visiometers. The dermal distance and intensity was also evaluated using Dermascan C. A statistically significant improvement in facial wrinkles (P<0.05) in eleven volunteers was observed in a clinical trial. The successive application of 0.06% retinyl retinoate cream for 3 months showed decreased depth and area of wrinkles in comparison with 0.075% retinol cream. The visual wrinkle improvement and the maximum roughness improvement rate (R2) for retinyl retinoate cream were 22% higher than that of retinol cream after 12 weeks. A statistically significant increase was observed after 8 and 4 weeks for dermal distance and dermal intensity, respectively (P<0.05). Retinyl retinoate had characteristic features of new anti-aging agents, and effectively improved facial wrinkle conditions.

Improvement in skin wrinkles from the use of photostable retinyl retinoate: a randomized controlled trial

Photoaged skin can be treated with retinoids, which are natural and synthetic vitamin A derivatives. However, these are photounstable and can cause skin irritation, which is a major limitation in their use in general cosmetics. Retinyl retinoate, which is an ester of all-trans retinoic acid (RA) and all-trans retinol, has reduced toxicity due to blocking of the carboxyl end group of RA and higher skin regeneration activity than retinol. To assess the efficacy of a photostable retinyl retinoate in treating women over 30 years old with periorbital wrinkles. We conducted two clinical studies with a total of 46 Korean women with periorbital wrinkles, who were not pregnant, nursing or undergoing any concurrent therapy. In the first clinical study, the efficacy of retinyl retinoate was compared with placebo. Twenty-four patients completed a 12-week trial of 0.06% retinyl retinoate applied twice daily to one side of the face and a placebo applied to the other side. In the second clinical study, the efficacy of retinyl retinoate was compared with retinol. Twenty-two patients completed an 8-week trial of 0.06% retinyl retinoate applied twice daily to one side of the face and 0.075% retinol applied to the other side. Efficacy was based on a global photodamage score, photographs, and image analysis using replicas and visiometer analysis (Skin-Visiometer SV 600; Courage & Khazaka, Cologne, Germany) every 4 weeks. The standard wrinkle and roughness parameters used in assessing skin by visiometer were calculated and statistically analysed. The retinyl retinoate-treated wrinkles improved compared with wrinkles treated with placebo or retinol, as assessed by both the investigators and the subjects. Also, skin replica analysis indicated significant improvements in retinyl retinoate-treated skin in both studies, especially in average roughness. Retinyl retinoate applied twice daily was significantly more effective than a placebo or retinol in treating periorbital wrinkles. Importantly, no severe side-effects were observed.

Image-free assessment of protein translocation in live cells

Protein translocation is a universal event shared by most cell signalling pathways to transmit signals between cell compartments. In recent years, the use of new fluorescence microscopy technologies combined with fluorescent probes--most often fluorescent proteins--and image analysis software has allowed the visualization and extensive analysis of such dynamic events in the context of the living cell. This review article focuses on emerging fluorescence approaches that tackle live cell protein translocation in the image-free context. Such methods are based on either protein-protein interactions or analysis of spatial diffusion of proteins by fluorescence intensity measurements. The potential benefits of intensity measurement on global cell populations versus image analysis of heterogeneous cell sample are discussed in the context of drug discovery applications.

Quantifying the Evolution of a Beach Protected by Low Crested Structures Using Video Monitoring

Abstract The purpose of this study is to analyse the shoreline response of a beach protected by a system of low crested structures (LCS) and to apply the results to the management of coastal stability problems. This contribution aims to provide heretofore scarce detailed data and observations of the shoreline variability of coasts protected by LCS. These aims are acheived by selecting and monitoring the appropriate Coastal State Indicator (CSI) to describe the state of the beach. The CSI used is the Mean Intertidal Position (MIP), which has been detected by the ARGUS system installed in Lido di Dante, Italy. The error in the shoreline estimation from video was assessed by comparing shorelines detected with global positioning system (GPS) and image analysis over a large number of cases. The horizontal error in the shoreline detection is estimated to be on the order of 0.90 ± 0.74 m, which is acceptable because it is on the same order of magnitude as the swash width. The MIP, which has been monitored over a...

A strategy for blood vessels segmentation based on the threshold which combines statistical and scale space filter: Application to the study of angiogenesis

This paper presents a strategy for segmenting blood vessels based on the threshold, which combines statistics and scale space filter. By incorporating statistical information, the strategy is capable of reducing over-segmentation. We propose a two-stage strategy which involves: (1) optimal selection of window size and (2) optimal selection of scale. We compared our strategy to two commonly used thresholding techniques. Experimental results showed that our method is much more robust and accurate. Our strategy suggested a modification to Otsu's method. In this application the important information to be extracted from images is only the number of blood vessels present in the images. The proposed segmentation technique is tested on manual segmentation, where segmentation errors less than 3% were observed. The work presented in this paper is a part of a global image analysis process. Therefore, these images will be subject to a further morphometrical analysis in order to diagnose and predict automatically malign tumors.

In Field Soil Characterization: Approach Based on Texture Image Analysis

Building on the development of a tool for in place soil investigation based on the use of endoscopy, this paper presents a method for soil characterization using the images recorded by this tool. Various techniques have been explored including texture analysis which is very attractive because it is based on global image analysis. The use of a third order moment resulting from spectral analysis and its value for soil characterization is presented. The influence of various parameters (particle size distribution, mineralogy, water content, and compaction) on the moment evolution is studied.

Contribution of image analysis to the description of enzymatic degradation kinetics for particulate food material

The objective of the present work was to relate the physical evolution quantified by image analysis to the chemical transformation of beet pulp particles during enzymatic degradation. Beet pulps were degraded into a torus reactor equipped for visualisation. Pectinolytic and cellulolytic enzymes were used separately or in combination. Two global image analysis techniques were tested to characterise the size distribution of overlapping particles. Granulometric curves were extracted by mathematical morphology and a regularisation dimension was assessed by fractal analysis. Both techniques proved efficient to follow particle size evolution during degradation. When using cellulolytic enzymes alone, no chemical or physical evolution was observed. When using pectinolytic enzymes, a chemical modification occurred without any physical evolution. Particles physically disappeared when both enzymes were used. The chemical and physical evolutions of particles during degradation were interpreted taking into account the current model of molecular arrangement of primary cell walls.

Global and multi-scale image analysis using power spectra

Image analysis is currently used to study the structure of materials. In this paper, classical techniques of signal analysis such as power spectrum and autocorrelation functions are applied for this purpose. These techniques allow the detection of hidden features in complex images such as fracture surfaces, before highlighting them using spatial filtering. For that, the power spectrum allows us to locate the range of scales of peculiar texture, present but invisible to the naked eye. Thus, this study deals with the homogeneity of epoxy networks. Another way to use the method concerns aggregation phenomena. Indeed, the method allows us to assimilate several images of different magnifications, in order to characterize the aggregation on a large range of scales from the size of the particle or fibre to the full size of the sample. Then, the peculiar morphology of thermoplastic composites made from commingled fibres can be studied. The autocorrelation function method is also used to highlight features in the images of such composite materials.