In this work, a novel biosensing platform was fabricated based on modification of a rotating glassy carbon electrode (GCE) with chitosan-ionic liquid (Ch-IL) composite film, electrochemical synthesis ...of gold palladium platinum trimetallic three metallic alloy nanoparticles (AuPtPd NPs) onto its surface, and electrosynthesis of dual templates molecularly imprinted polymers (MIPs) where morphine (MO) and codeine (COD) used as template molecules. The AuPtPd NPs were synthesized under different electrochemical conditions, and surfaces of electrodes were investigated by digital image processing, and the best electrode was chosen. Effects of experimental variables on response of the biosensor to MO and COD were optimized by a central composite design (CCD), and under optimized conditions (concentration of the phosphate buffered solution (PBS): 0.09 M, pH of the PBS: 3.21–3.2, time of immersion: 204.8–205 s, and rotation rate: 2993.51–3000 rpm) the biosensor responses to MO and COD were individually calibrated (1–20 pM for MO and 0.5–12 pM for COD), three-way calibrated by PARASIAS, PARAFAC2, and MCR-ALS, and validated in the presence of ascorbic acid and uric acid as uncalibrated interference. Finally, performance of the biosensor in simultaneous determination of MO and COD in the presence of ascorbic acid and uric acid as uncalibrated interference in human serum samples were verified and compared with the results of HPLC-UV as the reference method which guaranteed it as a reliable method.
•A novel electrochemical biosensor was fabricated for simultaneous determination of morphine and codeine.•Image processing, experimental design, and multi-way calibration supported the biosensor.•Interference caused by ascorbic acid and uric acid were tackled by exploiting second-order advantage.•The biosensor assisted by MCR-ALS was successful in analysis of serum samples.•Performance of the intelligent biosensor was admirable and comparable with the reference method.
Aggregate-binder adhesiveness impacts asphalt mixture performance. Evaluation of this interface within mixes typically involves visual assessment and digital image processing (DIP), often resulting ...in an average value for this complex property. Current computational simulations overlook the possibility of incomplete aggregate adhesion to the binder, a common occurrence in cases of adhesive/cohesive failure between materials. This study proposes an interface index determined from adhesiveness test results in order to improve computational simulations. For this purpose, twelve adhesiveness tests, following Brazilian standards, including mineral and steel-slag aggregates, and neat and modified binders, were conducted. Software with a graphical user interface (GUI) was developed to quantify the percentage of aggregate area coated by binder (%Coated) post-testing. Descriptive statistics and probability distributions were applied to %Coated values, in addition to the quality of measurements using DIP. The DIP values exhibited sensitivity across all examined covering scenarios, with statistical tests suggesting a high likelihood of accurately representing the %Coated parameter from the assessed probability distributions. In conclusion, the developed software enables satisfactory quantification of %Coated. Furthermore, this study indicates that the adhesion test results must be represented considering the data variability, with the Beta distribution being a good way to represent the behavior.
•The Beta distribution of probability represents the result of the aggregate-binder adhesiveness test.•100 particles are a reasonable number of observations to represent the Brazilian adhesiveness test.•The adhesion test can be represented with a mean value if the samples are close to 100 or 0 % of the coated aggregate area.•Steel slag aggregates, when compared to crushed mineral aggregates, demonstrated more uniform adhesion.•The binder brightness significantly influences the digital image processing with only samples with modified binders.
The problem associated with automatic plant disease identification using visible range images has received considerable attention in the last two decades, however the techniques proposed so far are ...usually limited in their scope and dependent on ideal capture conditions in order to work properly. This apparent lack of significant advancements may be partially explained by some difficult challenges posed by the subject: presence of complex backgrounds that cannot be easily separated from the region of interest (usually leaf and stem), boundaries of the symptoms often are not well defined, uncontrolled capture conditions may present characteristics that make the image analysis more difficult, certain diseases produce symptoms with a wide range of characteristics, the symptoms produced by different diseases may be very similar, and they may be present simultaneously. This paper provides an analysis of each one of those challenges, emphasizing both the problems that they may cause and how they may have potentially affected the techniques proposed in the past. Some possible solutions capable of overcoming at least some of those challenges are proposed.
•The challenges involved in the automatic identification of plant diseases are characterised.•The impact of those challenges on current proposals is discussed.•Possible solutions are suggested.•Some future perspectives for the technology are presented.
In concrete structures, surface cracks are important indicators of structural durability and serviceability. Generally, concrete cracks are visually monitored by inspectors who record crack ...information such as the existence, location, and width. Manual visual inspection is often considered ineffective in terms of cost, safety, assessment accuracy, and reliability. Digital image processing has been introduced to more accurately obtain crack information from images. A critical challenge is to automatically identify cracks from an image containing actual cracks and crack-like noise patterns (e.g. dark shadows, stains, lumps, and holes), which are often seen in concrete structures. This article presents a methodology for identifying concrete cracks using machine learning. The method helps in determining the existence and location of cracks from surface images. The proposed approach is particularly designed for classifying cracks and noncrack noise patterns that are otherwise difficult to distinguish using existing image processing algorithms. In the training stage of the proposed approach, image binarization is used to extract crack candidate regions; subsequently, classification models are constructed based on speeded-up robust features and convolutional neural network. The obtained crack identification methods are quantitatively and qualitatively compared using new concrete surface images containing cracks and noncracks.
•The bond strength between UHPC and concrete substrate was investigated experimentally.•30 specimens were tested using bi-surface shear test and different surface preparation.•Sandblasting is ...necessary to achieve better bond strength between UHPC and NC.•Two non-contact methods were incorporated to evaluate concrete surface roughness.•The substrate roughness degree is correlated to bond strength between UHPC and NC.
Exposing bridge elements to severe environmental conditions causes a reduction in service life and durability which demands repair or total replacement. Different strategies for repair and retrofit can be chosen. These strategies include patching, crack repairs, concrete sealers, a protective layer made of concrete or steel. Ultra-high performance concrete offers an option for repairing and retrofitting different structural elements, however, the bond strength between concrete substrates and ultra-high performance concrete can still be considered a knowledge gap in the literature. In this paper, bond strength between ultra-high performance concrete and substrate made of normal concrete with different surface preparation was investigated experimentally. Thirty specimens were tested under bi-surface shear test with different surface preparation, including roughness degree, mechanical connector, and bonding agent. Furthermore, two non-contact test methods including terrestrial laser scanning and digital image processing were incorporated to evaluate the roughness of the substrate interface and correlate the roughness degree to the bond strength between the two materials. The results showed that an adequate roughness for the interfacial surface with or without mechanical connectors transferred the failure mode to the concrete substrate indicating high bond strength between the two materials if compared to interfacial surfaces without any preparat;ion. In addition, the use of bonding agent could harm the bond strength between the two material which is inappropriate for retrofitting. The result from scanning and image processing showed that both methods qualitatively identified the degree of interface roughness and their result can be correlated to bond strength.
It is significant to study power device package fatigue failure as it seriously affects the reliability of power system. Nevertheless, the research of power device failure process is insufficient. In ...this paper, an accurate and intelligent approach is proposed to predict the power device fatigue failure process with multiple fatigue sampling method (MFSM) and minimal component unit method (MCUM). MFSM is proposed to accurately build the power device lifetime model. It is accomplished through multiple sampling fatigue morphology evolution process of solder layers combined with the fatigue parameter. Morphology evolution is detected by scanning acoustic microscope (SAM) technology under accelerated lifetime test (ALT). The fatigue parameter is got through finite element analysis (FEA) by establishing each sampling geometry model. Then, the lifetime model is determined by their same failure area fraction ( F s ). In particular, digital image processing (DIP) is applied to detailly describe solder layer shapes which is also the key to building a real FEA geometry model. MCUM is utilized to complete the prediction of failure process, where solder layers are divided into minimal units and the FEA solution and location information of each unit are known. Based on lifetime model, the failure area can be got and the fatigue failure process can be finished intelligently by cosimulation. The proposed method is accurate and intelligent enough in predicting the failure of solder layers which is more helpful for planned device management.
Visual Tracking: An Experimental Survey Smeulders, Arnold W. M.; Chu, Dung M.; Cucchiara, Rita ...
IEEE transactions on pattern analysis and machine intelligence,
07/2014, Volume:
36, Issue:
7
Journal Article
Peer reviewed
Open access
There is a large variety of trackers, which have been proposed in the literature during the last two decades with some mixed success. Object tracking in realistic scenarios is a difficult problem, ...therefore, it remains a most active area of research in computer vision. A good tracker should perform well in a large number of videos involving illumination changes, occlusion, clutter, camera motion, low contrast, specularities, and at least six more aspects. However, the performance of proposed trackers have been evaluated typically on less than ten videos, or on the special purpose datasets. In this paper, we aim to evaluate trackers systematically and experimentally on 315 video fragments covering above aspects. We selected a set of nineteen trackers to include a wide variety of algorithms often cited in literature, supplemented with trackers appearing in 2010 and 2011 for which the code was publicly available. We demonstrate that trackers can be evaluated objectively by survival curves, Kaplan Meier statistics, and Grubs testing. We find that in the evaluation practice the F-score is as effective as the object tracking accuracy (OTA) score. The analysis under a large variety of circumstances provides objective insight into the strengths and weaknesses of trackers.
Selective Search for Object Recognition Uijlings, J. R. R.; van de Sande, K. E. A.; Gevers, T. ...
International journal of computer vision,
09/2013, Volume:
104, Issue:
2
Journal Article
Peer reviewed
Open access
This paper addresses the problem of generating possible object locations for use in object recognition. We introduce selective search which combines the strength of both an exhaustive search and ...segmentation. Like segmentation, we use the image structure to guide our sampling process. Like exhaustive search, we aim to capture all possible object locations. Instead of a single technique to generate possible object locations, we diversify our search and use a variety of complementary image partitionings to deal with as many image conditions as possible. Our selective search results in a small set of data-driven, class-independent, high quality locations, yielding 99 % recall and a Mean Average Best Overlap of 0.879 at 10,097 locations. The reduced number of locations compared to an exhaustive search enables the use of stronger machine learning techniques and stronger appearance models for object recognition. In this paper we show that our selective search enables the use of the powerful Bag-of-Words model for recognition. The selective search software is made publicly available (Software:
http://disi.unitn.it/~uijlings/SelectiveSearch.html
).
In this paper, we propose a novel explicit image filter called guided filter. Derived from a local linear model, the guided filter computes the filtering output by considering the content of a ...guidance image, which can be the input image itself or another different image. The guided filter can be used as an edge-preserving smoothing operator like the popular bilateral filter 1, but it has better behaviors near edges. The guided filter is also a more generic concept beyond smoothing: It can transfer the structures of the guidance image to the filtering output, enabling new filtering applications like dehazing and guided feathering. Moreover, the guided filter naturally has a fast and nonapproximate linear time algorithm, regardless of the kernel size and the intensity range. Currently, it is one of the fastest edge-preserving filters. Experiments show that the guided filter is both effective and efficient in a great variety of computer vision and computer graphics applications, including edge-aware smoothing, detail enhancement, HDR compression, image matting/feathering, dehazing, joint upsampling, etc.
This paper presents a fiducial marker system specially appropriated for camera pose estimation in applications such as augmented reality and robot localization. Three main contributions are ...presented. First, we propose an algorithm for generating configurable marker dictionaries (in size and number of bits) following a criterion to maximize the inter-marker distance and the number of bit transitions. In the process, we derive the maximum theoretical inter-marker distance that dictionaries of square binary markers can have. Second, a method for automatically detecting the markers and correcting possible errors is proposed. Third, a solution to the occlusion problem in augmented reality applications is shown. To that aim, multiple markers are combined with an occlusion mask calculated by color segmentation. The experiments conducted show that our proposal obtains dictionaries with higher inter-marker distances and lower false negative rates than state-of-the-art systems, and provides an effective solution to the occlusion problem.
•We propose an algorithm for generating configurable marker dictionaries.•We derive the maximum theoretical inter-marker distance.•A method for automatically detecting the markers and correcting errors is proposed.•A solution to the occlusion problem in augmented reality applications is shown.