DSpace Angular :: Browsing by Author "Mery, Domingo"

Browsing by Author "Mery, Domingo"

Now showing 1 - 20 of 20

A systematic review and meta-analysis of artificial intelligence versus clinicians for skin cancer diagnosis
(2024) Salinas, María Paz; Sepúlveda, Javiera; Hidalgo, Leonel; Peirano, Dominga; Morel, Macarena; Uribe, Pablo; Rotemberg, Verónica; Briones, Juan; Mery, Domingo; Navarrete-Dechent, Cristian
Scientific research of artificial intelligence (AI) in dermatology has increased exponentially. The objective of this study was to perform a systematic review and meta-analysis to evaluate the performance of AI algorithms for skin cancer classification in comparison to clinicians with different levels of expertise. Based on PRISMA guidelines, 3 electronic databases (PubMed, Embase, and Cochrane Library) were screened for relevant articles up to August 2022. The quality of the studies was assessed using QUADAS-2. A meta-analysis of sensitivity and specificity was performed for the accuracy of AI and clinicians. Fifty-three studies were included in the systematic review, and 19 met the inclusion criteria for the meta-analysis. Considering all studies and all subgroups of clinicians, we found a sensitivity (Sn) and specificity (Sp) of 87.0% and 77.1% for AI algorithms, respectively, and a Sn of 79.78% and Sp of 73.6% for all clinicians (overall); differences were statistically significant for both Sn and Sp. The difference between AI performance (Sn 92.5%, Sp 66.5%) vs. generalists (Sn 64.6%, Sp 72.8%), was greater, when compared with expert clinicians. Performance between AI algorithms (Sn 86.3%, Sp 78.4%) vs expert dermatologists (Sn 84.2%, Sp 74.4%) was clinically comparable. Limitations of AI algorithms in clinical practice should be considered, and future studies should focus on real-world settings, and towards AI-assistance.
Author Correction: A systematic review and meta-analysis of artificial intelligence versus clinicians for skin cancer diagnosis
(2024) Salinas Espinoza, María Paz; Sepúlveda, Javiera; Hidalgo, Leonel; Peirano, Dominga; Morel, Macarena; Uribe, Pablo; Rotemberg, Verónica; Briones, Juan; Mery, Domingo; Navarrete Dechent, Cristian Patricio
Automated Detection of Welding Discontinuities without Segmentation
(AMER SOC NONDESTRUCTIVE TEST, 2011) Mery, Domingo
Automated fish bone detection using X-ray imaging
(ELSEVIER SCI LTD, 2011) Mery, Domingo; Lillo, Ivan; Loebel, Hans; Riffo, Vladimir; Soto, Alvaro; Cipriano, Aldo; Miguel Aguilera, Jose
In countries where fish is often consumed, fish bones are some of the most frequently ingested foreign bodies encountered in foods. In the production of fish fillets, fish bone detection is performed by human inspection using their sense of touch and vision which can lead to misclassification. Effective detection of fish bones in the quality control process would help avoid this problem. For this reason, an X-ray machine vision approach to automatically detect fish bones in fish fillets was developed. This paper describes our approach and the corresponding experiments with salmon and trout fillets. In the experiments, salmon X-ray images using 10 x 10 pixels detection windows and 24 intensity features (selected from 279 features) were analyzed. The methodology was validated using representative fish bones and trouts provided by a salmon industry and yielded a detection performance of 99%. We believe that the proposed approach opens new possibilities in the field of automated visual inspection of salmon, trout and other similar fish. (C) 2011 Elsevier Ltd. All rights reserved.
Automated visual testing using trifocal analysis in an uncalibrated sequence of images
(AMER SOC NONDESTRUCTIVE TEST, 2006) Carrasco, Miguel A.; Mery, Domingo
Automated visual testing using multiple views has been recently developed to automatically detect discontinuities in manufactured objects. The principal idea of this strategy is that, unlike the noise that appears randomly in images, only the discontinuities remain stable in a sequence of images because they remain in their position relative to the movement of the object being analyzed. This sort of multiple view imaging has been successfully applied in sequences of calibrated images for which the 3D -> 2D transference function for the projection of the views is known precisely. Nonetheless, its application in industrial environments is difficult because of the instabilities inherent in the system. This investigation proposes a new strategy, based on the detection of discontinuities in a uncalibrated sequence of images, The methodology consists in constructing a model and carrying out a trifocal analysis that allows the determination of the real position of a discontinuity using corresponding control points in the sequence. Experimental results obtained on radioscopic images of die castings illustrate the potential in the detection of discontinuities in uncalibrated images, detecting the totality of the discontinuities in the sequence.
Automatic Threat Detection in Single, Stereo (Two) and Multi View X-Ray Images
(IEEE, 2020) Tuli, Abhina; Bohra, Rohi; Moghe, Tanma; Chaturvedi, Niti; Mery, Domingo; Dhiraj
Accurate X-ray screening systems are of paramount importance in the present day. Most existing systems predict only on the basis of a single image, which could lead to false positives and false negatives due to limited information present. We implemented several approaches using single, two and multiple X-Ray views to make a reliable and practical model with varying levels of success in threat object detection. These approaches include long-established methods such as Bag of Visual Words (BOVW), 3D Object Recognition, Adaptive Implicit Shape Model and Deep Neural Networks. The approaches took in dual inputs to make more informed predictions. Varying levels of success are obtained in these methods ranging from 73% using BOVW to 87% using Deep CNN. It was observed that, when two views of an object are considered, an improvement of 5% to 15% in performance took place (considering various approaches) compared to a single view.
Color development and acrylamide content of pre-dried potato chips
(ELSEVIER SCI LTD, 2007) Pedreschi, Franco; Leon, Jorge; Mery, Domingo; Moyano, Pedro; Pedreschi, Romina; Kaack, Karl; Granby, Kit
The objective of this work was to study the development of color formation in pre-dried potato slices during frying and acrylamide formation in the final potato chips. Color measurement was done by using an inexpensive computer vision technique which allowed quantifying representatively and precisely the color of complex surfaces such as those of potato chips in L*a*b* units from RGB images. Prior to frying, potato slices (Desiree variety, diameter: 37 mm, width: 2.2 mm) were blanched in hot water at 85 degrees C for 3.5 min. Unblanched slices were considered as the control. Slices of the same dimensions were blanched as in the previous step, and then air-dried until reaching a moisture content of 60% (wet basis). These samples were called pre-dried potato slices. Potato slices were fried at 120 degrees C, 140 degrees C, 160 degrees C and 180 degrees C until reaching moisture contents of similar to 1.8% (total basis) for color quantification. Acrylamide concentration was determined only in final chips fried at 120 degrees C, 150 degrees C and 180 degrees C and compared with that of two brands of commercial chips produced in Chile (Moms and Frito Lay). Color values in L*a*b* units were recorded at different sampling times during frying at the four mentioned temperatures using the total color difference parameter (Delta E). Pre-drying did not affect the color of potato chips considerably when compared against blanched chips; however when fried at 180 degrees C, pre-dried potato chips present 44%, 22%, 44% lower acrylamide content than that of the control, Moms and Frito Lay chips, respectively. (c) 2006 Elsevier Ltd. All rights reserved.
Color kinetics and acrylamide formation in NaCl soaked potato chips
(ELSEVIER SCI LTD, 2007) Pedreschi, Franco; Bustos, Oscar; Mery, Domingo; Moyano, Pedro; Kaack, Karl; Granby, Kit
The objective of this work was to study the kinetics of color development in blanched and blanched-NaCl impregnated potato slices during frying by using the dynamic method and also to evaluate the effect of NaCl in reducing acrylamide formation in potato chips. The measurement of color was done by using an inexpensive computer vision technique which allowed quantifying in a more precise and representative way the color in L*a*b* units of complex surfaces such as those of potato slices during frying. The effect of potato slice soaking in NaCl was evaluated not only for color change but also for acrylamide formation. Prior to frying, potato slices (Desiree variety, diameter: 37 mm, width: 2.2 min) were blanched in hot water at 85 degrees C for 3.5 min; these slices were considered as the control. Slices of the same dimensions were blanched as in the previous step, and soaked at 25 degrees C in a NaCl solution of 0.02 g/l 5 min at 200 rpm of agitation. These samples were considered as NaCl soaked potato chips.
Color measurement in L*a*b* units from RGB digital images
(ELSEVIER, 2006) Leon, Katherine; Mery, Domingo; Pedreschi, Franco; Leon, Jorge
The superficial appearance and color of food are the first parameters of quality evaluated by consumers, and are thus critical factors for acceptance of the food item by the consumer. Although there are different color spaces, the most used of these in the measuring of color in food is the L*a*b* color space due to the uniform distribution of colors, and because it is very close to human perception of color. In order to carry out a digital image analysis in food, it is necessary to know the color measure of each pixel on the surface of the food item. However, there are at present no commercial L*17*b* color measures in pixels available because the existing commercial colorimeters generally measure small, non-representative areas of a few square centimeters. Given that RGB digital cameras obtain information in pixels, this article presents a computational solution that allows the obtaining of digital images in L*a*b* color units for each pixel of the digital RGB image. This investigation presents five models for the RGB -> L*a*b* conversion and these are: linear, quadratic, gamma, direct, and neural network. Additionally, a method is suggested for estimating the parameters of the models based on a minimization of the mean absolute error between the color measurements obtained by the models, and by a commercial colorimeter for uniform and homogenous surfaces. In the evaluation of the performance of the models, the neural network model stands out with an error of only 0.93%. On the basis of the construction of these models, it is possible to find a L*a*b* color measuring system that is appropriate for an accurate, exacting and detailed characterization of a food item, thus improving quality control and providing a highly useful tool for the food industry based on a color digital camera. (c) 2006 Elsevier Ltd. All rights reserved.
Detection and classification of weld discontinuities in radiographic images (Part I: Supervised learning)
(AMER SOC NONDESTRUCTIVE TEST, 2007) de Padua, Germano X.; da Silva, Romeu R.; Mery, Domingo; Siqueira, Marcio H. S.; Rebello, Joao M. A.; Caloba, Luiz P.
Radiographic testing of weld joints is of great importance for verifying and maintaining weld quality. This work presents a new technique for the development Of an automatic or semiautomatic system for radiographic weld analysis. This technique uses gray level profiles transversal to weld beads in radiographic patterns. These profiles were processed to aid in the setup of nonlinear pattern classifiers developed by neural networks with algorithms by backpropagation of error. The classification accuracy was estimated via the average correctness of 10 randomly chosen test sets. The results presented a general accuracy of classification correctness of around 95% for the class patterns in the profiles that were used.
Detection and Classification of Weld Discontinuities in Radiographic Images (Part III: Unsupervised Learning - Phenomenological Analysis)
(AMER SOC NONDESTRUCTIVE TEST, 2008) de Padua, Germano X.; da Silva, Romeu R.; Mery, Domingo; Rebello, Joao M. A.; Caloba, Luiz P.
This is the third and final installment of a three-part article on detection and classification of discontinuities appearing in radiographic images of welds. The present installment is the continuation of the section on unsupervised pattern recognition. In this work, the authors present the phenomenological analysis of the pattern profiles of weld discontinuities that resulted from the adaptive resonance theory (ART) networks that were carried out. It is recommended that the previous parts of this article (de Padua et al., 2007a; 2007b) be read before the present installment.
Development of a computer vision system to measure the color of potato chips
(ELSEVIER, 2006) Pedreschi, Franco; Leon, Jorge; Mery, Domingo; Moyano, Pedro
The objective of this research was to design and implement an inexpensive computer vision system for measuring the color of a highly heterogeneous food material not only in shape as well in color such as potato chips in L*a*b* units from RGB images. The system was composed of (i) a digital color camera for acquiring the images in a digital format, (ii) a computer for storage the images, (c) image analysis routines integrated into a software programmed in Matlab that converts the color RGB of the food image into L*a*b* units. In this way the color of potato chips can be calculated in L*a*b* units over representative areas and in a reproducible way. The kinetics of color changes in potato slices during frying at four temperatures was followed using the implemented computer vision system (CVS). Color values in L*a*b* units were recorded at different sampling times during frying at the four oil temperatures using the total color change parameter (AE). Chips fried at higher temperatures get darker as expected and showed by the CVS. The implemented computer vision system can be used to study as well foods different from potato chips by selecting their proper settings for image acquisition and digital image processing. (c) 2006 Elsevier Ltd. All rights reserved.
Distinguishing a planetary transit from false positives: a Transformer-based classification for planetary transit signals
(2023) Salinas, Helem; Pichara, Karim; Brahm, Rafael; Perez-Galarce, Francisco; Mery, Domingo
Current space-based missions, such as the Transiting Exoplanet Survey Satellite (TESS), provide a large database of light curves that must be analysed efficiently and systematically. In recent years, deep learning (DL) methods, particularly convolutional neural networks (CNN), have been used to classify transit signals of candidate exoplanets automatically. However, CNNs have some drawbacks; for example, they require many layers to capture dependencies on sequential data, such as light curves, making the network so large that it eventually becomes impractical. The self-attention mechanism is a DL technique that attempts to mimic the action of selectively focusing on some relevant things while ignoring others. Models, such as the Transformer architecture, were recently proposed for sequential data with successful results. Based on these successful models, we present a new architecture for the automatic classification of transit signals. Our proposed architecture is designed to capture the most significant features of a transit signal and stellar parameters through the self-attention mechanism. In addition to model prediction, we take advantage of attention map inspection, obtaining a more interpretable DL approach. Thus, we can identify the relevance of each element to differentiate a transit signal from false positives, simplifying the manual examination of candidates. We show that our architecture achieves competitive results concerning the CNNs applied for recognizing exoplanetary transit signals in data from the TESS telescope. Based on these results, we demonstrate that applying this state-of-the-art DL model to light curves can be a powerful technique for transit signal detection while offering a level of interpretability.
Evaluation of Acoustic Emission Signal Parameters for Identifying the Propagation of Discontinuities in Pressurized Tubes
(AMER SOC NONDESTRUCTIVE TEST, 2008) da Silva, Romeu Ricardo; Mery, Domingo; Soares, Sergio Damasceno
Acoustic emission tests are highly relevant among nondestructive tests applied to equipment in the petroleum industry. This paper presents methodologies for the classification of acoustic emission patterns obtained in testing to identify the propagation of discontinuities in pressurized tribes. This work is a continuation of previous research. To estimate the accuracy of tire classification and give greater reliability to previous results, rise is made in this paper of new signals with a greater number of parameters, and some new methodologies not used in previous work are presented here. The new results show tire efficiency of the pattern classification techniques implemented.
Fair Face Verification by Using Non-Sensitive Soft-Biometric Attributes
(2022) Villalobos, Esteban; Mery, Domingo; Bowyer, Kevin
Facial recognition has been shown to have different accuracy for different demographic groups. When setting a threshold to achieve a specific False Match Rate (FMR) on a mixed demographic impostor distribution, some demographic groups can experience a significantly worse FMR. To mitigate this, some authors have proposed to use demographic-specific thresholds. However, this can be impractical in an operational scenario, as it would either require users to report their demographic group or the system to predict the demographic group of each user. Both of these options can be deemed controversial since the demographic group is a sensitive attribute. Further, this approach requires listing the possible demographic groups, which can become controversial in itself. We show that a similar mitigation effect can be achieved using non-sensitive predicted soft-biometric attributes. These attributes are based on the appearance of the users (such as hairstyle, accessories, and facial geometry) rather than how the users self-identify. Our experiments use a set of 38 binary non-sensitive attributes from the MAAD-Face dataset. We report results on the Balanced Faces in the Wild dataset, which has a balanced number of identities by race and gender. We compare clustering-based and decision-tree-based strategies for selecting thresholds. We show that the proposed strategies can reduce differential outcomes in intersectional groups twice as effectively as using gender-specific thresholds and, in some cases, are also better than using race-specific thresholds.
Multi-scale flow structure of a strike-slip tectonic setting: A self-similar model for the Liquine-Ofqui Fault System and the Andean Transverse Faults, Southern Andes (39-40 degrees S)
(PERGAMON-ELSEVIER SCIENCE LTD, 2022) Roquer, Tomas; Arancibia, Gloria; Crempien, Jorge G. F.; Mery, Domingo; Rowland, Julie; Sepulveda, Josefa; Veloso, Eugenio E.; Nehler, Mathias; Bracke, Rolf; Morata, Diego
The flow structure of a brittle crustal volume is defined by the multi-scale geometric and hydraulic properties of its fracture meshes. The length density distribution n(L,l) and the transmissivity distribution K(L,l) control the hydrologic scaling, where l is fracture length and L is the system size. The flow structure might display at most three key hydrologic scales: the connection scale, above which flow is focused in few critical paths; the channeling scale, above which flow is distributed in several paths; and the homogenization scale, above which permeability approaches a constant value. According to these scales, the hydrological structure could be distributed or clustered, thus having a clear impact in geothermal exploration campaigns and reservoir modeling. In this work, we determine the multi-scale flow structure for the Liquine-Ofqui Fault System (LOFS) and the Andean Transverse Faults (ATF) in the Southern Andes, by establishing the hydrologic scaling they follow. Using fractal statistics, we integrated geological data at the regional, meso-and micro-scale, including image analysis from X-ray microtomography. Our results suggest a self-similar, dense network with n(L,l)similar to l(-a) and a = 2.6-2.9, from the regional scale where the LOFS and ATF interact to the meso-and micro-scale within highly fractured areas of the LOFS. Scaling models are constrained by the length distribution, and other power-law functions reflecting the geometric arrangement of fractures, as well as the spatial distribution of superficial geothermal occurrences. Thus, we expect the hydrologic scaling to depend on the transmissivity distribution. Lognormal transmissivity distribution yields a permeability increase with scale, from the connection to the homogenization scales; whereas power-law transmissivity distribution yields a permeability increase from the connection scale without a limiting value. Approximations of the connection scale are around 10(-3)-10(0) m; the channeling scale, around 100-104 m; and if the homogenization scale exists, it should be equal or greater than 10(3)-10(4) m. Finally, the results presented here could to define the internal architecture of fracture meshes in fault-controlled fluid flow, and be used to select an appropriate hydrologic model according to the analyzed scale. Therefore, these findings must be taken into consideration in future geothermal prospecting, modeling and exploitation.
Quality classification of corn tortillas using computer vision
(ELSEVIER SCI LTD, 2010) Mery, Domingo; Chanona Perez, Jorge J.; Soto, Alvaro; Miguel Aguilera, Jose; Cipriano, Aldo; Velez Rivera, Nayeli; Arzate Vazquez, Israel; Gutierrez Lopez, Gustavo F.
Computer vision is playing an increasingly important role in automated visual food inspection. However, quality control in tortilla production is still performed by human operators which may lead to misclassification due to their subjectivity and fatigue. In order to reduce the need for human operators and therefore misclassification, we developed a computer vision framework to automatically classify the quality of corn tortillas according to five hedonic sub-classes given by a sensorial panel. The proposed framework analyzed 750 corn tortillas obtained from 15 different Mexican commercial stores which were either small, medium or large in size. More than 2300 geometric and color features were extracted from 1500 images capturing both sides of the 750 tortillas. After implementing a feature selection algorithm, in which the most relevant features were selected for the classification of the five sub-classes, only 64 features were required to design a classifier based on support vector machines. Cross-validation yielded a performance of 95% in the classification of the five hedonic sub-classes. Additionally, using only 10 of the selected features and a simple statistical classifier, it was possible to determine the origin of the tortillas with a performance of 96%. We believe that the proposed framework opens up new possibilities in the field of automated visual inspection of tortillas. (c) 2010 Elsevier Ltd. All rights reserved.
The state of the art of weld seam radiographic testing: part 1, image processing
(AMER SOC NONDESTRUCTIVE TEST, 2007) Ricardo da Silva, Romeu; Mery, Domingo
Over the past 30 years, a large amount of research has been conducted to develop an automatic (or semiautomatic) system for the radiographic detection and classification of discontinuities in continuous welds. There are two major types of research in this field: image processing, which consists of improving radiographic image quality and segmenting regions of interest in the images, and pattern recognition, which aims at detecting and classifying the discontinuities segmented in the images. Because of the complexity of the problem of detecting weld discontinuities, a large number of techniques have been investigated in these areas. This paper represents a state of the art report on weld testing and is divided into separate parts on image processing and pattern recognition. The techniques presented are compared at each basic step of system development for the identification of discontinuities in continuous welds. This part deals with image processing.
The state of the art of weld seam radiographic testing: Part II, pattern recognition
(AMER SOC NONDESTRUCTIVE TEST, 2007) Ricardo da Silva, Romeu; Mery, Domingo
Over the last 30 years, there has been a large amount of research attempting to develop an automatic (or semiautomatic) system for the detection and classification of weld discontinuities in continuous welds examined by radiography. There are basically two large types of research areas in this field: image processing, which consists in improving the quality of radiographic images and segmenting regions of interest in the images, and pattern recognition, which aims at detecting and classifying the discontinuities segmented in the images. Because of the complexity of the problem of detecting weld discontinuities, a large number of techniques have been investigated in these areas. This paper represents a state of the art report on weld testing and is divided into the two parts mentioned above: image processing and pattern recognition. The techniques presented are compared at each basic step of the development of the system for the identification of discontinuities in continuous welds. The first part of this paper (included in the June issue of this journal) dealt with image processing. This part deals with pattern recognition.
Visual inspection of glass bottlenecks by multiple-view analysis
(TAYLOR & FRANCIS LTD, 2010) Carrasco, Miguel; Pizarro, Luis; Mery, Domingo
The narrow structure of bottlenecks poses a very challenging problem for automated visual inspection systems and surprisingly, this issue has received little attention in literature. Bottleneck inspection is highly relevant to the fabrication of glass bottles, e.g., for the wine and beer industry. Defects in glass bottles can arise in various situations such as an incomplete reaction in a batch, batch contaminants and interactions of the melted material among others. This paper presents an inspection approach that utilises geometry of multiple views along with a rich set of feature descriptors to discriminate real flaws from false alarms in uncalibrated images of glass bottlenecks. The proposed method is based on an automatic multiple view inspection (AMVI) technique for the automatic detection of flaws. This technique involves an initial step that extracts numerous segmented regions from a set of views of the object under inspection. These regions are subsequently classified either as real flaws or as false alarms. The classification process considers that image noise and false alarms occur as random events in different views while real flaws induce geometric and featural relations in the views where they appear. Therefore, by analysing such relations it is possible to successfully localise real flaws and to discard a large number of false alarms. An important characteristic of the proposed methodology is the complete lack of camera calibration which makes our method very suitable for applications where camera calibration is difficult or expensive to carry out. Our inspection system achieves a true positive rate of 99.1% and a false positive rate of 0.9%.

Browsing by Author "Mery, Domingo"

Results Per Page

Sort Options