Domingo Mery

Domingo Mery

Especialidad: Computer Vision. Machine Learning, Pattern Recognition, Visual Recognition, Object Detection. Medical Imaging, Machine Vision.
Domingo Mery es profesor titular del Departamento de Ciencias de la Computación de la Pontificia Universidad Católica de Chile. Tiene una maestría en el Instituto de Tecnología de Karlsruhe, Alemania, y  un Ph.D con distinción en la Universidad Técnica de Berlín, Alemania. Es autor de más de 90 publicaciones técnicas de SCI y de más de 90 ponencias en congresos. Se desempeña como editor asociado de IEEE Transactions on Information, Forensics and Security, IEEE Transactions on Transactions on Biometrics, Behavior, and Identity Science.

PUBLICACIONES

Publisher: Multimedia Tools and Applications, Link>

ABSTRACT

This paper proposes a novel online self-learning detection system for different types of objects. It allows users to random select detection target, generating an initial detection model by selecting a small piece of image sample and continue training the detection model automatically. The proposed framework is divided into two parts: First, the initial detection model and the online reinforcement learning. The detection model is based on the proportion of users of the Haar-like features to generate feature pool, which is used to train classifiers and get positive-negative (PN) classifier model. Second, as the videos plays, the detecting model detects the new sample by Nearest Neighbor (NN) Classifier to get the PN similarity for new model. Online reinforcement learning is used to continuously update classifier, PN model and new classifier. The experiment shows the result of less detection sample with automatic online reinforcement learning is satisfactory.


Publisher: Machine Vision and Applications, Link>

ABSTRACT

In the automotive industry, light-alloy aluminum castings are an important element for determining roadworthiness. X-ray testing with computer vision is used during automated inspections of aluminum castings to identify defects inside of the test object that are not visible to the naked eye. In this article, we evaluate eight state-of-the-art deep object detection methods (based on YOLO, RetinaNet, and EfficientDet) that are used to detect aluminum casting defects. We propose a training strategy that uses a low number of defect-free X-ray images of castings with superimposition of simulated defects (avoiding manual annotations). The proposed solution is simple, effective, and fast. In our experiments, the YOLOv5s object detector was trained in just 2.5 h, and the performance achieved on the testing dataset (with only real defects) was very high (average precision was 0.90 and the F1 factor was 0.91). This method can process 90 X-ray images per second, i.e. ,this solution can be used to help human operators conduct real-time inspections. The code and datasets used in this paper have been uploaded to a public repository for future studies. It is clear that deep learning-based methods will be used more by the aluminum castings industry in the coming years due to their high level of effectiveness. This paper offers an academic contribution to such efforts.


Publisher:, Link>

ABSTRACT

In this chapter, relevant applications on X-ray testing are described. We cover X-ray testing in (i) castings, (ii) welds, (iii) baggage, (iv) natural products, and (v) others (like cargos and electronic circuits). For each application, the state of the art is presented. Approaches in each application are summarized showing how they use computer vision techniques. A detailed approach is shown in each application and some examples using Python are given in order to illustrate the performance of the methods.


Publisher:, Link>

ABSTRACT

With the recent surge in threats to public safety, the security focus of several organizations has been moved towards enhanced intelligent screening systems. Conventional X-ray screening, which relies on the human operator is the best use of this technology, allowing for the more accurate identification of potential threats. This paper explores X-ray security imagery by introducing a novel approach that generates realistic synthesized data, which opens up the possibility of using different settings to simulate occlusion, radiopacity, varying textures, and distractors to generate cluttered scenes. The generated synthetic data is effective in the training of deep networks. It allows better generalization on training data to deal with domain adaptation in the real world. The extensive set of experiments in this paper provides evidence for the efficacy of synthetic datasets over human-annotated datasets for automated X-ray security screening. The proposed approach outperforms the state-of-the-art approach for a diverse threat object dataset on mean Average Precision (mAP) of region-based detectors and classification/regression-based detectors.


Publisher:, Link>

ABSTRACT

In this chapter, we will cover known classifiers that can be used in X-ray testing. Several examples will be presented using Python. The reader can easily modify the proposed implementations in order to test different classification strategies. We will then present how to estimate the accuracy of a classifier using hold-out, cross-validation and leave-one-out. Finally, we will present an example that involves all steps of a pattern recognition problem, i.e., feature extraction, feature selection, classifier’s design, and evaluation. We will thus propose a general framework to design a computer vision system in order to select—automatically—from a large set of features and a bank of classifiers, those features and classifiers that can achieve the highest performance.

 

Publisher:, Link>

ABSTRACT

In popular music, bass line tends to include relevant infor mation about the chord sequence and thus segmenting musical audio data by bass notes can be used as a mid-level step to improve posterior higher level analysis, as chord detection and music structure analysis. In this paper, we present a comparison between four methods for detecting bass line onsets. The first method uses a multipitch detection algorithm to find the lowest note boundaries. The second method searches spectral differences in a low frequency range. The third uses Convolutional Neural Networks (CNN) and the fourth Recurrent Neural Networks (RNN). These methods are trained and tested on a MIDI rendered audio database, and standard evaluation metrics for detection problems are used, as well as a temporal accuracy for each method. The results are compared to other onset detection systems showing that the deep learning based methods have better performance and time accuracy. We believe that our work comparing standard approaches provides a useful insight on how onset detection methods can be adapted to specific kind of onsets.


Publisher:, Link>

ABSTRACT

Deep learning has been inspired by ideas from neuroscience. The key idea of deep learning is to replace handcrafted features (explained in details in Chap. 5) with features that are learned efficiently using a hierarchical feature extraction approach. Usually, the learned features are so discriminative that no sophisticated classifiers are required. In last years, deep learning has been successfully used in image and video recognition, and it has been established as the state of the art in many areas such as computer vision, machine translation, and natural language processing. In comparison with other computer vision applications, we have seen that the introduction of techniques based on deep learning in computer vision for X-ray testing has been rather slow. However, there are many methods based on deep learning that have been designed and tested in some X-ray testing applications. In this chapter, we review many relevant concepts of deep learning that can be used in computer vision for X-ray testing. We covered the theory and practice of deep learning techniques in real X-ray testing problems. The chapter explained neural networks, Convolutional Neural Network (CNN) that can be used in classification problems, pre-trained models, transfer learning that are used in sophisticated models, Generative Adversarial Networks (GANs) to generate synthetic images, and modern detection methods that are used to classify and localize objects in an image. In addition, for every method, we give not only the basic concepts but also practical details in real X-ray testing examples that have been implemented in Python.


Publisher: Neural Computing and Applications, Link>

ABSTRACT

In the field of security, baggage-screening with X-rays is used as nondestructive testing for threat object detection. This is a common protocol when inspecting passenger baggage particularly at airports. Unfortunately, the accuracy of such human inspection is around 80–90%, under optimal operator conditions. For this reason, it is quite necessary to assist human inspectors with the aid of computer vision algorithms. This work proposes a deep learning-based methodology designed to detect threat objects in (single spectrum) X-ray baggage scan images. For this purpose, our proposed framework simulates a large number of X-ray images, using a combination of PGGAN (Karras et al. in International conference on learning representations, 2018. https://openreview.net/forum?id=Hk99zCeAb) and superimposition (Mery and Katsaggelos in 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW), 2017.https://doi.org/10.1109/CVPRW.2017.37) strategies, that are used to train state-of-the-art detection models such as YOLO (Redmon et al. in You only look once: unified, real-time object detection. CoRR abs/1506.02640, 2015. http://arxiv.org/ abs/1506.02640), SSD (Liu et al. in SSD: single shot multibox detector. CoRR abs/1512.02325, 2015. http://arxiv. org/abs/1512.02325) and RetinaNet (Lin et al. in Focal loss for dense object detection. CoRR abs/1708.02002, 2017. http://arxiv.org/abs/1708.02002). Our method has been tested on real X-ray images in the detection of four categories of threat objects: guns, knives, razor blades and shuriken (ninja stars). In our experiments, YOLOv3 (Redmon and Farhadi in Yolov3: An incremental improvement. CoRR abs/1804.02767, 2018. http://arxiv.org/abs/1804.02767) obtained the best mean average precision (mAP) with 96.3% for guns, 76.2% for knives, 86.9% for razor blades and 93.7% for shuriken, while the average mAP for all threat objects was 80.0%. We believe the effectiveness of our method in the detection of threat objects makes its use in checkpoints possible. Moreover, our methodology is scalable and can be easily extended to detect other categories automatically.


[:es]Publisher: Computers in biology and medicine, Link > Abstract: Recent advances in medical imaging have confirmed the presence of altered hemodynamics in bicuspid aortic valve (BAV) patients. Therefore, there is a need for new hemodynamic biomarkers to refine disease monitoring and improve patient risk stratification. This research aims to analyze and extract multiple correlation patterns of hemodynamic parameters from 4D Flow MRI data and find which parameters allow an accurate classification between healthy volunteers (HV) and BAV patients with dilated and non-dilated ascending aorta using machine learning. Sixteen hemodynamic parameters were calculated in the ascending aorta (AAo) and aortic arch (AArch) at peak systole from 4D Flow MRI. We used sequential forward selection (SFS) and principal component analysis (PCA) as feature selection algorithms. Then, eleven machine-learning classifiers were implemented to separate HV and BAV patients (non- and dilated ascending aorta). Multiple correlation patterns from hemodynamic parameters were extracted using hierarchical clustering. The linear discriminant analysis and random forest are the best performing classifiers, using five hemodynamic parameters selected with SFS (velocity angle, forward velocity, vorticity, and backward velocity in AAo; and helicity density in AArch) a 96.31 ± 1.76% and 96.00 ± 0.83% accuracy, respectively. Hierarchical clustering revealed three groups of correlated features. According to this analysis, we observed that features selected by SFS have a better performance than those selected by PCA because the five selected parameters were distributed according to 3 different clusters. Based on the proposed method, we concluded that the feature selection method found five potentially hemodynamic biomarkers related to this disease.[:]

Publisher: Agronomy, Link>

ABSTRACT

Black spot corresponds to a physiological disorder of the type of oxidative stress that occurs after the prolonged postharvest storage of Persea americana Mill. cv. Hass fruit. Industry tends to confuse this disorder with pathogen attack (Colletotrichum gloeosporioides), chilling injury, mechanical damage during harvest and transport or lenticel damage. The main objectives of this research were: (i) to develop a method to assess and differentiate lenticel damage and black spot and (ii) to study the correlation between mechanical damage and lenticel damage on the development of black spot. Avocado fruits from different orchards were evaluated at two sampling times using different harvesting systems (conventional and appropriate) and at two times of the day (a.m. or p.m.). Here, we report a method based on image analysis to differentiate and quantify lenticel damage and black spot disorder. In addition, the results show that conventional harvest increased lenticel damage and lenticel damage did not correlate with black spot development but correlated with increased weight loss during prolonged postharvest storage. These results have important commercial implications since the appropriate harvesting of avocado cv. Hass would not only control the incidence of lenticel damage, which would be an advantage in terms of external quality, but also reduce weight loss during transport to distant markets.


agencia nacional de investigación y desarrollo
Edificio de Innovación UC, Piso 2
Vicuña Mackenna 4860
Macul, Chile