Publicaciones

AUTHORS

Domingo Mery, Christian Pieringer

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.

AUTHORS

Domingo Mery, Christian Pieringer

ABSTRACT

In this chapter, we present the dataset that is used in this book to illustrate and test several methods. The database consists of 23,189 X-ray images. The images are organized in a public database called GDXray+that can be used free of charge, but for research and educational purposes only. The database includes five groups of X-ray images: castings, welds, baggage, natural objects, and settings. Each group has several series, and each series several X-ray images. Most of the series are annotated or labeled. In such cases, the coordinates of the bounding boxes of the objects of interest or the labels of the images are available in standard text files. The size of GDXray+is 4.5 GB and it can be downloaded from our website.

AUTHORS

Domingo Mery, Christian Pieringer

ABSTRACT

In order to evaluate the performance of computer vision techniques, computer simulation can be a useful tool. In this chapter, we review some basic concepts of the simulation of X-ray images, and present simple geometric and imaging models that can be used in the simulation. We explain the basic simulation principles and we address some techniques of simulated defects (that can be used to assess the performance of a computer vision method for automated defect recognition) and simulation of threat objects (that can be used to assess the performance of computer vision methods, to enhance the training dataset, or to improve a training program for human inspectors). Afterwards, the chapter gives an overview of the use of Generative Adversarial Networks (GANs) in the simulation of realistic X-ray images. Finally, we present ‘aRTist’, a simulation software that can be used to generate very realistic X-ray images. The chapter also has some Python examples that the reader can run and follow easily.

AUTHORS

Domingo Mery, Christian Pieringer

ABSTRACT

In this chapter, we cover several topics that are used to represent an X-ray image (or a specific region of an X-ray image). This representation means that new features are extracted from the original image that can give us more information than the raw information expressed as a matrix of gray values. This kind of information is extracted as features or descriptors, i.e., a set of values, that can be used in pattern recognition problems such as object recognition, defect detection, etc. The chapter explains geometric and intensity features, and local descriptors and sparse representations that are very common in computer vision applications. It is worthwhile to mention, that the features mentioned in this chapter are called handcrafted features, in contrast to the learned features that are explained in Chap. 7 using deep learning techniques. Finally, the chapter addresses some feature selection techniques that can be used to chose which features are relevant in terms of extraction.

AUTHORS

Domingo Mery, Christian Pieringer

ABSTRACT

X-ray testing has been developed for the inspection of materials or objects, where the aim is to analyze—nondestructively—those inner parts that are undetectable to the naked eye. Thus, X-ray testing is used to determine if a test object deviates from a given set of specifications. Typical applications are the inspection of automotive parts, quality control of welds, baggage screening, analysis of food products, inspection of cargos, and quality control of electronic circuits. In order to achieve efficient and effective X-ray testing, automated and semi-automated systems based on computer vision algorithms are being developed to execute this task. In this book, we present a general overview of computer vision approaches that have been used in X-ray testing in the last decades. In this chapter, we offer an introduction to our book by covering relevant issues of X-ray testing.

AUTHORS

Domingo Mery

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.

AUTHORS

Domingo Mery, Gabriel Duran, Patricio de la Cuadra

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.

AUTHORS

Domingo Mery, Christian Pieringer

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.

AUTHORS

Xian Tao, Ku Young Young, Domingo Mery, Eric Juwei Cheng, Jie Yang, Mukesh Prasad, Ding Rong Zheng, Chin Teng Lin

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.

AUTHORS

Domingo Mery

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.