Deep learning for symbols detection and classification in engineering drawings

Abstract

Engineering drawings are commonly used in different industries such as Oil and Gas, construction, and other types of engineering. Digitising these drawings is becoming increasingly important. This is mainly due to the need to improve business practices such as inventory, assets management, risk analysis, and other types of applications. However, processing and analysing these drawings is a challenging task. A typical diagram often contains a large number of different types of symbols belonging to various classes and with very little variation among them. Another key challenge is the class-imbalance problem, where some types of symbols largely dominate the data while others are hardly represented in the dataset. In this paper, we propose methods to handle these two challenges. First, we propose an advanced bounding-box detection method for localising and recognising symbols in engineering diagrams. Our method is end-to-end with no user interaction. Thorough experiments on a large collection of diagrams from an industrial partner proved that our methods accurately recognise more than 94% of the symbols. Secondly, we present a method based on Deep Generative Adversarial Neural Network for handling class-imbalance.The proposed GAN model proved to be capable of learning from a small number of training examples. Experiment results showed that the proposed method greatly improved the classification of symbols in engineering drawings.

CDSMOTE: class decomposition and synthetic minority class oversampling technique for imbalanced-data classification

“…More recently, Generative Adversarial Neural Networks (GAns) have been applied successfully to handle class-imbalance, by synthesizing new samples of the minority class's instances to handle the imbalance problem. A typical example was presented in [14,41,42] where a new data augmentation approach using variants of GANs to handle the class-imbalance problem was presented. Using image-based datasets, the methods showed favorable performance over other traditional sampling techniques.…”

“…Class-imbalance classification is a long withstanding problem in the literature [1][2][3][4][5] where a binary dataset contains a disproportionately larger amount of samples of the majority class (i.e., negative class) [6]. Such datasets are common in many domains including life sciences [7], protein classification [8], DNA sequence recognition [9], financial sector [10], Medical domain [11], Medicine rating and recommendations [12], engineering drawings analysis [13][14][15] and others. An example of a binary classification problem is shown in Eq.…”

A Deep Learning Digitisation Framework to Mark up Corrosion Circuits in Piping and Instrumentation Diagrams

“…The first one involves the use of heuristics to detect certain well-known shapes, such as geometrical symbols, arrows, connectors, tables and even text [3], [4], [5], [6]. The second and most recent one relies on deep learning techniques in which the algorithms are trained to recognise shapes based on the collection and tagging of numerous samples [7], [8], [9], [10]. Both approaches have advantages and disadvantages depending on the use case.…”

Object Detection, Distributed Cloud Computing and Parallelization Techniques for Autonomous Driving Systems

“…GAN architecture [41] These networks are typically used to generate more data samples so that the data used to train classification systems can be improved. Most notably, this has been applied for industrial applications such as face detection [42], fish classification [43] and symbol recognition in engineering drawings [44].…”