Yazeed Alaudah

A real-time license plate recognition system for Saudi Arabia using LabVIEW

License Plate Recognition (LPR) systems play an important role in intelligent transportation applications. These systems have been extensively used in highway and bridge charge, ports, airports, gate monitoring, parking and toll applications, to mention a few. In this paper, we propose a real-time LPR system that uses the LabVIEW software and is based on the NI-Camera Vision System. The system adapts automatically to detect license plates from the GCC countries and identify both English & Arabic letters and Numerals. The system uses recently introduced LPs in Saudi Arabia to test the real-time operation. The system was tested using low-resolution images of just 640×480 pixels and achieved a success rate of 94% under optimal conditions. Most importantly, the processing time is under 40 ms/plate outperforming most existing systems which average around 100 ms/plate.

Phase Congruency for image understanding with applications in computational seismic interpretation

Phase Congruency (PC) can highlight small discontinuities in images with varying illumination and contrast using the congruency of phase in Fourier components. PC can not only detect the subtle variations in the image intensity but can also highlight the anomalous values to develop a deeper understanding of the images content and context. In this paper, we propose a new method based on PC for computational seismic interpretation with an application to subsurface structures delineation within migrated seismic volumes. We show the effectiveness of the proposed method as compared to the edge- and texture-based methods for salt domes boundary detection. The subjective and objective evaluation of the experimental results on the real seismic dataset from the North Sea, F3 block show that the proposed method is not only computationally very efficient but also outperforms the state of the art methods for salt dome delineation.

Content-adaptive non-parametric texture similarity measure

In this paper, we introduce a non-parametric texture similarity measure based on the singular value decomposition of the curvelet coefficients followed by a content-based truncation of the singular values. This measure focuses on images with repeating structures and directional content such as those found in natural texture images. Such textural content is critical for image perception and its similarity plays a vital role in various computer vision applications. In this paper, we evaluate the effectiveness of the proposed measure using a retrieval experiment. The proposed measure outperforms the state-of-the-art texture similarity metrics on CUReT and PerTex texture databases, respectively.

A Hybrid Approach for Salt Dome Delineation within Migrated Seismic Volumes

The Gradient of Texture (GoT) can detect subtle changes in the texture of the seismic data along the boundary of salt domes even in the absence of strong reflections, whereas Phase Congruency (PC) can highlight small changes in images of varying illumination and contrast using congruency of phase in Fourier components. In this paper, we propose a hybrid feature, which combines the advantages of both GoT and PC and leads to improved subsurface structures delineation in migrated seismic volumes. This paper outlines the work flow for salt domes delineation which can be modified to capture other geological structures in Earths subsurface as well. The subjective and objective evaluation of the experimental results on the real seismic dataset from the North Sea, F3 block show that the proposed method outperforms the state of the art methods for salt dome delineation.

Learning to label seismic structures with deconvolution networks and weak labels

Recently, there has been increasing interest in using deep learning techniques for various seismic interpretation tasks. However, unlike shallow machine learning models, deep learning models are often far more complex and can have hundreds of millions of free parameters. This not only means that large amounts of computational resources are needed to train these models, but more critically, they require vast amounts of labeled training data as well. In this work, we show how automatically-generated weak labels can be effectively used to overcome this problem and train powerful deep learning models for labeling seismic structures in large seismic volumes. To achieve this, we automatically generate thousands of weak labels and use them to train a deconvolutional network for labeling fault, salt dome, and chaotic regions within the Netherlands F3 block. Furthermore, we show how modifying the loss function to take into account the weak training labels helps reduce false positives in the labeling results. The benefit of this work is that it enables the effective training and deployment of deep learning models to various seismic interpretation tasks without requiring any manual labeling effort. We show excellent results on the Netherlands F3 block, and show how our model outperforms other baseline models.

Multiresolution analysis and learning for computational seismic interpretation

We explore the use of multiresolution analysis techniques as texture attributes for seismic image characterization, especially in representing subsurface structures in large migrated seismic data. Namely, we explore the Gaussian pyramid, the discrete wavelet transform, Gabor filters, and the curvelet transform. These techniques are examined in a seismic structure labeling case study on the Netherlands offshore F3 block. In seismic structure labeling, a seismic volume is automatically segmented and classified according to the underlying subsurface structure using texture attributes. Our results show that multiresolution attributes improved the labeling performance compared to using seismic amplitude alone. Moreover, directional multiresolution attributes, such as the curvelet transform, are more effective than the non-directional attributes in distinguishing different subsurface structures in large seismic datasets, and can greatly help the interpretation process.

Structure Label Prediction Using Similarity-Based Retrieval and Weakly-Supervised Label Mapping

Recently, there has been significant interest in various supervised machine learning techniques that can help reduce the time and effort consumed by manual interpretation workflows. However, most successful supervised machine learning algorithms require huge amounts of annotated training data. Obtaining these labels for large seismic volumes is a very time-consuming and laborious task. We address this problem by presenting a weakly-supervised approach for predicting the labels of various seismic structures. By having an interpreter select a very small number of exemplar images for every class of subsurface structures, we use a novel similarity-based retrieval technique to extract thousands of images that contain similar subsurface structures from the seismic volume. By assuming that similar images belong to the same class, we obtain thousands of image-level labels for these images; we validate this assumption in our results section. We then introduce a novel weakly-supervised algorithm for mapping these rough image-level labels into more accurate pixel-level labels that localize the different subsurface structures within the image. This approach dramatically simplifies the process of obtaining labeled data for training supervised machine learning algorithms on seismic interpretation tasks. Using our method we generate thousands of automatically-labeled images from the Netherlands Offshore F3 block with reasonably accurate pixel-level labels. We believe this work will allow for more advances in machine learning-enabled seismic interpretation.

A directional coherence attribute for seismic interpretation

The coherence attribute is one of the most commonly used attributes in seismic interpretation. In this paper, we propose building on the recently introduced Generalized Tensor-based Coherence (GTC) attribute to make it directionally selective. This directional selectivity is achieved by selecting a directional Gaussian preprocessing kernel and applying a 3D rotational matrix to its covariance matrix. By weighing traces, or voxels, in the analysis cube by their relative proximity to the reference trace or voxel, this approach greatly enhances the clarity of the attribute. Furthermore, by making these weights directional, the proposed attribute gives interpreters greater freedom in exploring and understanding the seismic data. Various results from the Netherlands North Sea F3 block show that this approach greatly enhances the clarity of the coherence attribute and can highlight structures that are not visible using the traditional C3, or GTC coherence.

Weakly Supervised Seismic Structure Labeling via Orthogonal Non-Negative Matrix Factorization

Summary With the growing demand of high-resolution subsurface characterization from 3D seismic surveying, the size of 3D seismic datasets has been dramatically increasing, and correspondingly, the process of interpreting a seismic dataset is becoming more time consuming and labor intensive. In addition, supervised machine learning has proved to be very successful for many applications in computational seismic interpretation. However obtaining training labels for large volumes of seismic data is a very demanding task. Furthermore, while the amount of data is continuously growing, the ability of human experts to label data remains limited. In this work, we propose a weakly-supervised framework for labeling seismic structures using Non-Negative Matrix Factorization (NMF) with additional sparsity and orthogonality constraints. We show that weakly-supervised learning requires a much smaller number of labels. Furthermore, we show that “rough” image-level labels of specific seismic structures can be mapped into finer more localized locations within the seismic volume. Results obtained by labeling fault regions and salt dome boundaries from the Netherlands F3 block prove to be very promising.

Salt Dome Delineation Using Edge- and Texture-based Attributes

A lot of research has been done in the past to capture seismic features based on different edge- and texture-based attributes. In this paper, we apply a phase-based edge detection algorithm, namely phase congruency (PC), and a texture-based algorithm, namely gradient of texture (GoT), to localize a salt dome within SEAM dataset. Phase congruency (PC) can highlight small discontinuities in images with varying illumination and contrast using the congruency of phase in Fourier components. PC can not only detect the subtle variations in the image intensity but can also highlight the anomalous values to develop a deeper understanding of post-migrated seismic data. In contrast, GoT measures the perceptual dissimilarity of texture between two neighboring windows at each point in a seismic image along time or depth, and crossline directions, respectively. The GoT can effectively detect subtle variations characterized by changes in the texture of seismic data even in the absence of strong seismic reflections. We propose an interpreter-assisted workflow based on an attribute map obtained using either PC or GoT for computational seismic interpretation with an application to subsurface structures delineation within migrated seismic volumes. Experimental results show the effectiveness of PC and GoT for salt dome delineation.