We present a method based on deep learning for detecting and localizing abnormal/extreme events in sea surface temperature (SST) of the Red Sea images using training samples of normal events only. The method operates in two stages; the first one involves features extraction from each patch of the SST input image using the first two convolutional layers extracted from a pretrained convolutional neural network. In the second stage, two methods are used for training the model from the normal training data. The first method uses one-class support vector machine (1-SVM) classifier that allows a fast and robust abnormal detection in the presence of outliers in the training dataset. In the second method, a Gaussian model is defined on the Mahalanobis distances between all normal training data. Experimental tests are conducted on satellite-derived SST data of the Red Sea spanning for a period of 31 years (1985–2015). Our results suggest that the Gaussian model of Mahalanobis distances outperformed 1-SVM by providing better performance in terms of sensitivity and specificity.
This article deals with machine vision techniques applied to timber grading singularities. Timber used for architectural purposes must satisfy certain mechanical requirements, and, therefore, must be mechanically graded to ensure the manufacturer that the product complies with the requirements. However, the timber material has many singularities, such as knots, cracks, and presence of juvenile wood, which influence its mechanical behavior. Thus, identifying those singularities is of great importance. We address the problem of timber defects segmentation and classification and propose a method to detect timber defects such as cracks and knots using a bag-of-words approach. Extensive experimental results show that the proposed methods are efficient and can improve grading machines performances. We also propose an automated method for the detection of transverse knots, which allows the computation of knot depth ratio (KDR) images. Finally, we propose a method for the detection of juvenile wood regions based on tree rings detection and the estimation of the tree’s pith. The experimental results show that the proposed methods achieve excellent results for knots detection, with a recall of 0.94 and 0.95 on two datasets, as well as for KDR image computation and juvenile timber detection.
Wood singularities detection is a primary step in wood grading enhancement. Our approach is purely machine vision based. The main objective is to compute physical properties like density, modulus of elasticity (MOE) and modulus of rupture (MOR) given wood surface images. Knots are one of the main singularities which directly affect the wood strength. Hence, our target is to detect knots and classify them into transverse and non-transverse ones. Then the Knots Depth Ratio (KDR) is computed based on all found transverse knots. Afterwards, KDR is used for the wood mechanical model improvement. Our technique is based on colour image analysis where the knots are detected by means of contrast intensity transformation and morphological operations. Then KDR computations are based on transverse knots and clear wood densities. Finally, MOE and MOR are computed using KDR images. The accuracy of number of knots found, their locations, MOE and MOR has been validated using a dataset of 252 images. In our dataset, these values were manually calculated. To the best of our knowledge our approach is the first purely machine vision based method to compute KDR, MOE and MOR.