An SVM-Based Scheme for Automatic Identification of Architectural Line Features and Cracks

This research investigates fundamental problems in object recognition in earthen heritage and addresses the possibility of an automatic crack detection method for rammed earth images. We propose and validate a straightforward support vector machine (SVM)-based bidirectional morphological approach to automatically generate crack and texture line maps through transforming a surface image into an intermediate representation. Rather than relying on the application of the eight connectivity rule to a combination of horizontal and vertical gradient to extract edges, we instruct an edge classifier in the form of a support vector machine from features computed on each direction separately. The model couples a bidirectional local gradient and geometrical characteristics. It constitutes of four elements: (1) bidirectional edge maps; (2) bidirectional equivalent connected component maps; (3) SVM-based classifier and (4) crack and architectural line feature map generation. Relevant details are discussed in each part. Finally, the efficiency of the proposed algorithm is verified in a set of simulations that is satisfactorily conforming to labeled data provided manually for surface images of earthen heritage.

Inside out Capping Clusters: Matryoshka Series

Matryoshka clusters have been analyzed and categorized using skeletal numbers for the first time. They have been found to portray a unique way of capping by having the nuclear elements occupying the outer layer and what were supposed to be the capping elements on the outside taking the place of the nucleus. Hence they belong to a new type of cluster series. The different types of capping clusters have been identified. Isomeric graphical structures of the clusters can be constructed in accordance with the connectivity rule of the series. It appears that the elements with large skeletal numbers have a tendency of going inside and forming an icosahedral shape. The 4N series method is a useful hypothetical model for analyzing and categorizing clusters of the main group and transition metals.