Hand-Crafted and Learned Feature Aggregation for Visual Marble Tiles Screening.

An important factor in the successful marketing of natural ornamental rocks is providing sets of tiles with matching textures. The market price of the tiles is based on the aesthetics of the different quality classes and can change according to the varying needs of the market. The classification of the marble tiles is mainly performed manually by experienced workers. This can lead to misclassifications due to the subjectiveness of such a procedure, causing subsequent problems with the marketing of the product. In this paper, 24 hand-crafted texture descriptors and 20 Convolution Neural Networks were evaluated towards creating aggregated descriptors resulting from the combination of one hand-crafted and one Convolutional Neural Network at a time. A marble tile dataset designed for this study was used for the evaluation process, which was also released publicly to further enable the research for similar studies (both on texture and dolomitic ornamental marble tile analysis). This was done to automate the classification of the marble tiles. The best performing feature descriptors were aggregated together in order to achieve an objective classification. The resulting model was embodied into an automatic screening machine designed and constructed as a part of this study. The experiments showed that the aggregation of the VGG16 and SILTP provided the best results, with an AUC score of 0.9944.

Feature Extraction for Finger-Vein-Based Identity Recognition.

This paper aims to provide a brief review of the feature extraction methods applied for finger vein recognition. The presented study is designed in a systematic way in order to bring light to the scientific interest for biometric systems based on finger vein biometric features. The analysis spans over a period of 13 years (from 2008 to 2020). The examined feature extraction algorithms are clustered into five categories and are presented in a qualitative manner by focusing mainly on the techniques applied to represent the features of the finger veins that uniquely prove a human's identity. In addition, the case of non-handcrafted features learned in a deep learning framework is also examined. The conducted literature analysis revealed the increased interest in finger vein biometric systems as well as the high diversity of different feature extraction methods proposed over the past several years. However, last year this interest shifted to the application of Convolutional Neural Networks following the general trend of applying deep learning models in a range of disciplines. Finally, yet importantly, this work highlights the limitations of the existing feature extraction methods and describes the research actions needed to face the identified challenges.