TY - JOUR
AU - 
AB - sensors Review Visual-Based Defect Detection and Classification Approaches for Industrial Applications—A SURVEY Tamás Czimmermann * , Gastone Ciuti, Mario Milazzo , Marcello Chiurazzi, Stefano Roccella, Calogero Maria Oddo * and Paolo Dario The BioRobotics Institute of Scuola Superiore Sant’Anna and Department of Excellence in Robotics and AI of Scuola Superiore Sant’Anna, 56025, Pontedera (PISA), Italy; gastone.ciuti@santannapisa.it (G.C.); m.milazzo@santannapisa.it (M.M.); m.chiurazzi@santannapisa.it (M.C.); stefano.roccella@santannapisa.it (S.R.); paolo.dario@santannapisa.it (P.D.) * Correspondence: t.czimmermann@santannapisa.it (T.C.); calogero.oddo@santannapisa.it (C.M.O.) Received: 9 February 2020; Accepted: 2 March 2020; Published: 6 March 2020 Abstract: This paper reviews automated visual-based defect detection approaches applicable to various materials, such as metals, ceramics and textiles. In the first part of the paper, we present a general taxonomy of the different defects that fall in two classes: visible (e.g., scratches, shape error, etc.) and palpable (e.g., crack, bump, etc.) defects. Then, we describe artificial visual processing techniques that are aimed at understanding of the captured scenery in a mathematical/logical way. We continue with a survey of textural defect detection based on statistical, structural and other approaches. Finally, we report the state of the art for approaching the detection and classification of defects through supervised and non-supervised classifiers and deep learning. Keywords: defect detection; 
TI - Visual-Based Defect Detection and Classification Approaches for Industrial Applications—A SURVEY
JF - Sensors
DO - 10.3390/s20051459
DA - 2020-03-06
UR - https://www.deepdyve.com/lp/unpaywall/visual-based-defect-detection-and-classification-approaches-for-P8xbpCX8Gb
DP - DeepDyve
ER -