From announce at list.ipol.im Tue May 22 23:52:27 2018 From: announce at list.ipol.im (announcements about the IPOL journal) Date: Tue, 22 May 2018 23:52:27 +0200 Subject: [IPOL announce] new article: A MATLAB SMO Implementation to Train a SVM Classifier: Application to Multi-Style License Plate Numbers Recognition Message-ID: A new article is available in IPOL: http://www.ipol.im/pub/art/2018/173/ Pablo Negri, A MATLAB SMO Implementation to Train a SVM Classifier: Application to Multi-Style License Plate Numbers Recognition, Image Processing On Line, 8 (2018), pp. 51?70. https://doi.org/10.5201/ipol.2018.173 Abstract This paper implements the Support Vector Machine (SVM) training procedure proposed by John Platt denominated Sequential Minimimal Optimization (SMO). The application of this system involves a multi-style license plate characters recognition identifying numbers from '0' to '9'. In order to be robust against license plates with different character/background colors, the characters (numbers) visual information is encoded using Histograms of Oriented Gradients (HOG). A reliability measure to validate the system outputs is also proposed. Several tests are performed to evaluate the sensitivity of the algorithm to different parameters and kernel functions.