An Applicational Approach Toward comparing Deep Learning Based Methods and Classical Machine Learning Methods in Traffic Industry

چکیده مقاله

Deep learning based methods are growing among researchers in different machine vision fields In traffic industry, many applications are switching from traditional andclassical machine learning methods to deep learning based methods In this paper, we have experimented an accurate comparison between deep learning based methodsand classical ones on Automatic Number Plate Recognition ANPR application This comparison is based on both accuracy and processing time For this comparison, a database of ten thousands images from different ANPR cameras installed in Tehran is used We have implemented these methods on many different hardware platforms Although in many parts deep learning based methods reach better results, but in this paper it is shown that they still lack some optimization to replace traditional methods completely

کلیدواژه‌ها

نویسندگان

Mahsa Shams

Researcher at Mahya ITS Company

Parsa Panahi

Researcher at Mahya ITS Company

Iman Gholampour

Electronic Research Institute, Sharif University

Shams, Mahsa and Panahi, Parsa and Gholampour, Iman,1396,An Applicational Approach Toward comparing Deep Learning Based Methods and Classical Machine Learning Methods in Traffic Industry,The 17th International Conference on Traffic and Transportation Engineering,Tehran

ارائه‌شده در

مجموعه مقالات هفدهمین کنفرانس بین المللی مهندسی حمل و نقل و ترافیک29 بهمن 1396 · تهران