Fake Logo Detection using Yolo Algorithm

Fake Logo Detection using Yolo Algorithm

Author Name : Bharath Chandra Rayapati, Gautham R, Harisha N, Ganashree K R

ABSTRACT

When logos are increasingly created, logo detection has gradually become a research hotspot across many domains and tasks. Recent advances in this area are dominated by deep learning-based solutions, where many datasets, learning strategies, network architectures, etc. have been employed. This paper reviews the advance in applying deep learning techniques to logo detection. Firstly, we discuss a comprehensive account of public datasets designed to facilitate performance evaluation of logo detection algorithms, which tend to be more diverse, more challenging, and more reflective of real life. A logo detector is a device that detects illegal produced or counterfeit brand products. The focus of this research is to detect the product logo and consider the likeness of the sample product logo. Building the detector’s product logo detector, we used the image detection process with a darknet   framework   and   YOLO   algorithm.    Through    this    process,    the    logo    of the copyright products is being set as sample product data for having a dataset. Furthermore, Open CV image classification by DNN module is used in Python language to read our dataset and work in Windows OS platform, to create a Graphical User Interface (GUI) simply including the creating a function to support the various application. The YOLO algorithm will be the main variable in this research. With this precision, we can detect the fake logo with 97% confidence scores and for the authentic logo with 99% confidence scores