Tech Stack: Python 3.8.5, TensorFlow, PIL (Python Imaging Library), Streamlit, NumPy Features and Techniques: Transfer Learning, Image Preprocessing, Decision Tree, Piece Wise Painting Algorithm (PPA)
Every year, brands lose a significant portion of their sales to unauthorized knock off brands and counterfeits. Moreover, since such counterfeit products are usually of an inferior quality, they also end up damaging the credibility of the brand. Many a times consumers also get cheated out of their hard-earned money as they end up shelling out an exorbitant amount of money for a mere counterfeit . This Logo Detection app aims to help consumers distinguish forgeries from the original product. Using this system, a consumer can verify whether a product is in fact an original. This application can also be helpful for brands struggling to fight against forged products. The detection method is based on the piece-wise painting algorithm (PPA) and some probability features along with a decision tree.
EXISTING WORK: Signature and Brand logo act as a significant content for numerous documents specially for scanned documents. Brand recognition in pictures and videos is the key drawback in an exceedingly very large choice of applications, like infringement detection, discourse advertises placement, vehicle brand for intelligent traffic-control systems, machine-controlled computation of brand-related statistics on social media, etc. Historically, Brand logo recognition has been self-addressed with key point-based detectors and descriptors. This technique for brand recognition uses deep learning. Our recognition pipeline consists of a brand region proposal followed by a framework of Python known as Py-Torch specifically trained for brand classification, whether or not they are exactly localized.
PROPOSED WORK: Counterfeit products usually have an inferior built quality and along with stealing sales, they also damaging a brand’s reputation in the long run. - Along with harming a brand’s sales and reputation, unaware consumers also get cheated out of their money. - This Logo Detection project aims to help users identify forgeries by analyzing the logo on the product. - Along with helping users identify the logo, this app also helps brands combat logo piracy. - This project is developed using the Django framework with Python as programming language.
Image classification approach based on object detection & piece wise painting algorithm (PPA) feature along with decision tree and
