Brand Detection System using Deep Learning
Saumya Singh1, Saumya Dubey2, Paridhi Singhal3, Rajiv Kumar4
1Saumya Singh*, Department of Computer Science Engineering, G L Bajaj Institute of Technology and Management, Greater Noida, (U.P), India.
2Saumya Dubey, Department of Computer Science Engineering, G L Bajaj Institute of Technology and Management, Greater Noida, (U.P), India.
3Paridhi Singhal, Department of Computer Science Engineering, G L Bajaj Institute of Technology and Management, Greater Noida, (U.P), India.
4Dr. Rajiv Kumar, Professor, Department of Computer Science Engineering, G L Bajaj Institute of Technology and Management, Greater Noida, (U.P), India.
Manuscript received on June 18, 2020. | Revised Manuscript received on June 28, 2020. | Manuscript published on July 10, 2020. | PP: 497-500 | Volume-9 Issue-9, July 2020 | Retrieval Number: 100.1/ijitee.I7630079920 | DOI: 10.35940/ijitee.I7630.079920
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper a method of recognizing logos of the brand of cosmetic products using deep learning. There are several of hoax product which easily copies the famous brand’s logo and deteriorates the company’s image. The machine learning has proved to be useful in various of the fields like medical, object detection, vehicle logo recognitions. But till now very few of the works have been performed in cosmetic field. This field is covered using the model sequential convolutional neural network using Tensor flow and Keras. For the visual representation of the result Tensorboard is used. Work have been started with two of the brands-Lakme and L’Oreal. Depending upon the success of this technique, further brands for logo may be added for recognition. The accuracy of approximately 80% was obtained using this technique.
Keywords: Brand detection, Deep learning, Tensorflow, CNN, overfitting.
Scope of the Article: Deep learning