Retail Inventory Management using Deep Learning Techniques

Iyer, Karthik (2023) Retail Inventory Management using Deep Learning Techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (10MB) | Preview
Preview	PDF (Configuration manual) Download (3MB) | Preview

Abstract

The success of the Retail Industry is dependent on customer satisfaction and sales generated. It mainly depends on effective inventory management. If the store is fully stocked up with inventories it will lead to customer attraction and thereby result in the high volume of sales. Priorly the inventory management was done manually which was very time-consuming and also error-prone. Last two decades researchers have investigated the use of object detection using Faster R-CNN and YOLO for examining and keeping a count of stocks present on the shelf. But these researchers either examined the products present on the shelf or detected the empty spaces present on the shelf and didn’t provide the count of empty spaces present in each shelf. The purpose of this research is to train the retail shelf data using YOLOv7 algorithm for detection of Products as well as the empty spaces together.To begin, the YOLO algorithm will be trained not just to detect but also count and display the count of Objects as well as empty spaces. Finally, the tesseract OCR will be employed for extracting the count of empty spaces and convert it to speech using gTTS(Text to speech algorithm).. This will allow the system to alert shop management of vacant areas, allowing them to refill inventory more effectively. Using these novel approaches has the potential to change inventory management in the retail business while also improving consumer satisfaction by decreasing out-of-stock situations.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Tomer, Vikas UNSPECIFIED
Uncontrolled Keywords:	Object Detection and counting; YOLOv7; Tesseract OCR; gTTS(Text to speech conversion); Text extraction
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HF Commerce > Marketing > Consumer Behaviour Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Retail Industry
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	22 Nov 2024 11:57
Last Modified:	22 Nov 2024 11:57
URI:	https://norma.ncirl.ie/id/eprint/7191

Actions (login required)

View Item