On the Identification of Grocery Products.

Date of Submission

December 2016

Date of Award

Winter 12-12-2017

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Master's Dissertation

Degree Name

Master of Technology

Subject Name

Computer Science

Department

Electronics and Communication Sciences Unit (ECSU-Kolkata)

Supervisor

Mukherjee, Dipti Prasad (ECSU-Kolkata; ISI)

Abstract (Summary of the Work)

In this thesis, a methodology is proposed to identify the products present in a rack in retail stores. Only a single image of each category of products is given to us. A series of preprocessing algorithms are applied on the input images in order to assist the matching algorithms used. Our methodology involves a two layered approach to solve the problem. The first layer is used to shortlist the products in order to reduce the search space for the second layer. The products shortlisted in the first layer are used as nodes in a graph. A scale-space based approach involving bag-of-words model is used to provide the feedback. The results obtained are shown to be comparable to the existing state-of-the-art algorithm in this field.

Comments

ProQuest Collection ID: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:28843131

Control Number

ISI-DISS-2016-372

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

DOI

http://dspace.isical.ac.in:8080/jspui/handle/10263/6846

This document is currently not available here.

Share

COinS