Automatic Inspection of Food Packet Labels using Image Processing

Conference: McGraw-Hill International Conference on Signal, Image Processing Communication and Automation
Author(s): Divyashree D R, K. V. Suresh, Sachin K J Year: 2017
Grenze ID: 02.MH-ICSIPCA.2017.1.20 Page: 130-135

Abstract

Inspecting the food packets for proper printed labels is very essential in food manufacturing industries.\nInformation about the manufacturing date printed on the food packets is a valuable source of information about the life of the\npackaged food product for consumers. Manual inspection systems are inaccurate and time consuming. This paper proposes an\nautomatic printed label inspection system for food packets. The proposed algorithm can detect the defects like missing line,\nmissing character, improper printing and the patches present in the labels printed on food packets. The image of the food\npacket acquired by the camera undergoes pre-processing such as gray scale conversion, adaptive thresholding for\nbinarization, erosion and dilation. Optical character recognition is used for the recognition of text in the printed labels.\nSeveral experiments were conducted on real images to verify the effectiveness of the proposed algorithm.

<< BACK

MH-ICSIPCA - 2017