Research indexJournal article
An ELM Based Barcode Localization Algorithm
Wang, Li, Yu
Applied Mechanics and Materials30 Aug 2013Open access
NobleIDark:/48914/w1/20260526/899B4078DOI10.4028/www.scientific.net/amm.380-384.1185
An ELM Based Barcode Localization Algorithm
Wang, Li, Yu · Applied Mechanics and Materials · 2013
NobleIDark:/48914/w1/20260526/899B4078DOI10.4028/www.scientific.net/amm.380-384.1185
Free to read at the publisher
You can read the abstract here, or the full text at the publisher.
Abstract
Many applications have provided functions of automatic searching and reading barcodes in complex scenes with a camera. However state of the art barcode detection systems are limited to their serious requirement, such as shooting angle, light intensity and revolution. This paper proposes an effective solution for automatic barcode localization by exploiting ELM (extreme learning machine) and multichannel Gabor filtering techniques. We first employ Gabor filter to extract texture feature of the barcode, and then the barcode regions and the background region in texture image are use to train the ELM classifier. Finally, we apply our method to the barcode image database, which consists of several different barcode symbologies. Experiment shows our method is superior to the General morphology method and has desirable properties in accuracy, rotation invariance and robustness to noise.