Presentation 2013/9/5
Fish Detection by LBP Cascade Classifier with Optimized Processing Pipeline
HOANGANH DANG, PAO SRIPRASERTSUK, WATARU KAMEYAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we present a fish detection and classification mechanism using LBP feature. In this system, training sets are created for each fish species. Besides the strict sample alignment, a processing pipeline is applied in both training and detection process to achieve high performance of detection task. This pipeline further highlights unique features of each species such as edges and dominant colors. Machine learning is used to find the best pipeline model to be applied for each training set. A case study at a local aquarium shows high accuracy at a compelling detection rate.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # Vol.2013-AVM-82 NO.9
Date of Issue

Conference Information
Committee SIS
Conference Date 2013/9/5(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Smart Info-Media Systems (SIS)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Fish Detection by LBP Cascade Classifier with Optimized Processing Pipeline
Sub Title (in English)
Keyword(1)
1st Author's Name HOANGANH DANG
1st Author's Affiliation ()
2nd Author's Name PAO SRIPRASERTSUK
2nd Author's Affiliation
3rd Author's Name WATARU KAMEYAMA
3rd Author's Affiliation
Date 2013/9/5
Paper # Vol.2013-AVM-82 NO.9
Volume (vol) vol.113
Number (no) 202
Page pp.pp.-
#Pages 4
Date of Issue