Paper Info
Title
Book spine segmentation for various book orientations
Abstract
This work proposes a novel approach to separate books which are placed disorderly on a bookshelf. This work applies grayscale morphological reconstruction and Lo gradient minimization to erase texts on books while preserving book boundaries. Afterwards, Hough transform and the proposed SVM-based recovery scheme are applied to find book boundaries accurately. The proposed SVM-based recovery scheme is able to recover the book boundaries missed by Hough transform without incurring noticeable false alarm detections. Experiments demonstrate that the proposed method is able to segment books which are placed in various orientations.
Year
DOI
Venue
2015
10.1109/GCCE.2015.7398501
2015 IEEE 4th Global Conference on Consumer Electronics (GCCE)
Keywords
Field
DocType
book spine segmentation,morphological reconstruction,L0 gradient minimization,Support Vector Machine
Computer vision,False alarm,Scale-space segmentation,Pattern recognition,Computer science,Segmentation,Support vector machine,Hough transform,Minification,Artificial intelligence,Grayscale
Conference
Citations 
PageRank 
References 
0
0.34
2
Authors
3
Name
Order
Citations
PageRank
Chih-Chang Yu1328.93
Rui-Jun Zhang200.34
Hsu-Yung Cheng324323.56