A Study of Household Object Recognition Using SIFT-Based Bag-of-Words Dictionary and SVMs

被引：2

作者：

Sampath, Aadarsh ^{[1
]}

Sivaramakrishnan, Aravind ^{[1
]}

Narayan, Keshav ^{[1
]}

Aarthi, R. ^{[1
]}

机构：

[1] Amrita Vishwa Vidyapeetham, Dept CSE, Coimbatore, Tamil Nadu, India

来源：

PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON SOFT COMPUTING SYSTEMS, ICSCS 2015, VOL 1 | 2016年 / 397卷

关键词：

SIFT; Bag of visual words; SVM; Real time; Object recognition;

D O I：

10.1007/978-81-322-2671-0_55

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In the era of computational intelligence, computer vision-based techniques for robotic cognition have gained prominence. One of the important problems in computer vision is the recognition of objects in real-time environments. In this paper, we construct a SIFT-based SVM classifier and analyze its performance for real-time object recognition. Ten household objects from the CALTECH-101 dataset are chosen, and the optimal train-test ratio is identified by keeping other SVM parameters constant. The system achieves an overall accuracy of 85 % by maintaining the ratio as 3:2. The difficulties faced in adapting such a classifier for real-time recognition are discussed.

引用

页码：573 / 580

页数：8

共 12 条

[1] 50 Years of object recognition: Directions forward [J].

Andreopoulos, Alexander ;

Tsotsos, John K. .

COMPUTER VISION AND IMAGE UNDERSTANDING, 2013, 117 (08) :827-891

[2]

[Anonymous], 2010, P 18 ACM INT C MULT, DOI [10.1145/1873951.1874249, 10.1145/1873951.1874249.2]

[3] Automatic panoramic image stitching using invariant features [J].

Brown, Matthew ;

Lowe, David G. .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2007, 74 (01) :59-73

[4]

Duan KB, 2005, LECT NOTES COMPUT SC, V3541, P278

[5]

Elkan C., 2003, MACHINE LEARNING-INTERNATIONAL WORKSHOP THEN CONFERENCE, P147, DOI DOI 10.1016/0026-2714(92)90278-S

[6]

Issolah M, 2013, WORKING NOTES CLEF 2

[7]

Joachims T., 1998, MACHINE LEARNING ECM

[8]

Ke Y, 2004, PROC CVPR IEEE, P506

[9] Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories [J].

Li Fei-Fei ;

Fergus, Rob ;

Perona, Pietro .

COMPUTER VISION AND IMAGE UNDERSTANDING, 2007, 106 (01) :59-70

[10] Distinctive image features from scale-invariant keypoints [J].

Lowe, DG .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 60 (02) :91-110

← 1 2 →