Fast visual recognition of Scots pine boards using template matching

被引：4

作者：

Johansson, Erik ^{[1
,2
]}

Pahlberg, Tobias ^{[2
]}

Hagman, Olle ^{[2
]}

机构：

[1] SP Tech Res Inst Sweden, S-93177 Skelleftea, Sweden

[2] Lulea Univ Technol, S-93187 Skelleftea, Sweden

来源：

COMPUTERS AND ELECTRONICS IN AGRICULTURE | 2015年 / 118卷

关键词：

Recognition; Sawn timber; Scots pine; Template matching; Traceability; Wood; TRACEABILITY;

D O I：

10.1016/j.compag.2015.08.026

中图分类号：

S [农业科学];

学科分类号：

09 ;

摘要：

This paper describes how the image processing technique known as template matching performs when used to recognize boards of Scots pine (Pinus sylvestris L.). Recognition of boards enables tracking of individual boards through an industrial process, which is vital for process optimization. A dataset of 886 Scots pine board images were used as a database to match against. The proposed board recognition method was evaluated by rescanning 44 of the boards and matching these to the larger dataset. Three different template matching algorithms have been investigated while reducing the pixel densities of the board images (downsampling the images). Furthermore, the effect of variations in board length has been tested and the computational speed of the recognition with respect to the database size has been measured. Tests were conducted using the open source software package OpenCV due to its highly optimized code which is essential for applications with high production speed. The conducted tests resulted in recognition rates above 99% for board lengths down to 1 m and pixel densities down to 0.06 pixels/mm. This study concluded that template matching is a good choice for recognition of wooden board surfaces. (C) 2015 Elsevier B.V. All rights reserved.

引用

页码：85 / 91

页数：7

共 20 条

[11]

Nystrom J., 2008, P IUFRO WORK PART JO

[12]

Oja J., 2008, P IUFRO WORK PART JO

[13] Recognition of boards using wood fingerprints based on a fusion of feature detection methods [J].

Pahlberg, Tobias ;

Hagman, Olle ;

Thurley, Matthew .

COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2015, 111 :164-173

[14] Wood fingerprint recognition using knot neighborhood K-plet descriptors [J].

Pahlberg, Tobias ;

Johansson, Erik ;

Hagman, Olle ;

Thurley, Matthew .

WOOD SCIENCE AND TECHNOLOGY, 2015, 49 (01) :7-20

[15]

Polder A, 2010, PROCEEDINGS OF THE 7TH INTERNATIONAL CONFERENCE OF DAAAM BALTIC INDUSTRIAL ENGINEERING, VOLS 1 AND 2, P554

[16]

Polder A, 2012, J VIBROENG, V14, P477

[17]

Tamre M., 2008, TECHNICAL REPORT

[18]

Uusijarvi R., 2000, THESIS

[19] Rapid object detection using a boosted cascade of simple features [J].

Viola, P ;

Jones, M .

2001 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2001, :511-518

[20] Fast Template Matching Based on Normalized Cross Correlation With Adaptive Multilevel Winner Update [J].

Wei, Shou-Der ;

Lai, Shang-Hong .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2008, 17 (11) :2227-2235

← 1 2 →