ISME 2016 - Information Science and Management Engineering IV 2016
DOI: 10.5220/0006449503050311
|View full text |Cite
|
Sign up to set email alerts
|

The Improved Harris Operator based on Steerable Filter

Abstract: The conventional Harris corner detection operator is improved to enhance the missing rate and the detection capability of false corners in this paper. With the materials recognition on automated logistics and packaging line as an example, the acquired images were firstly pretreated to achieve the grayscale images. The rotations of four different angles were performed by the steerable filter based on the grayscale and the corner points were detected. Finally the authenticity corner points were determined throug… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2020
2020
2020
2020

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(2 citation statements)
references
References 2 publications
0
2
0
Order By: Relevance
“…In the test with ORL dataset, any changes in detected keypoints were dependent on the processed image while in the test with Head Pose Image Database, there was an increase from when detecting the original grayscale image with images that had been processed with DCT & Wiener Filtering. According to the research by [26], it is known that the Harris-Stephens do not have a definite way to describe the threshold value, which is necessary to define a descriptor [27].…”
Section: ) Minimum Eigenvaluementioning
confidence: 99%
See 1 more Smart Citation
“…In the test with ORL dataset, any changes in detected keypoints were dependent on the processed image while in the test with Head Pose Image Database, there was an increase from when detecting the original grayscale image with images that had been processed with DCT & Wiener Filtering. According to the research by [26], it is known that the Harris-Stephens do not have a definite way to describe the threshold value, which is necessary to define a descriptor [27].…”
Section: ) Minimum Eigenvaluementioning
confidence: 99%
“…Through visual observation on ORL database, the images had more noise rather than in Head Pose Image Database. According to the research conducted by [26], due to the ability of FAST to detect actual corner-points, the greater the noise, the more likely it is to detect the facial key points. However, because F-Score calculation is based on total of all keypoints detected, FAST feature detector fails to deliver the best results.…”
Section: ) Minimum Eigenvaluementioning
confidence: 99%