2020
DOI: 10.2478/jaiscr-2020-0015
|View full text |Cite
|
Sign up to set email alerts
|

Detecting Visual Objects by Edge Crawling

Abstract: AbstractContent-based image retrieval methods develop rapidly with a growing scale of image repositories. They are usually based on comparing and indexing some image features. We developed a new algorithm for finding objects in images by traversing their edges. Moreover, we describe the objects by histograms of local features and angles. We use such a description to retrieve similar images fast. We performed extensive experiments on three established image datasets proving the … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2021
2021
2021
2021

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 10 publications
(3 citation statements)
references
References 42 publications
0
3
0
Order By: Relevance
“…The presented solutions can be used in many different areas, i.e., not only in the implementation of algorithms known from classical control theory, but also in the implementation of adaptive fuzzy control systems [37], real-time emulation of objects based on the HIL methodology [38], or for the implementation of real-time reference trajectory planning algorithms for machines and robots [39]. The developed solution can also be useful for many other applications that require a short response time, for example, to detect visual objects in images delivered in real-time from the camera of mobile or industrial robots [40].…”
Section: Discussionmentioning
confidence: 99%
“…The presented solutions can be used in many different areas, i.e., not only in the implementation of algorithms known from classical control theory, but also in the implementation of adaptive fuzzy control systems [37], real-time emulation of objects based on the HIL methodology [38], or for the implementation of real-time reference trajectory planning algorithms for machines and robots [39]. The developed solution can also be useful for many other applications that require a short response time, for example, to detect visual objects in images delivered in real-time from the camera of mobile or industrial robots [40].…”
Section: Discussionmentioning
confidence: 99%
“…Therefore, for our information storage we will use SQL Server, a database manager that has a wide adaptability for information management in mobile applications and service-oriented frameworks with a new architecture for storing visual data. The storage, navigation and efficient search of image collections make it an important tool in computing [18]. Finally, to be closer to the user we will use the Chat Bot, software that interacts with users using natural language as if you were normally conversing with a person.…”
Section: Mobile Application Structurementioning
confidence: 99%
“…However, we cannot correctly locate the size and location of the lesion due to unclear edges, which is not auspicious to feature extraction, target detection, and image segmentation. Furthermore, the doctor's diagnosis will also be affected [9,10]. For the industrial extraction, due to the randomness of the production processing, internal defects are often generated, such as cracks, inclusions, and pores [11,12].…”
Section: Introductionmentioning
confidence: 99%