Enhanced Reinforcement Learning Model for Extraction of Objects in Complex Imaging
Object segmentation is the process of extracting and partitioning an image into digital information. In the field of computer vision and image processing, we perform several activities in the segmentation stage, such as image segmentation and dynamic context video segmentation. The semantic pixel wi...
| Main Authors: | Usmani, U.A., Roy, A., Watada, J., Jaafar, J., Aziz, I.A. |
|---|---|
| Format: | Article |
| Institution: | Universiti Teknologi Petronas |
| Record Id / ISBN-0: | utp-eprints.28855 / |
| Published: |
Springer Science and Business Media Deutschland GmbH
2022
|
| Online Access: |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85112578184&doi=10.1007%2f978-3-030-80119-9_63&partnerID=40&md5=32fcaf535c560dc81d27f61346a77257 http://eprints.utp.edu.my/28855/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
utp-eprints.28855 |
|---|---|
| recordtype |
eprints |
| spelling |
utp-eprints.288552022-03-17T02:21:02Z Enhanced Reinforcement Learning Model for Extraction of Objects in Complex Imaging Usmani, U.A. Roy, A. Watada, J. Jaafar, J. Aziz, I.A. Object segmentation is the process of extracting and partitioning an image into digital information. In the field of computer vision and image processing, we perform several activities in the segmentation stage, such as image segmentation and dynamic context video segmentation. The semantic pixel wise image segmentation method is the investigation of several objects that are extracted for image processing and interpretation. In general, segmentation relates to the partitioning of an image into full or identical regions. The effects of image segmentation have an effect on the image processing process. In general, it includes the description and specification of objects; higher order tasks follow, such as entity classification and attribute estimation. The visualization and classification of the area of interest in any picture is therefore an important function in order to segment the image. We examine a variety of image segmentation algorithms and give our reinforcement learning algorithm that uses Deep Convolutional Neural Networks for the detection of irregular objects, which has been tested on four datasets. We then relate our approaches to the previous literature to illustrate that the segmentation results are superior to the findings in the previous literature. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG. Springer Science and Business Media Deutschland GmbH 2022 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85112578184&doi=10.1007%2f978-3-030-80119-9_63&partnerID=40&md5=32fcaf535c560dc81d27f61346a77257 Usmani, U.A. and Roy, A. and Watada, J. and Jaafar, J. and Aziz, I.A. (2022) Enhanced Reinforcement Learning Model for Extraction of Objects in Complex Imaging. Lecture Notes in Networks and Systems, 283 . pp. 946-964. http://eprints.utp.edu.my/28855/ |
| institution |
Universiti Teknologi Petronas |
| collection |
UTP Institutional Repository |
| description |
Object segmentation is the process of extracting and partitioning an image into digital information. In the field of computer vision and image processing, we perform several activities in the segmentation stage, such as image segmentation and dynamic context video segmentation. The semantic pixel wise image segmentation method is the investigation of several objects that are extracted for image processing and interpretation. In general, segmentation relates to the partitioning of an image into full or identical regions. The effects of image segmentation have an effect on the image processing process. In general, it includes the description and specification of objects; higher order tasks follow, such as entity classification and attribute estimation. The visualization and classification of the area of interest in any picture is therefore an important function in order to segment the image. We examine a variety of image segmentation algorithms and give our reinforcement learning algorithm that uses Deep Convolutional Neural Networks for the detection of irregular objects, which has been tested on four datasets. We then relate our approaches to the previous literature to illustrate that the segmentation results are superior to the findings in the previous literature. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG. |
| format |
Article |
| author |
Usmani, U.A. Roy, A. Watada, J. Jaafar, J. Aziz, I.A. |
| spellingShingle |
Usmani, U.A. Roy, A. Watada, J. Jaafar, J. Aziz, I.A. Enhanced Reinforcement Learning Model for Extraction of Objects in Complex Imaging |
| author_sort |
Usmani, U.A. |
| title |
Enhanced Reinforcement Learning Model for Extraction of Objects in Complex Imaging |
| title_short |
Enhanced Reinforcement Learning Model for Extraction of Objects in Complex Imaging |
| title_full |
Enhanced Reinforcement Learning Model for Extraction of Objects in Complex Imaging |
| title_fullStr |
Enhanced Reinforcement Learning Model for Extraction of Objects in Complex Imaging |
| title_full_unstemmed |
Enhanced Reinforcement Learning Model for Extraction of Objects in Complex Imaging |
| title_sort |
enhanced reinforcement learning model for extraction of objects in complex imaging |
| publisher |
Springer Science and Business Media Deutschland GmbH |
| publishDate |
2022 |
| url |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85112578184&doi=10.1007%2f978-3-030-80119-9_63&partnerID=40&md5=32fcaf535c560dc81d27f61346a77257 http://eprints.utp.edu.my/28855/ |
| _version_ |
1741197161604841472 |
| score |
11.62408 |