An improved multi-object instance segmentation based on deep learning

Given the recent breakthroughs in recent years, Deep learning (DL) networks have attracted growing interest and attention by researchers and scholars alike due to its importance in detecting and instance segmentation of objects in an image. An entity's example instance segmentation is a critic...

Full description

Saved in:
Bibliographic Details
Main Authors: Nawaf Alshdaifat, Mohd Azam Osman, Abdullah Zawawi Talib
Format: Article
Language:English
Published: Elsevier 2022-03-01
Series:Kuwait Journal of Science
Online Access:https://journalskuwait.org/kjs/index.php/KJS/article/view/10879
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850138610493292544
author Nawaf Alshdaifat
Mohd Azam Osman
Abdullah Zawawi Talib
author_facet Nawaf Alshdaifat
Mohd Azam Osman
Abdullah Zawawi Talib
author_sort Nawaf Alshdaifat
collection DOAJ
description Given the recent breakthroughs in recent years, Deep learning (DL) networks have attracted growing interest and attention by researchers and scholars alike due to its importance in detecting and instance segmentation of objects in an image. An entity's example instance segmentation is a critical problem that requires further analysis. However, given the difficulties in adopting object detection and the instance segmentation approach, this study aims to develop an approach to overcome these issues by proposing a new approach based on the recent DL approach in addition to developing an approach for object instance segmentation. The approach presented in this study consisted of three stages in order to improve the recognition approach. First, adopting a DL approach improves the object's detection in the enhanced ResNet (residual neural network) and connects it with the convolution layer for each ResNet block. Second, improving the localization of multiple objects dependent on the Region Proposal Network (RPN) approach, and third, utilizing a complex instance segmentation approach. This study's findings revealed that the suggested approach using a typical benchmark-image dataset, called the COCO dataset, the experiments are carried out and validated using generic evaluation parameters. The proposed approach's performance is verified and measured against the recent image segmentation approach using object instances. The findings also revealed that in terms of average precision over IoU (AP) threshold measurements using different thresholds, the proposed approach obtained improved results compared to other well-known segmentation approaches.
format Article
id doaj-art-da6e396ccbfb42ab807f81ee91af6d59
institution OA Journals
issn 2307-4108
2307-4116
language English
publishDate 2022-03-01
publisher Elsevier
record_format Article
series Kuwait Journal of Science
spelling doaj-art-da6e396ccbfb42ab807f81ee91af6d592025-08-20T02:30:32ZengElsevierKuwait Journal of Science2307-41082307-41162022-03-0149210.48129/kjs.10879An improved multi-object instance segmentation based on deep learningNawaf Alshdaifat0Mohd Azam Osman1Abdullah Zawawi Talib2Universiti Sains MalaysiaSchool of Computer Sciences Universiti Sains Malaysia,11800, Pulau Pinang, MalaysiaSchool of Computer Sciences Universiti Sains Malaysia,11800, Pulau Pinang, Malaysia Given the recent breakthroughs in recent years, Deep learning (DL) networks have attracted growing interest and attention by researchers and scholars alike due to its importance in detecting and instance segmentation of objects in an image. An entity's example instance segmentation is a critical problem that requires further analysis. However, given the difficulties in adopting object detection and the instance segmentation approach, this study aims to develop an approach to overcome these issues by proposing a new approach based on the recent DL approach in addition to developing an approach for object instance segmentation. The approach presented in this study consisted of three stages in order to improve the recognition approach. First, adopting a DL approach improves the object's detection in the enhanced ResNet (residual neural network) and connects it with the convolution layer for each ResNet block. Second, improving the localization of multiple objects dependent on the Region Proposal Network (RPN) approach, and third, utilizing a complex instance segmentation approach. This study's findings revealed that the suggested approach using a typical benchmark-image dataset, called the COCO dataset, the experiments are carried out and validated using generic evaluation parameters. The proposed approach's performance is verified and measured against the recent image segmentation approach using object instances. The findings also revealed that in terms of average precision over IoU (AP) threshold measurements using different thresholds, the proposed approach obtained improved results compared to other well-known segmentation approaches. https://journalskuwait.org/kjs/index.php/KJS/article/view/10879
spellingShingle Nawaf Alshdaifat
Mohd Azam Osman
Abdullah Zawawi Talib
An improved multi-object instance segmentation based on deep learning
Kuwait Journal of Science
title An improved multi-object instance segmentation based on deep learning
title_full An improved multi-object instance segmentation based on deep learning
title_fullStr An improved multi-object instance segmentation based on deep learning
title_full_unstemmed An improved multi-object instance segmentation based on deep learning
title_short An improved multi-object instance segmentation based on deep learning
title_sort improved multi object instance segmentation based on deep learning
url https://journalskuwait.org/kjs/index.php/KJS/article/view/10879
work_keys_str_mv AT nawafalshdaifat animprovedmultiobjectinstancesegmentationbasedondeeplearning
AT mohdazamosman animprovedmultiobjectinstancesegmentationbasedondeeplearning
AT abdullahzawawitalib animprovedmultiobjectinstancesegmentationbasedondeeplearning
AT nawafalshdaifat improvedmultiobjectinstancesegmentationbasedondeeplearning
AT mohdazamosman improvedmultiobjectinstancesegmentationbasedondeeplearning
AT abdullahzawawitalib improvedmultiobjectinstancesegmentationbasedondeeplearning