A Comprehensive Survey of Deep Learning Approaches in Image Processing
The integration of deep learning (DL) into image processing has driven transformative advancements, enabling capabilities far beyond the reach of traditional methodologies. This survey offers an in-depth exploration of the DL approaches that have redefined image processing, tracing their evolution f...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/2/531 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587524530241536 |
|---|---|
| author | Maria Trigka Elias Dritsas |
| author_facet | Maria Trigka Elias Dritsas |
| author_sort | Maria Trigka |
| collection | DOAJ |
| description | The integration of deep learning (DL) into image processing has driven transformative advancements, enabling capabilities far beyond the reach of traditional methodologies. This survey offers an in-depth exploration of the DL approaches that have redefined image processing, tracing their evolution from early innovations to the latest state-of-the-art developments. It also analyzes the progression of architectural designs and learning paradigms that have significantly enhanced the ability to process and interpret complex visual data. Key advancements, such as techniques improving model efficiency, generalization, and robustness, are examined, showcasing DL’s ability to address increasingly sophisticated image-processing tasks across diverse domains. Metrics used for rigorous model evaluation are also discussed, underscoring the importance of performance assessment in varied application contexts. The impact of DL in image processing is highlighted through its ability to tackle complex challenges and generate actionable insights. Finally, this survey identifies potential future directions, including the integration of emerging technologies like quantum computing and neuromorphic architectures for enhanced efficiency and federated learning for privacy-preserving training. Additionally, it highlights the potential of combining DL with emerging technologies such as edge computing and explainable artificial intelligence (AI) to address scalability and interpretability challenges. These advancements are positioned to further extend the capabilities and applications of DL, driving innovation in image processing. |
| format | Article |
| id | doaj-art-c40dc3195f894b278baf740fbe512d07 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-c40dc3195f894b278baf740fbe512d072025-01-24T13:49:15ZengMDPI AGSensors1424-82202025-01-0125253110.3390/s25020531A Comprehensive Survey of Deep Learning Approaches in Image ProcessingMaria Trigka0Elias Dritsas1Industrial Systems Institute (ISI), Athena Research and Innovation Center, 26504 Patras, GreeceIndustrial Systems Institute (ISI), Athena Research and Innovation Center, 26504 Patras, GreeceThe integration of deep learning (DL) into image processing has driven transformative advancements, enabling capabilities far beyond the reach of traditional methodologies. This survey offers an in-depth exploration of the DL approaches that have redefined image processing, tracing their evolution from early innovations to the latest state-of-the-art developments. It also analyzes the progression of architectural designs and learning paradigms that have significantly enhanced the ability to process and interpret complex visual data. Key advancements, such as techniques improving model efficiency, generalization, and robustness, are examined, showcasing DL’s ability to address increasingly sophisticated image-processing tasks across diverse domains. Metrics used for rigorous model evaluation are also discussed, underscoring the importance of performance assessment in varied application contexts. The impact of DL in image processing is highlighted through its ability to tackle complex challenges and generate actionable insights. Finally, this survey identifies potential future directions, including the integration of emerging technologies like quantum computing and neuromorphic architectures for enhanced efficiency and federated learning for privacy-preserving training. Additionally, it highlights the potential of combining DL with emerging technologies such as edge computing and explainable artificial intelligence (AI) to address scalability and interpretability challenges. These advancements are positioned to further extend the capabilities and applications of DL, driving innovation in image processing.https://www.mdpi.com/1424-8220/25/2/531image processingdeep learningtechniquesmodelsmetrics |
| spellingShingle | Maria Trigka Elias Dritsas A Comprehensive Survey of Deep Learning Approaches in Image Processing Sensors image processing deep learning techniques models metrics |
| title | A Comprehensive Survey of Deep Learning Approaches in Image Processing |
| title_full | A Comprehensive Survey of Deep Learning Approaches in Image Processing |
| title_fullStr | A Comprehensive Survey of Deep Learning Approaches in Image Processing |
| title_full_unstemmed | A Comprehensive Survey of Deep Learning Approaches in Image Processing |
| title_short | A Comprehensive Survey of Deep Learning Approaches in Image Processing |
| title_sort | comprehensive survey of deep learning approaches in image processing |
| topic | image processing deep learning techniques models metrics |
| url | https://www.mdpi.com/1424-8220/25/2/531 |
| work_keys_str_mv | AT mariatrigka acomprehensivesurveyofdeeplearningapproachesinimageprocessing AT eliasdritsas acomprehensivesurveyofdeeplearningapproachesinimageprocessing AT mariatrigka comprehensivesurveyofdeeplearningapproachesinimageprocessing AT eliasdritsas comprehensivesurveyofdeeplearningapproachesinimageprocessing |