GPU-Accelerated Feature Extraction for Real-Time Vision AI and LLM Systems Efficiency: Autonomous Image Segmentation, Unsupervised Clustering, and Smart Pattern Recognition for Scalable AI Processing with 6.6× Faster Performance, 2.5× Higher Accuracy, and UX-Centric UI Boosting Human-in-the-Loop Productivity
The high computational cost of digital image processing, requiring high-performance hardware and extensive resources, severely limits real-time applications. While advancements in algorithm design and GPU acceleration have significantly improved efficiency, modern AI-driven applications such as larg...
Saved in:
| Published in: | ASMC proceedings pp. 1 - 8 |
|---|---|
| Main Authors: | , , , |
| Format: | Conference Proceeding |
| Language: | English |
| Published: |
IEEE
05.05.2025
|
| Subjects: | |
| ISSN: | 2376-6697 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | The high computational cost of digital image processing, requiring high-performance hardware and extensive resources, severely limits real-time applications. While advancements in algorithm design and GPU acceleration have significantly improved efficiency, modern AI-driven applications such as large language models (LLMs), Generative AI (GenAI), medical imaging, autonomous vehicle perception, photography, advanced nano-scale semiconductor metrology, satellite image analysis, high-precision manufacturing, robotics, and real-time anomaly detection, still demand further optimization to reduce computational overhead and improve scalability.In this paper, we introduce GPU-Accelerated Feature Extraction to enhance runtime and efficiency in edge-based simulations. Our approach leverages AI-driven clustering, grouping images with similar visual and pattern characteristics to enable adaptive tuning on a small subset before generalizing across the full dataset. This method achieves a 3.78× reduction in runtime.Furthermore, rather than processing an entire image, we recognize and extract a single representative pattern or region of interest (ROI) per image, removing redundant data and background noise. This refinement results in an additional 1.74× runtime improvement, culminating in an overall 6.6× speed boost, enhancing Scalable Real-Time AI Processing. We also demonstrated that with a similar runtime, the accuracy achieved is 2.5× higher.This solution, integrated into Calibre SEMSuite™, supports multicloud and real-time deployment for enhanced scalability, usability, and performance, providing users with a powerful tool for fully automated, AI-driven image classification, making high-throughput image review feasible even at the scale required for cutting-edge applications.Beyond performance gains, this approach introduces autonomous data cleaning, anomaly detection and defect identification mechanism, allowing failed patterns and defective images to be identified without human intervention, boosting the reviewer productivity.As GenAI and LLM systems gain popularity, the computational demands on modern systems have reached unprecedented levels. As we demonstrate, thanks to feature extraction and ROI selection, instead of needing for the entire dataset to be processed, only a fraction of the data could be used. This is crucial for reducing the computational overhead of LLM systems.We demonstrate that our method enables high-precision, real-time AI inference with applications in computer vision, LLMs, autonomous systems, healthcare, and scalable AI computing. |
|---|---|
| AbstractList | The high computational cost of digital image processing, requiring high-performance hardware and extensive resources, severely limits real-time applications. While advancements in algorithm design and GPU acceleration have significantly improved efficiency, modern AI-driven applications such as large language models (LLMs), Generative AI (GenAI), medical imaging, autonomous vehicle perception, photography, advanced nano-scale semiconductor metrology, satellite image analysis, high-precision manufacturing, robotics, and real-time anomaly detection, still demand further optimization to reduce computational overhead and improve scalability.In this paper, we introduce GPU-Accelerated Feature Extraction to enhance runtime and efficiency in edge-based simulations. Our approach leverages AI-driven clustering, grouping images with similar visual and pattern characteristics to enable adaptive tuning on a small subset before generalizing across the full dataset. This method achieves a 3.78× reduction in runtime.Furthermore, rather than processing an entire image, we recognize and extract a single representative pattern or region of interest (ROI) per image, removing redundant data and background noise. This refinement results in an additional 1.74× runtime improvement, culminating in an overall 6.6× speed boost, enhancing Scalable Real-Time AI Processing. We also demonstrated that with a similar runtime, the accuracy achieved is 2.5× higher.This solution, integrated into Calibre SEMSuite™, supports multicloud and real-time deployment for enhanced scalability, usability, and performance, providing users with a powerful tool for fully automated, AI-driven image classification, making high-throughput image review feasible even at the scale required for cutting-edge applications.Beyond performance gains, this approach introduces autonomous data cleaning, anomaly detection and defect identification mechanism, allowing failed patterns and defective images to be identified without human intervention, boosting the reviewer productivity.As GenAI and LLM systems gain popularity, the computational demands on modern systems have reached unprecedented levels. As we demonstrate, thanks to feature extraction and ROI selection, instead of needing for the entire dataset to be processed, only a fraction of the data could be used. This is crucial for reducing the computational overhead of LLM systems.We demonstrate that our method enables high-precision, real-time AI inference with applications in computer vision, LLMs, autonomous systems, healthcare, and scalable AI computing. |
| Author | Ahi, Kiarash Sriram, Satya Wu, Stewart Fenger, Germain |
| Author_xml | – sequence: 1 givenname: Kiarash surname: Ahi fullname: Ahi, Kiarash email: kiarash.ahi@siemens.com organization: Siemens EDA,USA – sequence: 2 givenname: Stewart surname: Wu fullname: Wu, Stewart organization: Siemens EDA,Belgium – sequence: 3 givenname: Satya surname: Sriram fullname: Sriram, Satya organization: Siemens EDA,India – sequence: 4 givenname: Germain surname: Fenger fullname: Fenger, Germain organization: Siemens EDA,USA |
| BookMark | eNo9kVGO0zAQhrMIJHaXvQESc4CmJHHtJLyFqN1WyoqKtIi3leNOUqPErmxnISfhQFwMhwWeLP3j-f6Z-W-Cl0orDIJ3cbSM4yh_X9QPJVvROFkmUUJnLY5okl4Fd3maZ4TElMQZjV4E1wlJWchYnr4Obqz9FkURy7P4-iq93x_DQgjs0XCHJ9ggd6NBWP9whgsntYJWG_iMvA8PckD4Iu0sFjvg6gRV9QD1ZB0OFtZtK4VEJaYPUIxOKz3o0cJu4B1Cjd2AyvGZuICjsuMFzZO03rLsRw8wUnWLP8x64MbBnjsvKu8sdKfk_0lqwXve9DhPsDdaoLW-E75Ldwa2ZL9-wobPONij8f8HrgQuIFlSX9nK7uwrft_RLzc92x2_hqWfzEgBxx181Nq6GbgdfWsoVejOGFZaX2a30-hP8iTd9CZ41fLe4t3f9zY4bNaHchtWn-53ZVGFMicuFD6RJmszzihpEk59HiuSEi5Yg1GOlNO0YVEj4lNGVk2eZA3lKeMNy9mqzSght8HbZ6xExMeLkf400-O_nMlvkhCkAw |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/ASMC64512.2025.11010527 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISBN | 9798331531850 |
| EISSN | 2376-6697 |
| EndPage | 8 |
| ExternalDocumentID | 11010527 |
| Genre | orig-research |
| GroupedDBID | 23M 6IE 6IF 6IH 6IK 6IL 6IM 6IN AAJGR AAWTH ABLEC ACGFS ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP IPLJI M43 OCL RIE RIL RIO RNS |
| ID | FETCH-LOGICAL-i93t-c110b8f8a653b2a51534373ac6be09e5a57b60bc1d834b928b5a76ab6964f8533 |
| IEDL.DBID | RIE |
| IngestDate | Wed Aug 27 01:39:04 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i93t-c110b8f8a653b2a51534373ac6be09e5a57b60bc1d834b928b5a76ab6964f8533 |
| PageCount | 8 |
| ParticipantIDs | ieee_primary_11010527 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-May-5 |
| PublicationDateYYYYMMDD | 2025-05-05 |
| PublicationDate_xml | – month: 05 year: 2025 text: 2025-May-5 day: 05 |
| PublicationDecade | 2020 |
| PublicationTitle | ASMC proceedings |
| PublicationTitleAbbrev | ASMC |
| PublicationYear | 2025 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0006981 |
| Score | 2.290731 |
| Snippet | The high computational cost of digital image processing, requiring high-performance hardware and extensive resources, severely limits real-time applications.... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1 |
| SubjectTerms | Accuracy AI clustering Anomaly detection Artificial intelligence autonomous image segmentation Clustering algorithms Computational efficiency deep pattern recognition edge deployment Feature extraction GenAI Generative AI GPU-accelerated computing Image edge detection LLM Efficiency real-time AI inference Real-time systems Runtime scalable vision systems Tuning |
| Title | GPU-Accelerated Feature Extraction for Real-Time Vision AI and LLM Systems Efficiency: Autonomous Image Segmentation, Unsupervised Clustering, and Smart Pattern Recognition for Scalable AI Processing with 6.6× Faster Performance, 2.5× Higher Accuracy, and UX-Centric UI Boosting Human-in-the-Loop Productivity |
| URI | https://ieeexplore.ieee.org/document/11010527 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NbtswDNbWYoftsr8MW_cDHnaM0tixZGu3LEi2AGlhNE2RWyFZchFgsYPYLrYn2QPtxUbKTrsddtjNsCGRggiSlvh9ZOwjxhAtVCC4syrkkbSWa6cND_Qoi_LE5rnHV1wt4vPzZL1WaQdW91gY55wvPnMDevR3-bbMGjoqO8VQhelAGB-xoziWLVjrzu1KlQRdAVcwVKfj5dlERqgK_gOGYnAY-lcTFR9DZk__U_oz1rtH40F6F2ees4eueMGe_EEk-PJB_CVd8XGWYQwh6gcLlNk1ewfT7_W-hS4AZqdwgWkhJ9QHXHlMOYznoAsLi8UZdNzlMPWkEoTI_ATjpibQQ9lUMN-i54Glu9l2aKWiD6uianbkbCoUOfnWEOkC6tP3cy63aJWQev7OAi4OhUqdJku0DUJtkQYdWAFHAh0LgxzIXz9hpmk6SO-RDX0IBwK_tLUpgOttcHE_WnGrNfcn1ZsMVnP4XJYVFXSDv6Tgm4JjossXZbkjacRx65tm9NjlbHo5-cq7lhB8o0Y1z3APTJInWoqRQSNDd03UTDqTxg2VE1rERg5NFthkFBkVJkboWGojlUTDw8z2FTsuysK9ZhDJnLr_OhVqE2H0MUGG5mpsaPGPMFTiDeuRCVzvWtKP68Pun_zj_Vv2mAzN10KKd-y43jfuPXuU3dabav_Bm-pvox7v-A |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NjtMwEDawILFc-Cti-Z0Dx7rbpLETcytVy1akVbRtV71VduysKtGkahIET8ID8WKMnXQXDhy4RYnsGcujmYk93zeEfMAYIpnwGDVa-DTgWlNppKKeHKRBFuksc_iKqzicz6P1WiQtWN1hYYwxrvjM9Oyju8vXRVrbo7JzDFWYDvjhPXKfBYHfb-BaN46Xi8hrS7i8vjgfLmYjHqAy-Bfos95x8F9tVFwUmTz-T_lPSOcWjwfJTaR5Su6a_Bl59AeV4PM74edkRYdpilHEkj9osLldfTAw_l4dGvACYH4Kl5gYUov7gCuHKofhFGSuIY5n0LKXw9jRSlhM5kcY1pWFPRR1CdMd-h5YmOtdi1fKu7DKy3pv3U2JIkdfa0u7gPp03ZyLHdolJI7BM4fLY6lSq8kCrcPitqwGLVwBR4I9GAbe479-wkTa6SC5xTZ0we8x_NJUpwCut8bF_WjErdbUnVVvU1hN4VNRlLakG9w1Bd3mFFNdGhfF3kqzLLeubUaHLCfj5eiCtk0h6FYMKpriHqgoiyRnA4Vmhg7bkjPJlCvTF4ZJFireV6mno0GghB8pJkMuFRccTQ9z2xfkJC9y85JAwDPb_9cIX6oA44_yUjRYpX2N_4S-YGekY01gs29oPzbH3X_1j_fvycOL5SzexNP5l9fk1Bqdq4xkb8hJdajNW_Ig_VZty8M7Z7a_ATbu8z8 |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=ASMC+proceedings&rft.atitle=GPU-Accelerated+Feature+Extraction+for+Real-Time+Vision+AI+and+LLM+Systems+Efficiency%3A+Autonomous+Image+Segmentation%2C+Unsupervised+Clustering%2C+and+Smart+Pattern+Recognition+for+Scalable+AI+Processing+with+6.6%C3%97+Faster+Performance%2C+2.5%C3%97+Higher+Accuracy%2C+and+UX-Centric+UI+Boosting+Human-in-the-Loop+Productivity&rft.au=Ahi%2C+Kiarash&rft.au=Wu%2C+Stewart&rft.au=Sriram%2C+Satya&rft.au=Fenger%2C+Germain&rft.date=2025-05-05&rft.pub=IEEE&rft.eissn=2376-6697&rft.spage=1&rft.epage=8&rft_id=info:doi/10.1109%2FASMC64512.2025.11010527&rft.externalDocID=11010527 |