BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Warsaw BEGIN:DAYLIGHT DTSTART:20250330T030000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST END:DAYLIGHT BEGIN:STANDARD DTSTART:20251026T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250410T173945Z UID:3E6008B2-4615-499E-BEA9-411B41EA0ECC DTSTART;TZID=Europe/Warsaw:20250410T113000 DTEND;TZID=Europe/Warsaw:20250410T133000 DESCRIPTION:This talk presents an integrated exploration of advanced geomet ric and computational approaches applied to the modeling and analysis of t he human eye. Our discussion is divided into three main parts: (1) 3D mode ling of the oculomotor system\, (2) a novel theory of color perception usi ng conformal geometric algebra\, and (3) deep learning-based medical image processing techniques for detecting eye-related illnesses.\n\n1. 3D Eye M odel and the Motor Algebra Framework\nWe begin by presenting a detailed 3D model of the oculomotor system using the Motor Algebra Framework. This ma thematical formulation allows for a more accurate representation of rigid body motions and rotations within the eye. Unlike traditional vector-based models\, motor algebra offers compact and coordinate-free formulations\, making it particularly well-suited for simulating the complex movements of the eyeball and extraocular muscles. This has promising implications for biomedical engineering\, particularly in the development of assistive tech nologies\, surgical simulations\, and diagnostic tools.\n\n2. A Novel Theo ry of Color in Conformal Geometric Algebra\nIn the second part of the lect ure\, we introduce a groundbreaking theory of color developed using the to ols of Conformal Geometric Algebra (CGA). This theory not only generalizes prior models from the last five decades but also provides a unified and c onsistent framework for representing and processing color information in h igher-dimensional spaces. By employing the light cone as a geometric compu tational framework and utilizing the Minkowski metric in conjunction with Lorentz transformations\, we construct a physically coherent space suited for accurate color modeling and processing. The conventional RGB model\, r epresented in 3D Euclidean space\, fails to represent color appropriately\ ; instead\, a pseudo-Euclidean metric—such as that defined by the light cone—is necessary for a correct depiction of color space. The practical validity of this theory is demonstrated through its ability to model chang es in object appearance under different natural lighting conditions\, such as those occurring throughout the day. In this context\, we introduce the Quaternion Split Fourier Transform (QSFT) for color image filtering withi n a pseudo-Euclidean metric. This approach proves to be more robust and ef fective than the conventional Quaternion Fourier Transform\, particularly in capturing the chromatic and structural components of images under non-u niform illumination. We further demonstrate how the Quaternion Split Neura l Network (QSNN) can be used to equalize and enhance color images by learn ing the transformations dictated by our geometric framework.\n\n3. Deep Le arning in Medical Image Processing of Eye Diseases\nIn the final section\, we shift focus to the application of Deep Learning\, specifically Convolu tional Neural Networks (CNNs)\, in the medical analysis of eye diseases. D iseases such as age-related macular degeneration\, diabetic retinopathy\, glaucoma\, and cataracts can be detected and monitored using automated ima ge processing techniques.\nBy training CNNs on large datasets of retinal a nd ocular images\, we are able to automatically extract and classify criti cal pathological features. This includes segmentation of lesions\, blood v essels\, and optic disc regions\, which are crucial for accurate diagnosis . The integration of geometric color modeling into the preprocessing pipel ine can further enhance feature extraction by correcting lighting variatio ns and improving contrast.\nThe use of these technologies allows for earli er and more precise diagnosis\, supporting ophthalmologists in decision-ma king and enabling personalized treatment strategies for patients. Moreover \, these tools hold potential for deployment in remote or under-resourced healthcare settings\, expanding access to high-quality eye care.\n\nCo-spo nsored by: Poznan University of Technology\n\nSpeaker(s): Eduardo Bayro\n\ nRoom: room 230\, Bldg: CENTER FOR MECHATRONICS\, BIOMECHANICS\, AND NANOE NGINEERING\, POZNAŃ UNIVERSITY OF TECHNOLOGY\, ul. Jana Pawła II 24\, 60 -965 Poznań\, Poland\, Poznań\, Wielkopolskie\, Poland\, 60-965\, Virtua l: https://events.vtools.ieee.org/m/478210 LOCATION:Room: room 230\, Bldg: CENTER FOR MECHATRONICS\, BIOMECHANICS\, AN D NANOENGINEERING\, POZNAŃ UNIVERSITY OF TECHNOLOGY\, ul. Jana Pawła II 24\, 60-965 Poznań\, Poland\, Poznań\, Wielkopolskie\, Poland\, 60-965\, Virtual: https://events.vtools.ieee.org/m/478210 ORGANIZER:adam.dabrowski@put.poznan.pl SEQUENCE:49 SUMMARY:Eye Modeling\, Color Theory\, and Medical Image Processing of Eye D iseases URL;VALUE=URI:https://events.vtools.ieee.org/m/478210 X-ALT-DESC:Description: <br /><p>This talk presents an integrated explorati on of advanced geometric and computational approaches applied to the model ing and analysis of the human eye. Our discussion is divided into three ma in parts: (1) 3D modeling of the oculomotor system\, (2) a novel theory of color perception using conformal geometric algebra\, and (3) deep learnin g-based medical image processing techniques for detecting eye-related illn esses.</p>\n<p>1. 3D Eye Model and the Motor Algebra Framework<br>We begin by presenting a detailed 3D model of the oculomotor system using the Moto r Algebra Framework. This mathematical formulation allows for a more accur ate representation of rigid body motions and rotations within the eye. Unl ike traditional vector-based models\, motor algebra offers compact and coo rdinate-free formulations\, making it particularly well-suited for simulat ing the complex movements of the eyeball and extraocular muscles. This has promising implications for biomedical engineering\, particularly in the d evelopment of assistive technologies\, surgical simulations\, and diagnost ic tools.</p>\n<p>2. A Novel Theory of Color in Conformal Geometric Algebr a<br>In the second part of the lecture\, we introduce a groundbreaking the ory of color developed using the tools of Conformal Geometric Algebra (CGA ). This theory not only generalizes prior models from the last five decade s but also provides a unified and consistent framework for representing an d processing color information in higher-dimensional spaces. By employing the light cone as a geometric computational framework and utilizing the Mi nkowski metric in conjunction with Lorentz transformations\, we construct a physically coherent space suited for accurate color modeling and process ing. The conventional RGB model\, represented in 3D Euclidean space\, fail s to represent color appropriately\; instead\, a pseudo-Euclidean metric&m dash\;such as that defined by the light cone&mdash\;is necessary for a cor rect depiction of color space. The practical validity of this theory is de monstrated through its ability to model changes in object appearance under different natural lighting conditions\, such as those occurring throughou t the day. In this context\, we introduce the Quaternion Split Fourier Tra nsform (QSFT) for color image filtering within a pseudo-Euclidean metric. This approach proves to be more robust and effective than the conventional Quaternion Fourier Transform\, particularly in capturing the chromatic an d structural components of images under non-uniform illumination. We furth er demonstrate how the Quaternion Split Neural Network (QSNN) can be used to equalize and enhance color images by learning the transformations dicta ted by our geometric framework.</p>\n<p>3. Deep Learning in Medical Image Processing of Eye Diseases<br>In the final section\, we shift focus to the application of Deep Learning\, specifically Convolutional Neural Networks (CNNs)\, in the medical analysis of eye diseases. Diseases such as age-re lated macular degeneration\, diabetic retinopathy\, glaucoma\, and catarac ts can be detected and monitored using automated image processing techniqu es.<br>By training CNNs on large datasets of retinal and ocular images\, w e are able to automatically extract and classify critical pathological fea tures. This includes segmentation of lesions\, blood vessels\, and optic d isc regions\, which are crucial for accurate diagnosis. The integration of geometric color modeling into the preprocessing pipeline can further enha nce feature extraction by correcting lighting variations and improving con trast.<br>The use of these technologies allows for earlier and more precis e diagnosis\, supporting ophthalmologists in decision-making and enabling personalized treatment strategies for patients. Moreover\, these tools hol d potential for deployment in remote or under-resourced healthcare setting s\, expanding access to high-quality eye care.</p> END:VEVENT END:VCALENDAR