สืบค้นงานวิจัย
Semantic segmentation of artery-venous retinal vessel using simple convolutional neural network
Setiawan W. - ไม่ระบุหน่วยงาน
ชื่อเรื่อง (EN): Semantic segmentation of artery-venous retinal vessel using simple convolutional neural network
ผู้แต่ง / หัวหน้าโครงการ (EN): Setiawan W.
บทคัดย่อ (EN): Semantic segmentation is how to categorize objects in an image based on pixel color intensity. There is an implementation in the medical imaging. This article discusses semantic segmentation in retinal blood vessels. Retinal blood vessels consist of artery and vein. Arteryvenous segmentation is needed to detect diabetic retinopathy, hypertension, and artherosclerosis. The data for the experiment is Retinal Image vessel Tree Extraction (RITE). Data consists of 20 patches with a dimension of 128 × 128 × 3. The process for performing semantic segmentation consists of 3 method, create a Conventional Neural Network (CNN) model, pre-trained network, and training the network. The CNN model consists of 10 layers, 1 input layer image, 3 convolution layers, 2 Rectified Linear Units (ReLU), 1 Max pooling, 1 transposed convolution layer, 1 softmax and 1 pixel classification layer. The pre-trained network uses the optimization algorithm Stochastic Gradient Descent with Momentum (SGDM), Root Mean Square Propagation (RMSProp) and Adaptive Moment optimization (Adam). Various scenarios were tested to get optimal accuracy. The learning rate is 1e-3 and 1e-2. Minibatch size are 4,8,16,32,64, and 128. The maximum value of epoch is set to 100. The results show the highest accuracy of up to 98.35% © 2019 Published under licence by IOP Publishing Ltd.
บทคัดย่อ: ไม่พบข้อมูลจากหน่วยงานต้นทาง
ภาษา (EN): en
เอกสารแนบ (EN): https://www.scopus.com/inward/record.uri?eid=2-s2.0-85064865010&doi=10.1088%2f1755-1315%2f243%2f1%2f012021&partnerID=40&md5=1c08f82636f80529d922e7dcde015541
เผยแพร่โดย (EN): มหาวิทยาลัยมหิดล
คำสำคัญ (EN): Image segmentation
เจ้าของลิขสิทธิ์ (EN): มหาวิทยาลัยมหิดล
หากไม่พบเอกสารฉบับเต็ม (Full Text) โปรดติดต่อหน่วยงานเจ้าของข้อมูล

การอ้างอิง


TARR Wordcloud:
Semantic segmentation of artery-venous retinal vessel using simple convolutional neural network
Setiawan W.
มหาวิทยาลัยมหิดล
ไม่ระบุวันที่เผยแพร่
A simple grid implementation with Berkeley Open Infrastructure for Network Computing using BLAST as a model Three-stages hard exudates segmentation in retinal images Determination of corn leaf area using simple mathematic models Identification of Rubber Clones (Hevea brasiliensis) Using Inter Simple Sequence Repeat (ISSR) Markers Assessing genetic diversity of some banana cultivars using inter simple sequence repeats (ISSR) markers Differentiating Corynespora Cassiicola Isolated From Hevea Plantations in Malaysia Using Inter Simple Sequence Repeat (ISSR) Markers Phytostilbenoid production in white mulberry (Morus alba L.) cell culture using bioreactors and simple deglycosylation by endogenous enzymatic hydrolysis Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images Predictions of equilibrium solubility and mass transfer coefficient for CO2 absorption into aqueous solutions of 4-diethylamino-2-butanol using artificial neural networks A novel highly flexible, simple, rapid and low-cost fabrication tool for paper-based microfluidic devices (μPADs) using technical drawing pens and in-house formulated aqueous inks
คัดลอก URL
กระทู้ของฉัน
ผลการสืบค้นทั้งหมด โพสต์     เรียงลำดับจาก