Loss function for ambiguous boundaries for deep neural network (DNN) for image segmentation

被引：1

作者：

Hakumura, Yuma ^{[1
]}

Ito, Taiyo ^{[1
]}

Matsui, Shiori ^{[1
]}

Akiba, Yuya ^{[1
]}

Aoki, Kimiya ^{[1
]}

Nakashima, Yuki ^{[2
]}

Hirao, Kiyoshi ^{[2
]}

Fukushima, Manabu ^{[2
]}

机构：

[1] Chukyo Univ, 101-2 Yagotohonmachi,Showa Ku, Nagoya, Aichi 4668666, Japan

[2] Natl Inst Adv Ind Sci & Technol, Multimat Res Inst, Ceram Microstruct Control Grp, Nagoya, Aichi, Japan

来源：

ELECTRONICS AND COMMUNICATIONS IN JAPAN | 2023年 / 106卷 / 04期

关键词：

blurriness of grain boundaries; deep neural network; fine ceramics; loss function; segmentation;

D O I：

10.1002/ecj.12429

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This study deals with the task of segmentation of SEM images of fine ceramics sintered bodies by using deep neural network (DNN). In particular, we focus on misclassification caused by the blurriness of grain boundaries(boundaries between particles). Therefore, we utilize the frequency distribution of brightness gradient of grain boundaries and give higher weights to pixels with lower gradient values. Experiments confirmed that the model trained with proposed loss function gave the best prediction results.

引用

页数：9

共 50 条

[41] Closing the Gap Between Deep Neural Network Modeling and Biomedical Decision-Making Metrics in Segmentation via Adaptive Loss Functions
Seo, Hyunseok
Bassenne, Maxime
Xing, Lei
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2021, 40 (02) : 585 - 593
[42] Towards resource-frugal deep convolutional neural networks for hyperspectral image segmentation
Nalepa, Jakub
Antoniak, Marek
Myller, Michal
Lorenzo, Pablo Ribalta
Marcinkiewicz, Michal
MICROPROCESSORS AND MICROSYSTEMS, 2020, 73
[43] Deep learning based neural network application for automatic ultrasonic computed tomographic bone image segmentation
Marwa, Fradi
Zahzah, El-hadi
Bouallegue, Kais
Machhout, Mohsen
MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (10) : 13537 - 13562
[44] Ovarian Tumor Ultrasound Image Segmentation with Deep Neural Networks
Siahpoosh, Mahnaz
Imani, Maryam
Ghassemian, Hassan
PROCEEDINGS OF THE 13TH IRANIAN/3RD INTERNATIONAL MACHINE VISION AND IMAGE PROCESSING CONFERENCE, MVIP, 2024, : 112 - 116
[45] Development of a Deep Neural Network (DNN) Model for Feature Selection from Satellite Images
Mitra, Soma
Chowdhury, Debkumar
Nandan, Mauparna
Parial, Kajori
Basu, Saikat
JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING, 2025,
[46] Structure-aware Loss Function for Ultrasound Image Segmentation
Fu, Yixuan
Chen, Junying
Li, Kai
INTERNATIONAL ULTRASONICS SYMPOSIUM (IEEE IUS 2021), 2021,
[47] Deep learning neural network for texture feature extraction in oral cancer: enhanced loss function
Bishal Bhandari
Abeer Alsadoon
P. W. C. Prasad
Salma Abdullah
Sami Haddad
Multimedia Tools and Applications, 2020, 79 : 27867 - 27890
[48] Deep learning neural network for texture feature extraction in oral cancer: enhanced loss function
Bhandari, Bishal
Alsadoon, Abeer
Prasad, P. W. C.
Abdullah, Salma
Haddad, Sami
MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (37-38) : 27867 - 27890
[49] Toward Multicenter Skin Lesion Classification Using Deep Neural Network With Adaptively Weighted Balance Loss
Yue, Guanghui
Wei, Peishan
Zhou, Tianwei
Jiang, Qiuping
Yan, Weiqing
Wang, Tianfu
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2023, 42 (01) : 119 - 131
[50] SEGMENTATION OF ELECTRICAL SUBSTATIONS USING DEEP CONVOLUTIONAL NEURAL NETWORK
Mesvari, M.
Shah-Hosseini, R.
ISPRS GEOSPATIAL CONFERENCE 2022, JOINT 6TH SENSORS AND MODELS IN PHOTOGRAMMETRY AND REMOTE SENSING, SMPR/4TH GEOSPATIAL INFORMATION RESEARCH, GIRESEARCH CONFERENCES, VOL. 10-4, 2023, : 495 - 500

← 1 2 3 4 5 →