Details

Autor(en) / Beteiligte

• Sultana, Farhana
• Sufian, Abu
• Dutta, Paramartha

Titel

Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey

Ist Teil von

• Knowledge-based systems, 2020-08, Vol.201-202, p.106062, Article 106062

Ort / Verlag

Amsterdam: Elsevier B.V

Erscheinungsjahr

2020

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• From the autonomous car driving to medical diagnosis, the requirement of the task of image segmentation is everywhere. Segmentation of an image is one of the indispensable tasks in computer vision. This task is comparatively complicated than other vision tasks as it needs low-level spatial information. Basically, image segmentation can be of two types: semantic segmentation and instance segmentation. The combined version of these two basic tasks is known as panoptic segmentation. In the recent era, the success of deep convolutional neural networks (CNN) has influenced the field of segmentation greatly and gave us various successful models to date. In this survey, we are going to take a glance at the evolution of both semantic and instance segmentation work based on CNN. We have also specified comparative architectural details of some state-of-the-art models and discuss their training details to present a lucid understanding of hyper-parameter tuning of those models. We have also drawn a comparison among the performance of those models on different datasets. Lastly, we have given a glimpse of some state-of-the-art panoptic segmentation models. •Gives taxonomy and survey of the evolution of CNN based image segmentation.•Explores elaborately some CNN based popular state-of-the-art segmentation models.•Compares training details of those models to have a clear view of hyper-parameter tuning.•Compares the performance metrics of those state-of-the-art models on different datasets.