Abstract
Image semantic segmentation is one of the key problems in computer vision. Despite the enormous advances in applications, almost all the image semantic segmentation algorithms fail to achieve satisfactory segmentation results due to lack of sensitivity to details, or difficulty in evaluating the global similarity of pixels, or both. Posting-processing enhancement methods, as the outstandingly crucial means to ameliorate the above-mentioned inherent flaws of algorithms, are almost based on conditional random fields (CRFs). Inspired by CRFs, this paper proposes a novel post-processing enhancement framework with theoretical simplicity from the perspective of filtering, and a new weighted composite filter (WCF) is designed to enhance the segmentation masks in a unified framework. First, by adjusting the weight ratio, the WCF is decomposed into a local part and a global part. Secondly, a guided image filter is designed as the local filter, which can restore boundary information to present necessary details. Moreover, a minimum spanning tree (MST)-based filter is designed as the global filter to provide a natural measure of global pixel similarity for image matching. Thirdly, a unified post-processing enhancement framework, including selection and normalization, WCF and argmax, is designed. Finally, the effectiveness and superiority of the proposed method for enhancement, as well as its range of applications, are verified through experiments.
Highlights
Image semantic segmentation [1,2] refers to the pixel level segmentation and marking of different kinds of objects from the image, and it is widely applied into various fields such as aerospace, military, intelligent driving, multimedia, medicine, and so on
A majority of popular learning methods for image semantic segmentation are mainly based on fully convolutional network (FCN) [3], which greatly improves the segmentation accuracy and is considered as the cornerstone of this research field [4]
This allows us to have more choices to handle the enhancement issues when designing post-processing enhancement strategies besides the frameworks based on conditional random fields (CRFs)
Summary
Image semantic segmentation [1,2] refers to the pixel level segmentation and marking of different kinds of objects from the image, and it is widely applied into various fields such as aerospace, military, intelligent driving, multimedia, medicine, and so on. A majority of popular learning methods for image semantic segmentation are mainly based on fully convolutional network (FCN) [3], which greatly improves the segmentation accuracy and is considered as the cornerstone of this research field [4]. A semi-supervised multilabel FCN for hierarchical object parsing of images is presented in [6]. A global-and-local network architecture (GLNet) is proposed in [9] to incorporate global spatial information and dense local multi-scale context information, so as to model the relationship between objects in a scene. Two types of attention modules are appended
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
