no code implementations • 19 Apr 2024 • Hisashi Shimodaira
In this paper, we propose a method to improve prediction accuracy of semantic segmentation methods as follows: (1) construct a neural network that has pre-processing layers based on a convolutional autoencoder ahead of a semantic segmentation network, and (2) train the entire network initialized by the weights of the pre-trained autoencoder.
no code implementations • 19 Jun 2019 • Hisashi Shimodaira
The probabilistic Rand (PR) index has the following three problems: It lacks variations in its value over images; the normalized probabilistic Rand (NPR) index to address this is theoretically unclear, and the sampling method of pixel-pairs was not proposed concretely.
no code implementations • 26 Nov 2017 • Hisashi Shimodaira
The major features of our method are as follows: the use of square elemental regions instead of pixels as the processing unit, a seed generation method based on enhanced gradient values, a seed region growing method exploiting local gradient values, a region merging method using a similarity measure including a homogeneity distance based on Tsallis entropy, and a termination condition of region merging using an estimated desired number of regions.