no code implementations • 28 Dec 2023 • Ga-Eun Kim, Chang-Hwan Son
More importantly, for the new challenging dataset IP102(CBSS) that contains only pest images with complex backgrounds and small sizes, the proposed model can maintain high recognition accuracy, whereas that of other SOTA models decrease sharply, demonstrating that our model is more robust to complex background and scale problems.
no code implementations • 5 Apr 2023 • Jae-Hyeon Lee, Chang-Hwan Son
In addition, the proposed model is confirmed to be effective in overcoming severe occlusions and variations in pose and scale.
no code implementations • 18 Apr 2022 • Chang-Hwan Son, Da-Hee Jeong
Unlike traditional image degradation models (IDM), such as rain removal and superresolution, this study addresses a new IDM referred to as a scale-aware heavy rain model and proposes a method for restoring high-resolution face images (HR-FIs) from low-resolution heavy rain face images (LRHR-FI).
no code implementations • 28 May 2021 • Chang-Hwan Son, Pung-Hwi Ye
To achieve this, a target encoder is initially trained in an encoder-decoder framework to associate visual features with semantic words.
no code implementations • 27 Dec 2020 • Chang-Hwan Son
For the detail layer, a new structure-aware residual deblurring subnetwork (SARDS) is presented.
1 code implementation • 2 May 2019 • Chang-Hwan Son
The subnetwork for the image structure prediction is trained using the mini-batch gradient descent algorithm given the halftoned patches and gradient patches, which are fed into the input and loss layers of the subnetwork, respectively.
no code implementations • 25 Mar 2019 • Hee-Jin Yu, Chang-Hwan Son
The two subnetworks exhibit the architecture types of an encoder-decoder network and VGG network, respectively; subsequently, they are trained separately through transfer learning with a new training set containing class information, according to the types of leaf diseases and the ground truth images where the background, leaf area, and spot area are separated.
no code implementations • 22 Jan 2017 • Chang-Hwan Son, Xiao-Ping Zhang
Different from conventional fusion approaches, the proposed method conducts a series of transfers: contrast, detail, and color transfers.
no code implementations • 3 Oct 2016 • Chang-Hwan Son, Xiao-Ping Zhang
This paper introduces a new coloring method to add colors to near-infrared gray images based on a contrast-preserving mapping model.
no code implementations • 3 Oct 2016 • Chang-Hwan Son, Xiao-Ping Zhang
Next, residual rain patches are selected randomly, and then added to the given target image along a raster scanning direction.
no code implementations • 3 Oct 2016 • Chang-Hwan Son, Xiao-Ping Zhang
Based on this error map, both the sparse codes of rain and non-rain dictionaries are used jointly to represent the image structures of objects and avoid the edge artifacts in the non-rain regions.
no code implementations • 1 Oct 2016 • Chang-Hwan Son, Xiao-Ping Zhang
It is also shown that the proposed color regularization can remove the edge artifacts which arise from the use of the conventional dark prior model.