An Effective and Efficient Dehazing Method of Single Input Image

2018 ◽  
pp. 596-604
Author(s):  
Fu-Qiang Han ◽  
Zhan-Li Sun ◽  
Ya-Min Wang
Keyword(s):  
Input Image ◽  
Single Input

scholarly journals Unsupervised Learning from Videos for Object Discovery in Single Images

Symmetry ◽  
2020 ◽  
Vol 13 (1) ◽  
pp. 38
Author(s):  
Dong Zhao ◽  
Baoqing Ding ◽  
Yulin Wu ◽  
Lei Chen ◽  
Hongchao Zhou
Keyword(s):  
Input Image ◽  
Frame Structure ◽  
Object Discovery ◽  
Spatial Transformations ◽  
Learning Tasks ◽  
Video Frames ◽  
Segmentation Methods ◽  
Feed Forward Network ◽  
Single Input ◽  
Inter Frame

This paper proposes a method for discovering the primary objects in single images by learning from videos in a purely unsupervised manner—the learning process is based on videos, but the generated network is able to discover objects from a single input image. The rough idea is that an image typically consists of multiple object instances (like the foreground and background) that have spatial transformations across video frames and they can be sparsely represented. By exploring the sparsity representation of a video with a neural network, one may learn the features of each object instance without any labels, which can be used to discover, recognize, or distinguish object instances from a single image. In this paper, we consider a relatively simple scenario, where each image roughly consists of a foreground and a background. Our proposed method is based on encoder-decoder structures to sparsely represent the foreground, background, and segmentation mask, which further reconstruct the original images. We apply the feed-forward network trained from videos for object discovery in single images, which is different from the previous co-segmentation methods that require videos or collections of images as the input for inference. The experimental results on various object segmentation benchmarks demonstrate that the proposed method extracts primary objects accurately and robustly, which suggests that unsupervised image learning tasks can benefit from the sparsity of images and the inter-frame structure of videos.

scholarly journals Face Recognition in SSPP Problem Using Face Relighting Based on Coupled Bilinear Model

Sensors ◽  
2018 ◽  
Vol 19 (1) ◽  
pp. 43 ◽  
Author(s):  
Sang-Il Choi ◽  
Yonggeol Lee ◽  
Minsik Lee
Keyword(s):  
Face Recognition ◽  
Feature Space ◽  
Training Image ◽  
Poor Quality ◽  
Input Image ◽  
Bilinear Model ◽  
Proposed Model ◽  
Virtual Images ◽  
Single Input

There have been decades of research on face recognition, and the performance of many state-of-the-art face recognition algorithms under well-conditioned environments has become saturated. Accordingly, recent research efforts have focused on difficult but practical challenges. One such issue is the single sample per person (SSPP) problem, i.e., the case where only one training image of each person. While this problem is challenging because it is difficult to establish the within-class variation, working toward its solution is very practical because often only a few images of a person are available. To address the SSPP problem, we propose an efficient coupled bilinear model that generates virtual images under various illuminations using a single input image. The proposed model is inspired by the knowledge that the illuminance of an image is not sensitive to the poor quality of a subspace-based model, and it has a strong correlation to the image itself. Accordingly, a coupled bilinear model was constructed that retrieves the illuminance information from an input image. This information is then combined with the input image to estimate the texture information, from which we can generate virtual illumination conditions. The proposed method can instantly generate numerous virtual images of good quality, and these images can then be utilized to train the feature space for resolving SSPP problems. Experimental results show that the proposed method outperforms the existing algorithms.

Haze Removal for a Single Image Using Adaptive Template Dark Channel Prior

2014 ◽  
Vol 543-547 ◽  
pp. 2480-2483
Author(s):  
Jing Zhang ◽  
Wei Dong ◽  
Juan Li ◽  
Xu Ning Liu
Keyword(s):  
Input Image ◽  
Dark Channel Prior ◽  
Edge Region ◽  
Single Image ◽  
Haze Removal ◽  
Flat Region ◽  
Imaging Model ◽  
Texture Region ◽  
Dark Channel ◽  
Single Input

In this paper, we propose an adaptive template method based on the dark channel prior. The method combines with the haze imaging model to haze removal for a single image. This method can effectively remove haze from a single input image. According to the characteristics of the image itself and the haze removal effect of the different template we divide the input image into flat region, edge region and texture region. Then, select the lager size template dispose the flat region and use midrange or minitype template dispose the edge region and texture area. Experimental results demonstrate that the proposed algorithm has very good performance for fog removal and retains the image details more effectively.

scholarly journals Image Dehazing Technique Based On DWT Decomposition and Intensity Retinex Algorithm

2019 ◽  
pp. 116-122
Author(s):  
Sunita Shukla ◽  
Silky Pareyani
Keyword(s):  
Median Filter ◽  
Weather Conditions ◽  
Input Image ◽  
Single Image ◽  
Distance Information ◽  
Haze Removal ◽  
Imaging Model ◽  
Single Input ◽  
Adjacent Pixel ◽  
Different Depths

Conventional designs use multiple image or single image to deal with haze removal. The presented paper uses median filer with modified co-efficient (16 adjacent pixel median) and estimate the transmission map and remove haze from a single input image. The median filter prior(co-efficient) is developed based on the idea that the outdoor visibility of images taken under hazy weather conditions seriously reduced when the distance increases. The thickness of the haze can be estimated effectively and a haze-free image can be recovered by adopting the median filter prior and the new haze imaging model. Our method is stable to image local regions containing objects in different depths. Our experiments showed that the proposed method achieved better results than several state-of-the-art methods, and it can be implemented very quickly. Our method due to its fast speed and the good visual effect is suitable for real-time applications. This work confirms that estimating the transmission map using the distance information instead the color information is a crucial point in image enhancement and especially single image haze removal.

scholarly journals MONOCULAR-DEPTH ASSISTED SEMI-GLOBAL MATCHING

2019 ◽  
Vol IV-2/W7 ◽  
pp. 55-62
Author(s):  
M. Hödel ◽  
T. Koch ◽  
L. Hoegner ◽  
U. Stilla
Keyword(s):  
A Priori ◽  
Depth Estimation ◽  
Point Clouds ◽  
Input Image ◽  
Depth Image ◽  
Dense Matching ◽  
Global Matching ◽  
Single Input ◽  
Monocular Depth ◽  
Image Pairs

<p><strong>Abstract.</strong> Reconstruction of dense photogrammetric point clouds is often based on depth estimation of rectified image pairs by means of pixel-wise matching. The main drawback lies in the high computational complexity compared to that of the relatively straightforward task of laser triangulation. Dense image matching needs oriented and rectified images and looks for point correspondences between them. The search for these correspondences is based on two assumptions: pixels and their local neighborhood show a similar radiometry and image scenes are mostly homogeneous, meaning that neighboring points in one image are most likely also neighbors in the second. These rules are violated, however, at depth changes in the scene. Optimization strategies tend to find the best depth estimation based on the resulting disparities in the two images. One new field in neural networks is the estimation of a depth image from a single input image through learning geometric relations in images. These networks are able to find homogeneous areas as well as depth changes, but result in a much lower geometric accuracy of the estimated depth compared to dense matching strategies. In this paper, a method is proposed extending the Semi-Global-Matching algorithm by utilizing a-priori knowledge from a monocular depth estimating neural network to improve the point correspondence search by predicting the disparity range from the single-image depth estimation (SIDE). The method also saves resources through path optimization and parallelization. The algorithm is benchmarked on Middlebury data and results are presented both quantitatively and qualitatively.</p>

scholarly journals Ghost-Free High Dynamic Range Imaging Using Histogram Separation and Edge Preserving Denoising

2014 ◽  
Vol 12 (3) ◽  
pp. 3329-3337
Author(s):  
Ramratan Ahirwal ◽  
Yogesh Singh Rajput ◽  
Dr. Yogendra Kumar Jain
Keyword(s):  
Dynamic Range ◽  
Dynamic Environment ◽  
High Dynamic Range ◽  
Input Image ◽  
High Dynamic Range Imaging ◽  
Range Imaging ◽  
Edge Preserving ◽  
Software Application ◽  
Single Input ◽  
High Dynamic

In this paper, we introduce a ghost-free High Dynamic Range imaging algorithm for obtaining ghost-free high dynamicrange (HDR) images. The multiple image fusion based HDR method work only on condition that there is no movement ofcamera and object when capturing multiple, differently exposed low dynamic range (LDR) images. The proposed algorithmmakes three LDR images from a single input image to remove such an unrealistic condition. For this purpose a histogramseparation method is proposed in the algorithm for generating three LDR images by stretching each separated histogram.An edge-preserving denoising technique is also proposed in the algorithm to suppress the noise that is amplified in thestretching process. In the proposed algorithm final HDR image free from ghost artifacts in dynamic environment because itself-generates three LDR images from a single input image. Therefore, the proposed algorithm can be use in mobilephone camera and a consumer compact camera to provide the ghost artifacts free HDR images in the form of either inbuiltor post-processing software application.

A Modified Haze Removal Algorithm Using Dark Channel Prior

2012 ◽  
Vol 457-458 ◽  
pp. 1397-1402
Author(s):  
Xiao Tian Wu ◽  
Xing Hao Ding ◽  
Quan Xiao
Keyword(s):  
Adaptive Algorithm ◽  
Bilateral Filter ◽  
Input Image ◽  
Dark Channel Prior ◽  
Edge Preserving ◽  
Haze Removal ◽  
Dark Channel ◽  
Color Shift ◽  
Single Input ◽  
Channel Image

In this paper, we propose a new algorithm to remove haze from a single input image. Based on the Dark Channel Prior proposed by He [1], we exploit the Gauss Bilateral Filter and the min operation to obtain an edge-preserving dark channel image, which is non-iterative, requires less time. We further utilize this dark channel image to extract the estimation of medium transmission, and finally recover a haze-free image from that. Furthermore, we use a self-adaptive algorithm to set the haze parameters to solve the color shift problem for large sky region. Experiments demonstrate our algorithm can effectively remove haze from a foggy image while keep edges sharp.

Sign in / Sign up

Export Citation Format

Share Document