scholarly journals Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software

2020 ◽  
Vol 34 (07) ◽  
pp. 11296-11303 ◽  
Author(s):  
Satoshi Kosugi ◽  
Toshihiko Yamasaki
Keyword(s):  
Reinforcement Learning ◽  
Image Enhancement ◽  
High Performance ◽  
State Of The Art ◽  
Mapping Function ◽  
Generative Adversarial Networks ◽  
Image Editing ◽  
Learning Framework ◽  
Adversarial Networks ◽  
Image Pairs

This paper tackles unpaired image enhancement, a task of learning a mapping function which transforms input images into enhanced images in the absence of input-output image pairs. Our method is based on generative adversarial networks (GANs), but instead of simply generating images with a neural network, we enhance images utilizing image editing software such as Adobe® Photoshop® for the following three benefits: enhanced images have no artifacts, the same enhancement can be applied to larger images, and the enhancement is interpretable. To incorporate image editing software into a GAN, we propose a reinforcement learning framework where the generator works as the agent that selects the software's parameters and is rewarded when it fools the discriminator. Our framework can use high-quality non-differentiable filters present in image editing software, which enables image enhancement with high performance. We apply the proposed method to two unpaired image enhancement tasks: photo enhancement and face beautification. Our experimental results demonstrate that the proposed method achieves better performance, compared to the performances of the state-of-the-art methods based on unpaired learning.

scholarly journals Deep Fake Image Detection Based on Pairwise Learning

2020 ◽  
Vol 10 (1) ◽  
pp. 370 ◽  
Author(s):  
Chih-Chung Hsu ◽  
Yi-Xiu Zhuang ◽  
Chia-Yen Lee
Keyword(s):  
State Of The Art ◽  
Random Noise ◽  
Input Image ◽  
Generative Adversarial Networks ◽  
Source Image ◽  
Image Forgery ◽  
Social Media Networks ◽  
Adversarial Networks ◽  
Pairwise Learning ◽  
Image Pairs

Generative adversarial networks (GANs) can be used to generate a photo-realistic image from a low-dimension random noise. Such a synthesized (fake) image with inappropriate content can be used on social media networks, which can cause severe problems. With the aim to successfully detect fake images, an effective and efficient image forgery detector is necessary. However, conventional image forgery detectors fail to recognize fake images generated by the GAN-based generator since these images are generated and manipulated from the source image. Therefore, in this paper, we propose a deep learning-based approach for detecting the fake images by using the contrastive loss. First, several state-of-the-art GANs are employed to generate the fake–real image pairs. Next, the reduced DenseNet is developed to a two-streamed network structure to allow pairwise information as the input. Then, the proposed common fake feature network is trained using the pairwise learning to distinguish the features between the fake and real images. Finally, a classification layer is concatenated to the proposed common fake feature network to detect whether the input image is fake or real. The experimental results demonstrated that the proposed method significantly outperformed other state-of-the-art fake image detectors.

scholarly journals A New Strategy for One-Example Person re-ID: Exploit the Unlabeled Data Gradually Base on Style-Transferred Images

Symmetry ◽  
2020 ◽  
Vol 12 (5) ◽  
pp. 689
Author(s):  
Qiang Li ◽  
Ling Gao
Keyword(s):  
Computer Vision ◽  
State Of The Art ◽  
Recognition Rate ◽  
Research Field ◽  
Generative Adversarial Networks ◽  
Learning Framework ◽  
Adversarial Networks ◽  
New Strategy ◽  
Labeling Scheme ◽  
Self Learning

As a research field of symmetry journals, computer vision has received more and more attention. Person re-identification (re-ID) has become a research hotspot in computer vision. We focus on one-example person re-ID, where each person only has one labeled image in the dataset, and other images are unlabeled. There are two main challenges of the task, the insufficient labeled data, and the lack of labeled images cross-cameras. In dealing with the above issue, we propose a new one-example labeling scheme, which generates style-transferred images by CycleGAN (Cycle Generative Adversarial Networks) to ensure that for each person, there is one labeled image under each camera style. Then a self-learning framework is adopted, which iteratively train a CNN (Convolutional Neural Networks) model with labeled images and labeled style-transferred images, and mine the reliable images to assign a pseudo label. The experimental results prove that by integrating the camera style transferred images, we effectively expand the dataset, and the problem of low recognition rate caused by the lack of labeled pedestrian pictures across cameras is effectively solved. Notably, the rank-1 accuracy of our method outperforms the state-of-the-art method by 8.7 points on the Market-1501 dataset, and 6.3 points on the DukeMTMC-ReID dataset.

scholarly journals Enhanced network optimized generative adversarial network for image enhancement

2021 ◽  
Author(s):  
Lingyu Yan ◽  
Jiarun Fu ◽  
Chunzhi Wang ◽  
Zhiwei Ye ◽  
Hongwei Chen ◽  
...  
Keyword(s):  
Image Enhancement ◽  
Image Recognition ◽  
Generative Adversarial Networks ◽  
Low Light ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Enhancement Method ◽  
New Space ◽  
Traditional Image

AbstractWith the development of image recognition technology, face, body shape, and other factors have been widely used as identification labels, which provide a lot of convenience for our daily life. However, image recognition has much higher requirements for image conditions than traditional identification methods like a password. Therefore, image enhancement plays an important role in the process of image analysis for images with noise, among which the image of low-light is the top priority of our research. In this paper, a low-light image enhancement method based on the enhanced network module optimized Generative Adversarial Networks(GAN) is proposed. The proposed method first applied the enhancement network to input the image into the generator to generate a similar image in the new space, Then constructed a loss function and minimized it to train the discriminator, which is used to compare the image generated by the generator with the real image. We implemented the proposed method on two image datasets (DPED, LOL), and compared it with both the traditional image enhancement method and the deep learning approach. Experiments showed that our proposed network enhanced images have higher PNSR and SSIM, the overall perception of relatively good quality, demonstrating the effectiveness of the method in the aspect of low illumination image enhancement.

scholarly journals Facial UV photo imaging for skin pigmentation assessment using conditional generative adversarial networks

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Kaname Kojima ◽  
Kosuke Shido ◽  
Gen Tamiya ◽  
Kenshi Yamasaki ◽  
Kengo Kinoshita ◽  
...  
Keyword(s):  
Skin Pigmentation ◽  
Generative Adversarial Networks ◽  
Pigment Spot ◽  
Detection Analysis ◽  
Adversarial Networks ◽  
Skin Cancers ◽  
Uv Photography ◽  
Highly Correlated ◽  
Image Pairs ◽  
Skin Damages

AbstractSkin pigmentation is associated with skin damages and skin cancers, and ultraviolet (UV) photography is used as a minimally invasive mean for the assessment of pigmentation. Since UV photography equipment is not usually available in general practice, technologies emphasizing pigmentation in color photo images are desired for daily care. We propose a new method using conditional generative adversarial networks, named UV-photo Net, to generate synthetic UV images from color photo images. Evaluations using color and UV photo image pairs taken by a UV photography system demonstrated that pigment spots were well reproduced in synthetic UV images by UV-photo Net, and some of the reproduced pigment spots were difficult to be recognized in color photo images. In the pigment spot detection analysis, the rate of pigment spot areas in cheek regions for synthetic UV images was highly correlated with the rate for UV photo images (Pearson’s correlation coefficient 0.92). We also demonstrated that UV-photo Net was effective for floating up pigment spots for photo images taken by a smartphone camera. UV-photo Net enables an easy assessment of pigmentation from color photo images and will promote self-care of skin damages and early signs of skin cancers for preventive medicine.

scholarly journals Improving Skin Lesion Analysis with Generative Adversarial Networks

2020 ◽  
Author(s):  
Alceu Bissoto ◽  
Sandra Avila
Keyword(s):  
Skin Lesion ◽  
State Of The Art ◽  
Synthetic Data ◽  
Clinical Information ◽  
Analysis Data ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Classification Models ◽  
Adversarial Networks ◽  
Lesion Analysis

Melanoma is the most lethal type of skin cancer. Early diagnosis is crucial to increase the survival rate of those patients due to the possibility of metastasis. Automated skin lesion analysis can play an essential role by reaching people that do not have access to a specialist. However, since deep learning became the state-of-the-art for skin lesion analysis, data became a decisive factor in pushing the solutions further. The core objective of this M.Sc. dissertation is to tackle the problems that arise by having limited datasets. In the first part, we use generative adversarial networks to generate synthetic data to augment our classification model’s training datasets to boost performance. Our method generates high-resolution clinically-meaningful skin lesion images, that when compound our classification model’s training dataset, consistently improved the performance in different scenarios, for distinct datasets. We also investigate how our classification models perceived the synthetic samples and how they can aid the model’s generalization. Finally, we investigate a problem that usually arises by having few, relatively small datasets that are thoroughly re-used in the literature: bias. For this, we designed experiments to study how our models’ use data, verifying how it exploits correct (based on medical algorithms), and spurious (based on artifacts introduced during image acquisition) correlations. Disturbingly, even in the absence of any clinical information regarding the lesion being diagnosed, our classification models presented much better performance than chance (even competing with specialists benchmarks), highly suggesting inflated performances.

Sign in / Sign up

Export Citation Format

Share Document