scholarly journals Anti-Forensics of Image Contrast Enhancement Based on Generative Adversarial Network

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Hao Zou ◽  
Pengpeng Yang ◽  
Rongrong Ni ◽  
Yao Zhao
Keyword(s):  
Contrast Enhancement ◽  
Enhancement Effect ◽  
Multimedia Forensics ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Visual Enhancement ◽  
Contrast Enhanced ◽  
Image Contrast Enhancement ◽  
Pixel Value ◽  
Value Changes

In the multimedia forensics community, anti-forensics of contrast enhancement (CE) in digital images is an important topic to understand the vulnerability of the corresponding CE forensic method. Some traditional CE anti-forensic methods have demonstrated their effective forging ability to erase forensic fingerprints of the contrast-enhanced image in histogram and even gray level cooccurrence matrix (GLCM), while they ignore the problem that their ways of pixel value changes can expose them in the pixel domain. In this paper, we focus on the study of CE anti-forensics based on Generative Adversarial Network (GAN) to handle the problem mentioned above. Firstly, we exploit GAN to process the contrast-enhanced image and make it indistinguishable from the unaltered one in the pixel domain. Secondly, we introduce a specially designed histogram-based loss to enhance the attack effectiveness in the histogram domain and the GLCM domain. Thirdly, we use a pixel-wise loss to keep the visual enhancement effect of the processed image. The experimental results show that our method achieves high anti-forensic attack performance against CE detectors in the pixel domain, the histogram domain, and the GLCM domain, respectively, and maintains the highest image quality compared with traditional CE anti-forensic methods.

scholarly journals Fast contrast enhancement by adaptive pixel value stretching

2018 ◽  
Vol 14 (8) ◽  
pp. 155014771879380
Author(s):  
Gang Cao ◽  
Huawei Tian ◽  
Lifang Yu ◽  
Xianglin Huang
Keyword(s):  
Contrast Enhancement ◽  
Dynamic Range ◽  
Computational Cost ◽  
Computer Applications ◽  
Visual Sensor ◽  
Visual Sensor Network ◽  
Image Contrast Enhancement ◽  
Quantitative Performance ◽  
Pixel Value ◽  
Adaptive Gamma Correction

In this article, we propose a fast and effective method for digital image contrast enhancement. The gray-level dynamic range of contrast-distorted images is extended maximally via adaptive pixel value stretching. The quantity of saturated pixels is set intelligently according to the perceptual brightness of global images. Adaptive gamma correction is also novelly used to recover the normal luminance in enhancing dimmed images. Different from prior methods, our proposed technique could be enforced automatically without complex manual parameter adjustment per image. Both qualitative and quantitative performance evaluation results show that, comparing with some recent influential contrast enhancement techniques, our proposed method achieves comparative or better enhancement quality at a surprisingly lower computational cost. Besides general computer applications, such merit should also be valuable in low-power scenarios, such as the imaging pipelines used in small mobile terminals and visual sensor network.

Unsupervised fabric defect detection based on a deep convolutional generative adversarial network

2019 ◽  
Vol 90 (3-4) ◽  
pp. 247-270 ◽  
Author(s):  
Guanghua Hu ◽  
Junfeng Huang ◽  
Qinghui Wang ◽  
Jingrong Li ◽  
Zhijia Xu ◽  
...  
Keyword(s):  
Defect Detection ◽  
Surface Defects ◽  
Generative Adversarial Network ◽  
Query Image ◽  
Training Strategy ◽  
Fabric Defect Detection ◽  
Adversarial Network ◽  
Fabric Defect ◽  
Pixel Value ◽  
Textured Materials

Detecting and locating surface defects in textured materials is a crucial but challenging problem due to factors such as texture variations and lack of adequate defective samples prior to testing. In this paper we present a novel unsupervised method for automatically detecting defects in fabrics based on a deep convolutional generative adversarial network (DCGAN). The proposed method extends the standard DCGAN, which consists of a discriminator and a generator, by introducing a new encoder component. With the assistance of this encoder, our model can reconstruct a given query image such that no defects but only normal textures will be preserved in the reconstruction. Therefore, when subtracting the reconstruction from the original image, a residual map can be created to highlight potential defective regions. Besides, our model generates a likelihood map for the image under inspection where each pixel value indicates the probability of occurrence of defects at that location. The residual map and the likelihood map are then synthesized together to form an enhanced fusion map. Typically, the fusion map exhibits uniform gray levels over defect-free regions but distinct deviations over defective areas, which can be further thresholded to produce a binarized segmentation result. Our model can be unsupervisedly trained by feeding with a set of small-sized image patches picked from a few defect-free examples. The training is divided into several successively performed stages, each under an individual training strategy. The performance of the proposed method has been extensively evaluated by a variety of real fabric samples. The experimental results in comparison with other methods demonstrate its effectiveness in fabric defect detection.

scholarly journals Segmentation Techniques for Brain Tumor from MRI – A Survey

2020 ◽  
Author(s):  
Jeevitha R ◽  
Selvaraj D
Keyword(s):  
Brain Tumor ◽  
Medical Science ◽  
Radio Waves ◽  
Mri Scan ◽  
Generative Adversarial Network ◽  
Usual Procedure ◽  
Adversarial Network ◽  
Contrast Enhanced ◽  
Pros And Cons ◽  
Magnetic Resonance Imaging Mri

In the medical science, Biomedical images are the core. Generally, Magnetic Resonance Imaging(MRI) scan is the most usual procedure followed. Radio waves and strong magnetic flux were used to determine comprehensive images of tissues and organs inside the body. The enhancement in MRI scan has become a large milestone in the medical world. Generally, the brain is segmented into White and gray matter, and cerebrospinal fluid(CSF). Various segmentation techniques have been proposed with promising results. Still, they all have their own pros and cons. Deep neural networks(DNN) have established good performance in segmentation and classification task via Deep Wavelet Autoencoder(DWA). In this study, by using a pairwise Generative Adversarial Network(GAN) model, it addresses the problems in brain tumor detection using MRI from various scanner modalities T1 weighted, T2 weighted, T1 weighted with contrast-enhanced and FLAIR images.

FMAGAN:Fusing multiple attention and generative adversarial network to enhance underwater image

2021 ◽  
pp. 1-13
Author(s):  
Long Hou ◽  
Long Yu ◽  
Shengwei Tian ◽  
Yanhan Zhang
Keyword(s):  
Loss Function ◽  
Hot Spot ◽  
Enhancement Effect ◽  
Generative Adversarial Network ◽  
Qualitative And Quantitative ◽  
Adversarial Network ◽  
Underwater Environment ◽  
Underwater Image ◽  
Underwater Vision ◽  
Proposed Model

Underwater image enhancement has always been a hot spot in underwater vision research. However, due to complicated underwater environment, a lot of problems such as the color distortion and low brightness of underwater raw images are very likely to occur. In response to the above situation, we proposed a generative adversarial network that integrated multiple attention to enhance underwater images. In the generator, we introduced multi-layer dense connections and CSAM modules, of which the former could capture more detailed features and make use of previous features, while the latter could improve the utilization of the feature map. Meanwhile, we improved the enhancement effect of the generated image by combining VGG19 content loss function and SmoothL1 loss function. Finally, we verified the effectiveness of the proposed model through qualitative and quantitative experiments, and compared the results with the performance of several latest models. The results show that the methods proposed in this paper are superior to the existing methods.

Positive correlation between neovascularization degree of carotid atherosclerosis determined by contrast-enhanced ultrasound and level of serum C-reactive protein

VASA ◽  
2015 ◽  
Vol 44 (3) ◽  
pp. 0187-0194 ◽  
Author(s):  
Xiaoni Chang ◽  
Jun Feng ◽  
Litao Ruan ◽  
Jing Shang ◽  
Yanqiu Yang ◽  
...  
Keyword(s):  
Contrast Enhancement ◽  
Rank Correlation ◽  
Artery Stenosis ◽  
Contrast Enhanced Ultrasound ◽  
C Reactive Protein ◽  
Protein Levels ◽  
Reactive Protein ◽  
Contrast Enhanced ◽  
Grade 3 ◽  
Axis View

Background: Neovascularization is one of the most important risk factors for unstable plaque. This study was designed to correlate plaque thickness, artery stenosis and levels of serum C-reactive protein with the degree of intraplaque enhancement determined by contrast-enhanced ultrasound. Patients and methods: Contrast-enhanced ultrasound was performed on 72 carotid atherosclerotic plaques in 48 patients. Contrast enhancement within the plaque was categorized as grade 1, 2 or 3. Maximum plaque thickness was measured in short-axis view. Carotid artery stenosis was categorized as mild, moderate or severe. Results: Plaque contrast enhancement was not associated with the degree of artery stenosis or with plaque thickness. Serum C-reactive protein levels were positively correlated with the number of new vessels in the plaque. C-reactive protein levels increased in the three groups(Grade 1: 3.72±1.79mg/L; Grade 2: 7.88±4.24 mg/L; Grade 3: 11.02±3.52 mg/L), with significant differences among them (F=10.14, P<0.01), and significant differences between each two groups (P<0.05). Spearman’s rank correlation analysis showed that serum C-reactive protein levels were positively correlated with the degree of carotid plaque enhancement (Rs =0.69, P<0.01). Conclusions: The combination of C-reactive protein levels and intraplaque neovascularization detected by contrast-enhanced ultrasound may allow more accurate evaluation of plaque stability.

Sign in / Sign up

Export Citation Format

Share Document