Reverse image filtering with clean and noisy filters

Wang, Lizhong; Fayolle, Pierre-Alain; Belyaev, Alexander

doi:10.1007/s11760-022-02236-w

Cited by 13 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this step, the pre-processing of clothing dataset images by using Reverse Image Filtering (RIF) [29] is proposed. The objective of reverse image filtering, given an image filter, is to eliminate or suppress the filter effects using simply the filter.…”

Section: B Pre-processing Using Reverse Image Filteringmentioning

confidence: 99%

Clothing Design Style Recommendation Using Optimized Semantic-Preserved Generative Adversarial Network

Guannan Yang

2024

jes

View full text Add to dashboard Cite

Recommendations for clothing design styles provide a tailored and efficient buying experience, decreasing consumers' decision fatigue and boosting interest. There are a number of obstacles to implementing clothing design style recommendations, including the requirement for diverse and accurate data to train efficient algorithms, the possibility of biases in recommendation systems, the complexity of comprehending subtle customer preferences, and the ever-changing nature of fashion trends. To overcome this complication, Clothing Design Style Recommendation Using Optimized Semantic-Preserved Generative Adversarial Network (ICMA-SPGAN-SFOA-CD) are proposed. Initially, the images collected from the clothing dataset are given as input. Afterward, the data are fed to pre-processing. In pre-processing, Reverse Image Filter (RIF) is used for redundant of data and noise removal. The pre-processing output is fed to Pyramidal Convolution Shuffle Attention Neural Network (PCSANN) for clothing design style recommendation. The recommended clothing design style was given for classification using Semantic-Preserved Generative Adversarial Network (SPGAN) optimized with Sheep Flock Optimization Algorithm (SFOA)for classifying clothing design style as Basic clothing, Looseness Season for clothing, Collar type, Colour and Advanced clothing . MATLAB is used to implement the proposed ICMA-SPGAN-SFOA-CD method. The performance of the proposed ICMA-SPGAN-SFOA-CD approach attains 25%, 21.5%, and 22.5% high precision,25.3%, 27.5%, and 21.8% high recall and 27.6%, 24.8%, and 23.2% high F1-Scorecompared with existing methods such as RCNN Framework Using L-Softmax Loss (CAR-RCNN-LSL) ,Clothing Attribute Recognition Based on Clothing fashion style recognition with design issue graph (CFSR-DCNN-DIG), Personalized Smart Clothing Design Based on Multimodal Visual Data Detection (PSCD-DNN-MVDD) models respectively.

show abstract

Section: B Pre-processing Using Reverse Image Filteringmentioning

confidence: 99%

Clothing Design Style Recommendation Using Optimized Semantic-Preserved Generative Adversarial Network

Guannan Yang

2024

jes

View full text Add to dashboard Cite

show abstract

“…Luo et al [14] used the SRM filter to guide the RGB features. Wang et al [40] proposed to use modified Landweber iterations for reverse image filtering. Jia et al [18] proposed a novel adversarial attack method based on meta-learning to generate perturbations in the frequency domain.…”

Section: Frequency-based Forgery Detectionmentioning

confidence: 99%

An Attention-Erasing Stripe Pyramid Network for Face Forgery Detection

Duan

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

ace forgery detection aims to distinguish between real and fake facial images or videos by identifying manipulated or forged visual media. The main challenge in face forgery detection is achieving high model generalization ability, i.e., satisfactory performance under cross-database scenarios where the training and testing datasets are from different forgery methods. To achieve this goal, this paper presents an Attention-Erasing Stripe Pyramid Network (ASPNet) to utilize high-frequency noises and exploit both the RGB and fine-grained frequency clues. First, since separately extracting features from different scales and granularities will ignore their complementarity, we employ a Stripe Pyramid Block (SPB) to learn multi-scale and multi-granularity features simultaneously. Second, to make the model to focus on useful information and suppress noise, a Two-Stage Attention Block (TSAB) is introduced by combining spatial attention and channel attention to filter out the pixel-wise and channel-wise noise in the learned feature maps. Finally, to dynamically guide the model to pay attention to different areas of the human face, an Attention Erasing (AE) scheme is adopted by randomly erasing units in attention maps. Sufficient experiments demonstrate that ASPNet has superior performance than F3-Net on the FaceForensics++ dataset. The Area Under the Receiver Operating Characteristic Curve (AUC) and the Accuracy (ACC) of our model reach 77.4% and 70.85% respectively, whichare improved by 0.83% and 1.28% compared with F3-Net. Our code is available at: https://github.com/NWPU-Zwu.

show abstract

“…These filters are aimed to effectively suppress noise while preserving important image details, ultimately improving the overall image quality. The author [4] introduced a modified Landweber iteration-based reverse image filtering method and showed superior performance in image deblurring and super-resolution tasks, offering robustness to noise as compared to existing reverse image filtering methods. Dmytro et al [5] addressed the limitations of conventional filtering methods in image processing software and proposed a model of additive impulse noise and least finite differences (MLFD) method for image filtering, along with an interactive web service for its implementation.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Gaussian Wiener Filter for CT-Scan Images with Gaussian Noise Variance

Lew,

Kew,

Sim

et al. 2024

JIWE

View full text Add to dashboard Cite

Medical imaging plays an important role in modern healthcare, with Computed Tomography (CT) being essential for high-resolution cross-sectional imaging. However, Gaussian noise often occurs within the CT scan images and makes it difficult for image interpretation and reduces the diagnostic accuracy, creating a significant obstacle to fully utilizing CT scanning technology. Existing denoising techniques have a hard time balance between noise reduction and preserving the important image details, failing to enable the optimal diagnostic precision. This study introduces Adaptive Gaussian Wiener Filter (AGWF), a novel filter aims to denoise CT scan images that have been corrupted with various Gaussian noise variance without compromising the image details. The AGWF combines the Gaussian filter for initial noise reduction, followed by the implementation of Wiener filter, which can adaptively estimate noise variance and signal power in localized regions. This approach not only outperforms other existing techniques but also showcases a remarkable balance between noise reduction and image detail preservation. The experiment evaluates 300 images from the dataset and each image is corrupted with Gaussian noise variance to ensure a comprehensive evaluation of the AGWF’s performance. The evaluation indicated that AGWF can improve the Signal-to-Noise Ratio (SNR) value and reduce the Root Mean Square Error (RMSE) and Mean Square Error (MSE) value, showing a qualitative improvement in CT scan imagery. The proposed method holds promising potential for advancing medical imaging technology with the implementation of deep learning.

show abstract

Reverse image filtering with clean and noisy filters

Abstract: Given an image filter $${{\varvec{y}}}={{\varvec{f}}}\,({{\varvec{x}}})$$ y = f ( x ) , where $${{\varvec{x}}}$$ x and $${{\varvec{y}}}$$ … Show more

Cited by 13 publications

References 32 publications

Clothing Design Style Recommendation Using Optimized Semantic-Preserved Generative Adversarial Network

Clothing Design Style Recommendation Using Optimized Semantic-Preserved Generative Adversarial Network

An Attention-Erasing Stripe Pyramid Network for Face Forgery Detection

Adaptive Gaussian Wiener Filter for CT-Scan Images with Gaussian Noise Variance

Contact Info

Product

Resources

About