A Deep Learning Framework for Joint Image Restoration and Recognition

Chen, Ruilong; Mihaylova, Lyudmila; Zhu, Hao; Bouaynaya, Nidhal

doi:10.1007/s00034-019-01222-x

Cited by 16 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also put the photographs through their paces with occlusion, noise, and rotation, among other image degradation factors. Finally, the collaborative frameworks they propose aren't restricted to the application in question; they may be used for a range of image recognition/restoration jobs and could use several inner network architectures [10].…”

Section: Literature Surveymentioning

confidence: 99%

Image-based classification of healthy and diseased bell pepper using the transfer learning method

Dhanalakshmi¹,

Sivakumar

Kumari

et al. 2022

ijhs

View full text Add to dashboard Cite

The bell pepper is a fruit that is often misunderstood as a vegetable due to its usage. The plant which grows bell pepper grows for about three to six feet. These plants do not require intensive care but some necessary steps have to be taken to increase the productivity of the plant. Plant diseases like bacterial spots can heavily affect growth. The consequences of such diseases can be reduced if they’re detected in their early stages. This research aims the comparison of two Deep Learning (DL) models which were developed using VGG-16 architecture and the AlexNet. For training and testing the efficiency of the models, images of the bell pepper plant’s leaf are obtained from Kaggle. This data acquired further undergoes some pre-processing techniques like resizing and rescaling to reach the desired format. The cleaned data is then split into three divisions. One of them is used to train both DL models and the second one is used to validate the models. The last part is used to test the accuracy and loss of the two models. In the end, the accuracy and loss of both the models are compared and the results are tabulated.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Image-based classification of healthy and diseased bell pepper using the transfer learning method

Dhanalakshmi¹,

Sivakumar

Kumari

et al. 2022

ijhs

View full text Add to dashboard Cite

show abstract

“…Thus the proposed network is expected to reinforce a classification network by the information of degradation levels more directly. Chen et al [19] have proposed a network based on multi-task learning for the restoration and classification of degraded images. They have numerically shown that the performance of each task improves against single-task learning.…”

Section: Related Workmentioning

confidence: 99%

CNN-Based Classification of Degraded Images Without Sacrificing Clean Images

2021

View full text Add to dashboard Cite

Image classification needs to consider image degradations in practice because an image classification network trained with clean images works poorly for degraded images while digital images usually include some degradations such as JPEG compression. To tackle this problem, a common approach is training classification networks on degraded images with various levels of degradation, e.g. various quality factors for JPEG compression. However, the classification networks do not usually have enough accuracy for clean images because the classification networks have been averagely trained for various levels of degradation. This paper aims to construct a classification network of degraded images without sacrificing the performance of clean images. This paper proposes a network to learn the classification of degraded images and degradation levels of degraded images as multi-task learning. Learning the classification of degraded images is the main task of multi-task learning. On the other hand, learning degradation levels is a sub-task of multi-task learning and reinforces the classification ability. In the proposed network, a feature extractor of the classification is trained with image features acquired from a classification network of clean images by using consistency regularization with the cosine similarity loss. The experimental results using different types of degradations, including JPEG compression, Gaussian blur, Gaussian noise, and salt-and-pepper noise, show that our proposed network has enough ability to classify degraded images without sacrificing the performance for clean images.

show abstract

“…The median filter can almost completely eradicate it. The method of using [18] background information to repair and reconstruct deleted areas of an image is known as image inpainting.…”

Section: Introductionmentioning

confidence: 99%

Restoring Deteriorated Images using Deep Learning Techniques: Region Filling, Median Filter

Patil¹,

Ananya²,

Nayak³

et al. 2022

IJERCSE

View full text Add to dashboard Cite

Image restoration is a technique for recovering images from corrupted images that have blur and noise, lowering the image's quality. Motion blur, low resolution, moisture in the atmosphere, and other factors can all contribute to image noise. For noise removal, there are a variety of restoration techniques and a spatial domain filter. To eliminate blur and scratches in deteriorated photographs, an image restoration method has been developed. Deep learning has gained popularity as a method for image restoration during the last few years. Denoising and other image restoration operations are necessary steps in many image processing applications. Image fusion using the stacked median operator, low resolution detail improvement using guided super sampling, and repeated visual consistency assessment and refining are the three processes in the restoration process. Two VAEs (Variational Autoencoders) are trained in this model to translate old and clean pictures into two latent spaces, respectively. This is due to the fact that they are all using supervised learning, which is a difficulty created by the domain gap between the original image and the ones synthesized for training. The suggested project offers a cost-effective solution that can deal with noise, picture rotations, and occlusions.

show abstract

A Deep Learning Framework for Joint Image Restoration and Recognition

Cited by 16 publications

References 25 publications

Image-based classification of healthy and diseased bell pepper using the transfer learning method

Image-based classification of healthy and diseased bell pepper using the transfer learning method

CNN-Based Classification of Degraded Images Without Sacrificing Clean Images

Restoring Deteriorated Images using Deep Learning Techniques: Region Filling, Median Filter

Contact Info

Product

Resources

About