Enhanced Single Image Super Resolution Method Using Lightweight Multi-Scale Channel Dense Network

Lee, Yooho; Jun, Dongsan; Kim, Byung-Gyu; Lee, Hunjoo

doi:10.3390/s21103351

Cited by 10 publications

(8 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These networking models disrupt the transitional characteristics in the image classification, and push the related characteristics to cause perception loss. This model does not preserve quantitative consistency when treated with naturalness but achieves perceptive gains over the other models [23,25]. The job is then to upgrade pictures with high-resolution ground-truth photographs so that the upscaling methods can regularize the balance between both qualitative and quantitative consistency.…”

Section: Super-resolution Generative Adversarialmentioning

confidence: 99%

Deep Learning Methods on High- Resolution Image and Video – A Profound Assessment

2023

View full text Add to dashboard Cite

Conversion of law resolution images into high resolution is known as super resolution job. This is a very challenging job which is now years are performed by multiple deep learning approaches. In this article we discuss these deep learning approaches and compare their results. Apart from it we also discuss the different characteristics of super resolution approaches and compare these with the peak signal noise ratio and SSIM measurements. Several deep learning approaches or algorithms are discussed.

show abstract

Section: Super-resolution Generative Adversarialmentioning

confidence: 99%

Deep Learning Methods on High- Resolution Image and Video – A Profound Assessment

2023

View full text Add to dashboard Cite

show abstract

“…SSFPN [11] utilizes scale-invariant features which are extracted by 3D CNN. Multi-scale objects can also be detected by a super resolution method [12].…”

Section: Deep Learning Object Detection Networkmentioning

confidence: 99%

Guidance for Visually Impaired Person through Braille Block Detection by Deep Learning

Lee¹,

Kim²,

Kwon³

2022

J Multimed Inf Syst

View full text Add to dashboard Cite

In this paper, we propose a passage guidance method for the visually impaired person through a braille block detection. The proposed method recognizes the passage information by detecting the braille blocks individually through a neural network based on a captured image. The braille blocks are detected through YOLOv7 which is a state-of-the-art object detection network. Then, the placements of the detected braille blocks are analyzed to find the groups of the straight blocks arranged in a single line and of the dot blocks gathered in a square shape. The passage information is recognized by comparing between the analyzed block placement and predefined placements. Objects in a sidewalk are detected together with the braille block to warn obstacles on the sidewalk. The passage information is guided in voice for the visually impaired person. In simulation results, the proposed method recognized the passage information with about 85% accuracy.

show abstract

“…Moreover, artificial intelligence (AI) technology based on deep learning has been rapidly advanced and widely applied along with machine vision in the fishing industry [14][15]. Particularly, AI combined with machine vision brings powerful synergy effects [16][17][18][19][20][21][22]. Since AI machine vision exhibits exceptional performance, it is expected that this technology will be effectively applied in various industries including the fishing industry.…”

Section: Introductionmentioning

confidence: 99%

Machine Vision Based Fish Cutting Point Prediction for Target Weight

Jang¹,

Seo²

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Food processing companies pursue the distribution of ingredients that were packaged according to a certain weight. Particularly, foods like fish are highly demanded and supplied. However, despite the high quantity of fish to be supplied, most seafood processing companies have yet to install automation equipment. Such absence of automation equipment for seafood processing incurs a considerable cost regarding labor force, economy, and time. Moreover, workers responsible for fish processing are exposed to risks because fish processing tasks require the use of dangerous tools, such as power saws or knives. To solve these problems observed in the fish processing field, this study proposed a fish cutting point prediction method based on AI machine vision and target weight. The proposed method performs threedimensional (3D) modeling of a fish's form based on image processing techniques and partitioned random sample consensus (RANSAC) and extracts 3D feature information. Then, it generates a neural network model for predicting fish cutting points according to the target weight by performing machine learning of the extracted 3D feature information and measured weight information. This study allows for the direct cutting of fish based on cutting points predicted by the proposed method. Subsequently, we compared the measured weight of the cut pieces with the target weight. The comparison result verified that the proposed method showed a mean error rate of approximately 3%.

show abstract

Enhanced Single Image Super Resolution Method Using Lightweight Multi-Scale Channel Dense Network

Cited by 10 publications

References 40 publications

Deep Learning Methods on High- Resolution Image and Video – A Profound Assessment

Deep Learning Methods on High- Resolution Image and Video – A Profound Assessment

Guidance for Visually Impaired Person through Braille Block Detection by Deep Learning

Machine Vision Based Fish Cutting Point Prediction for Target Weight

Contact Info

Product

Resources

About