A fast single-image super-resolution via directional edge-guided regularized extreme learning regression

Sidike, Paheding; Krieger, Evan; Alom, Zahangir; Asari, Vijayan K.; Taha, Tarek M.

doi:10.1007/s11760-016-1045-8

Cited by 11 publications

(16 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among machine learning methods, Extreme Learning Machine (ELM; [31]), and its variants with different activation functions, have been successfully applied to a variety of research fields [32][33][34][35][36][37]. The activation function is the nonlinear transformation of the weighted input signals and bias [38].…”

Section: Introductionmentioning

confidence: 99%

Dual Activation Function-Based Extreme Learning Machine (ELM) for Estimating Grapevine Berry Yield and Quality

Maimaitiyiming

Sagan

Kwasniewski³

2019

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Reliable assessment of grapevine productivity is a destructive and time-consuming process. In addition, the mixed effects of grapevine water status and scion-rootstock interactions on grapevine productivity are not always linear. Despite the potential opportunity of applying remote sensing and machine learning techniques to predict plant traits, there are still limitations to previously studied techniques for vine productivity due to the complexity of the system not being adequately modeled. During the 2014 and 2015 growing seasons, hyperspectral reflectance spectra were collected using a handheld spectroradiometer in a vineyard designed to investigate the effects of irrigation level (0%, 50%, and 100%) and rootstocks (1103 Paulsen, 3309 Couderc, SO4 and Chambourcin) on vine productivity. To assess vine productivity, it is necessary to measure factors related to fruit ripeness and not just yield, as an over cropped vine may produce high-yield but poor-quality fruit. Therefore, yield, Total Soluble Solids (TSS), Titratable Acidity (TA) and the ratio TSS/TA (maturation index, IMAD) were measured. A total of 20 vegetation indices were calculated from hyperspectral data and used as input for predictive model calibration. Prediction performance of linear/nonlinear multiple regression methods and Weighted Regularized Extreme Learning Machine (WRELM) were compared with our newly developed WRELM-TanhRe. The developed method is based on two activation functions: hyperbolic tangent (Tanh) and rectified linear unit (ReLU). The results revealed that WRELM and WRELM-TanhRe outperformed the widely used multiple regression methods when model performance was tested with an independent validation dataset. WRELM-TanhRe produced the highest prediction accuracy for all the berry yield and quality parameters (R2 of 0.522–0.682 and RMSE of 2–15%), except for TA, which was predicted best with WRELM (R2 of 0.545 and RMSE of 6%). The results demonstrate the value of combining hyperspectral remote sensing and machine learning methods for improving of berry yield and quality prediction.

show abstract

Section: Introductionmentioning

confidence: 99%

Dual Activation Function-Based Extreme Learning Machine (ELM) for Estimating Grapevine Berry Yield and Quality

Maimaitiyiming

Sagan

Kwasniewski³

2019

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, neural networks have also 3 been explored to solve this problem, in various ways. Sidike et al [31] uses a neural network to learn a regressor that tries to follow edges. Zeng et al [46] proposes the use of coupled deep autoencoder (CDA) to learn both efficient representations for low and high resolution patches as well as a mapping function between them.…”

Section: A Approaches Using External Datamentioning

confidence: 99%

Single Image Super-Resolution Based on Wiener Filter in Similarity Domain

Cruz

Mehta

Katkovnik

et al. 2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Single image super-resolution (SISR) is an ill-posed problem aiming at estimating a plausible high-resolution (HR) image from a single low-resolution image. Current state-of-the-art SISR methods are patch-based. They use either external data or internal self-similarity to learn a prior for an HR image. External data-based methods utilize a large number of patches from the training data, while self-similarity-based approaches leverage one or more similar patches from the input image. In this paper, we propose a self-similarity-based approach that is able to use large groups of similar patches extracted from the input image to solve the SISR problem. We introduce a novel prior leading to the collaborative filtering of patch groups in a 1D similarity domain and couple it with an iterative back-projection framework. The performance of the proposed algorithm is evaluated on a number of SISR benchmark data sets. Without using any external data, the proposed approach outperforms the current non-convolutional neural network-based methods on the tested data sets for various scaling factors. On certain data sets, the gain is over 1 dB, when compared with the recent method A+. For high sampling rate (x4), the proposed method performs similarly to very recent state-of-the-art deep convolutional network-based approaches.

show abstract

“…Edge based insertion methods are developed with the goal of improving artifacts around margin. These methods employ directional edge intelligence to sustain edge sharpness in the HR image [12]. A comprehensive review of the state-of-the-art techniques for ALPR has been presented by Shan Du et al [7].…”

Section: Figure 2 Basic Block Diagram For License Plate Recognition mentioning

confidence: 99%

“…A machine learning-based approach to rebuild a high-resolution (HR) image from a single LR image has been presented by Paheding Sidike et al [12]. Inspired by the human visual cortex system, which is caring to high-frequency (HF) components in an image, the model is endeavored based on this concept by training a neural network to estimate the missing HF components that contain structural details.…”

Section: International Journal Of Computer Applications (0975 -8887) mentioning

confidence: 99%

A Survey on Detecting License Plates from Low Quality Images

Neeraja¹,

Rathi²

2018

IJCA

View full text Add to dashboard Cite

In real-time, identifying license plates from low quality images affected by multiple factors, such as severe brightness condition, tough background, distinct weather conditions, darkness, and appearance distortions is a difficult process. This paper gives a comparative analysis of different license plate detection (LPD) techniques in terms of their detection ratios. Super-resolution and enhancement techniques are discussed to overcome the problems faced by license plate recognition systems such as detecting license plates from blurred images. It is realized that image enhancement techniques are superior to image super-resolution techniques for improving low quality images.

show abstract

A fast single-image super-resolution via directional edge-guided regularized extreme learning regression

Cited by 11 publications

References 39 publications

Dual Activation Function-Based Extreme Learning Machine (ELM) for Estimating Grapevine Berry Yield and Quality

Dual Activation Function-Based Extreme Learning Machine (ELM) for Estimating Grapevine Berry Yield and Quality

Single Image Super-Resolution Based on Wiener Filter in Similarity Domain

A Survey on Detecting License Plates from Low Quality Images

Contact Info

Product

Resources

About