This page has only limited features, please log in for full access.

Unclaimed
Surendra Shrestha
Department of Electronics & Computer Engineering, Pulchowk Campus, Institute of Engineering, Tribhuvan University, Lalitpur 44700, Nepal

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

The user biography is not available.
Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Journal article
Published: 21 December 2020 in Mathematics
Reads 0
Downloads 0

Enhancement of Cultural Heritage such as historical images is very crucial to safeguard the diversity of cultures. Automated colorization of black and white images has been subject to extensive research through computer vision and machine learning techniques. Our research addresses the problem of generating a plausible colored photograph of ancient, historically black, and white images of Nepal using deep learning techniques without direct human intervention. Motivated by the recent success of deep learning techniques in image processing, a feed-forward, deep Convolutional Neural Network (CNN) in combination with Inception- ResnetV2 is being trained by sets of sample images using back-propagation to recognize the pattern in RGB and grayscale values. The trained neural network is then used to predict two a* and b* chroma channels given grayscale, L channel of test images. CNN vividly colorizes images with the help of the fusion layer accounting for local features as well as global features. Two objective functions, namely, Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR), are employed for objective quality assessment between the estimated color image and its ground truth. The model is trained on the dataset created by ourselves with 1.2 K historical images comprised of old and ancient photographs of Nepal, each having 256 × 256 resolution. The loss i.e., MSE, PSNR, and accuracy of the model are found to be 6.08%, 34.65 dB, and 75.23%, respectively. Other than presenting the training results, the public acceptance or subjective validation of the generated images is assessed by means of a user study where the model shows 41.71% of naturalness while evaluating colorization results.

ACS Style

Madhab Joshi; Lewis Nkenyereye; Gyanendra Joshi; S. Islam; Mohammad Abdullah-Al-Wadud; Surendra Shrestha. Auto-Colorization of Historical Images Using Deep Convolutional Neural Networks. Mathematics 2020, 8, 2258 .

AMA Style

Madhab Joshi, Lewis Nkenyereye, Gyanendra Joshi, S. Islam, Mohammad Abdullah-Al-Wadud, Surendra Shrestha. Auto-Colorization of Historical Images Using Deep Convolutional Neural Networks. Mathematics. 2020; 8 (12):2258.

Chicago/Turabian Style

Madhab Joshi; Lewis Nkenyereye; Gyanendra Joshi; S. Islam; Mohammad Abdullah-Al-Wadud; Surendra Shrestha. 2020. "Auto-Colorization of Historical Images Using Deep Convolutional Neural Networks." Mathematics 8, no. 12: 2258.

Journal article
Published: 07 September 2019 in Applied Sciences
Reads 0
Downloads 0

This study aimed to develop magnetic Fe3O4/sugarcane bagasse activated carbon composite for the adsorption of arsenic (III) from aqueous solutions. Activated carbon (AC) was prepared from sugarcane bagasse by chemical activation using H3PO4 as an activating agent at 400 °C. To enhance adsorption capacity for arsenic, the resultant AC was composited with Fe3O4 particles by facile one-pot hydrothermal treatment. This method involves mixing the AC with aqueous solution of iron (II) chloride tetrahydrate, polyvinyl pyrrolidone (PVP), and ethanol. Batch adsorption experiments were conducted for the adsorption of As (III) onto the composite. The effects of pH, adsorbent dosage, and contact time on the arsenic adsorption were studied. The result showed that the composite could remove the arsenic from the water far more effectively than the plain AC. The highest percentage of arsenic removal was found at pH at 8, adsorbent dose of 1.8 g/L, and contact time of 60 min. Langmuir and Freundlich adsorption isotherm was used to analyze the equilibrium experimental data. Langmuir model showed the best fit compared to the Freundlich model with a maximal capacity of 6.69 mg/g. These findings indicated that magnetic Fe3O4/sugarcane bagasse AC composite could be potentially applied for adsorptive removal of arsenic (III) from aqueous solutions.

ACS Style

Sahira Joshi; Manobin Sharma; Anshu Kumari; Surendra Shrestha; Bhanu Shrestha. Arsenic Removal from Water by Adsorption onto Iron Oxide/Nano-Porous Carbon Magnetic Composite. Applied Sciences 2019, 9, 3732 .

AMA Style

Sahira Joshi, Manobin Sharma, Anshu Kumari, Surendra Shrestha, Bhanu Shrestha. Arsenic Removal from Water by Adsorption onto Iron Oxide/Nano-Porous Carbon Magnetic Composite. Applied Sciences. 2019; 9 (18):3732.

Chicago/Turabian Style

Sahira Joshi; Manobin Sharma; Anshu Kumari; Surendra Shrestha; Bhanu Shrestha. 2019. "Arsenic Removal from Water by Adsorption onto Iron Oxide/Nano-Porous Carbon Magnetic Composite." Applied Sciences 9, no. 18: 3732.