Search Results for author:
Found 10 papers, 1 papers with code
Revealing the Underlying Patterns: Investigating Dataset Similarity, Performance, and Generalization
Supervised deep learning models require significant amount of labeled data to achieve an acceptable performance on a specific task.
TrueDeep: A systematic approach of crack detection with less data
The objective of this work is to show that by incorporating domain knowledge along with deep learning architectures, we can achieve similar performance with less data.
CoreDeep: Improving Crack Detection Algorithms Using Width Stochasticity
Detecting, measuring and quantifying cracks for distress analysis in challenging background scenarios is a difficult task as there is no clear boundary that separates cracks from the background.
Improving Facial Emotion Recognition Systems Using Gradient and Laplacian Images
These modifications help the network learn additional information from the gradient and Laplacian of the images.
Binary Document Image Super Resolution for Improved Readability and OCR Performance
This gives rise to the problem of binary document image super-resolution (BDISR).
MSCE: An edge preserving robust loss function for improving super-resolution algorithms
With the recent advancement in the deep learning technologies such as CNNs and GANs, there is significant improvement in the quality of the images reconstructed by deep learning based super-resolution (SR) techniques.
Computationally Efficient Approaches for Image Style Transfer
In this work, we have investigated various style transfer approaches and (i) examined how the stylized reconstruction changes with the change of loss function and (ii) provided a computationally efficient solution for the same.
Segmentation of Liver Lesions with Reduced Complexity Deep Models
We propose a computationally efficient architecture that learns to segment lesions from CT images of the liver.
A hybrid approach of interpolations and CNN to obtain super-resolution
We propose a novel architecture that learns an end-to-end mapping function to improve the spatial resolution of the input natural images.
Language Independent Single Document Image Super-Resolution using CNN for improved recognition
The problem involves quality improvement before passing it to a properly trained OCR to get accurate recognition of the text.
