Computer Vision

...
Textual Art Generator Using Hybrid Learning Techniques

Our approach involves a fusion of deformable style transfer (DST), an optimization-centric technique that harmonizes the texture and geometry of a given content image to closely align with a chosen style image. This methodology is coupled with diffusion model inpainting, which is applied to content images originating from Calliar: an online dataset featuring handwritten Arabic calligraphy. Diverging from previous generative art methodologies, our approach presents aesthetically pleasing results, all the while preserving the integrity and structure of the Arabic script.

A Deep Learning based Framework for low-light image enhancement

We develop a CNN-based exposure fusion framework that can detect and eliminate hidden degradations in the darkness, as well as adjust different lightning conditions. The framework helps in extracting optimized feature representations using denoising, enhancement, and fusion module. Moreover, we perform a variety of ablation studies of low-light enhancement methods as well as comparative analysis of our proposed method with existing method is performed both qualitatively and quantitatively.

...
An Automated Teeth Lesion Diagnosis based on deep learning

A pipeline based on context-aware light-weight transformers with the goal of improving image quality without sacrificing the naturalness of the image, as well as reducing the inference time and size of the model. In this study, we trained a deep network-based transformer model on two standard datasets, i.e., Large-Scale Underwater Image (LSUI) and Underwater Image Enhancement Benchmark Dataset (UIEB), so that the network becomes more generalized, which subsequently improved the performance. Our real-time underwater image enhancement system shows superior results on edge devices. Also, we provide a comparison with other transformer-based methods.

Using Vision Transfers for Image Enhancement

A pipeline based on context-aware light-weight transformers with the goal of improving image quality without sacrificing the naturalness of the image, as well as reducing the inference time and size of the model. In this study, we trained a deep network-based transformer model on two standard datasets, i.e., Large-Scale Underwater Image (LSUI) and Underwater Image Enhancement Benchmark Dataset (UIEB), so that the network becomes more generalized, which subsequently improved the performance. Our real-time underwater image enhancement system shows superior results on edge devices. Also, we provide a comparison with other transformer-based methods.

Handwriting analysis of offline data for gender prediction

Significant progress has been made in the field of Writer identification and Signature Verification. Handwriting Analysis can be applied for classifying age, gender and nationality. Writer Recognition through handwriting analysis can be divided into two categories: online and off-line. On-line character recognition involves the identification of characters while they are written and deals with time […]