Ajay Kumar Reddy Poreddy

ORCID: 0000-0002-2920-9997
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Image and Video Quality Assessment
  • Advanced Image Fusion Techniques
  • Visual Attention and Saliency Detection
  • AI in cancer detection
  • Advanced Image Processing Techniques
  • Brain Tumor Detection and Classification
  • Cutaneous Melanoma Detection and Management
  • Image and Signal Denoising Methods
  • Industrial Vision Systems and Defect Detection
  • Smart Systems and Machine Learning
  • Retinal and Optic Conditions
  • Dermatological and COVID-19 studies
  • Acute Ischemic Stroke Management
  • Traditional Chinese Medicine Studies
  • Face recognition and analysis
  • COVID-19 diagnosis using AI
  • Herpesvirus Infections and Treatments
  • Retinal Imaging and Analysis
  • Nonmelanoma Skin Cancer Studies
  • Cell Image Analysis Techniques

Indian Institute of Technology Indore
2025

Sri Sivasubramaniya Nadar College of Engineering
2025

Indian Institute of Information Technology, Design and Manufacturing, Kancheepuram
2021-2024

Jawaharlal Nehru Technological University, Kakinada
2020

With the rapid proliferation of virtual reality (VR) technologies, usage VR in multimedia, education, and social media platforms has increased due to realistic immersive 3D viewing experiences. In particular, refers a computer-generated synthetic environment where users can experience 180 × 360° spherical content through head-mounted displays (HMD). Due range, quality assessment (QA) images becomes quite difficult compared conventional 2D image (IQA) models. To alleviate this problem, paper,...

10.1109/tim.2023.3322995 article EN IEEE Transactions on Instrumentation and Measurement 2023-01-01

In this paper, we develop a framework to assess the perceptual quality of Virtual Reality (VR) images by studying joint dependencies between luminance and disparity pairs using Bivariate Generalized Gaussian Distribution (BGGD) model. We compute model parameters ($\alpha,\ \beta$) BGGD at multi-scale multi-orient steerable pyramid decomposition cube map projection (CMP) faces both left right views VR image. learn Multivariate (MVG) from features CMP pristine as reference representative....

10.1109/spcom55316.2022.9840855 article EN 2022 IEEE International Conference on Signal Processing and Communications (SPCOM) 2022-07-11

In this work, we propose a supervised no-reference (NR) Image Quality Assessment (IQA) model for the objective evaluation of perceptual quality 3D virtual reality (VR) images. To achieve such practical algorithm, first study scene statistics saliency maps individual left and right views VR images, empirically these with Univariate Generalized Gaussian Distribution (UGGD). We compute UGGD parameters at multi-scale multi-orient steerable subband decomposition, introduce features as distortion...

10.1117/12.2597327 article EN 2021-07-30

Among various types of skin cancers, melanoma is the most aggressive and deadly. There a notable growth in implementation deep learning (DL) methods to identify malignancies dermoscopy images. This paper introduces lightweight DL-based approach designed for seamless integration into low-memory devices within healthcare applications. The proposed method incorporates three convolutional neural network (CNN) models: MobileNet-v2, SqueezeNet, GoogLeNet. Initially, test features are computed from...

10.1109/wispnet61464.2024.10532923 article EN 2024-03-21

This paper presents an unsupervised virtual reality (VR) image quality assessment (IQA) model based on feature-fusion technique. A distilled feature selection approach is employed to obtain the optimal features of computationally efficient 2D IQA models. Further, obtained are used compute quality-aware from viewports VR images. Principal components and projection matrices each pristine viewport by principal component analysis which further vector a test set. Multivariate Gaussian modeling...

10.1109/tim.2024.3400304 article EN IEEE Transactions on Instrumentation and Measurement 2024-01-01

Anemia, characterized by a deficiency in red blood corpuscles or hemoglobin, poses significant global health challenge, particularly affecting vulnerable populations. Traditional diagnostic methods often involve invasive procedures, posing challenges resource-limited settings. This study aims to explore non-invasive anemia detection using fingernail images and convolutional neural networks (CNNs) as promising alternative conventional approaches. The utilizes dataset of collected from...

10.1109/icbsii61384.2024.10564094 article EN 2024-03-20

Breast cancer (BC) is a potentially life-threatening disease that occurs because of uncontrolled growth abnormal corpuscles in the breast tissue. Pathologists analyze tissue structures using histopathological whole slide images to identify cancerous anomalies. However, pathologists face severe challenges such as fatigue, subjectivity, and inter-observer variability early detection BC. Understanding intricacies BC from molecular complex, inexpertise leads adverse outcomes. This paper proposes...

10.1109/icbsii61384.2024.10564079 article EN 2024-03-20

Anemia is a common medical condition affecting millions worldwide, particularly in developing countries. Early detection of anemia crucial for prompt treatment and prevention its potential complications. In recent years, deep learning (DL) has shown great various applications, including image classification, anomaly detection, segmentation. This study proposes transfer learning-based approach using pre-trained DL model to detect from palpebral conjunctiva images. The proposed method utilizes...

10.1109/cict59886.2023.10455477 article EN 2022 IEEE 6th Conference on Information and Communication Technology (CICT) 2023-12-15

Growth and usage of digital images have been tremendous in recent years as they are the source for representing communicating information. Various algorithms developed to improve performance an image when it is subjected distortions viz., acquisition, transmission, compression. It highly undesirable evaluate quality score or quantitative index based on Human Visual System (HVS) practical systems. A large number restoration available enhance quality. So, a metric needs be deployed determine...

10.2139/ssrn.3647949 article EN SSRN Electronic Journal 2020-01-01
Coming Soon ...