Amrutha Kommineni

Aspiring Computer Science student with a background in deep learning, computer vision, and data analysis. I am experienced in implementing Mask R-CNN for object detection and good in Python, SQL, and web development. Actively seeking opportunities to apply and expand my technical skills through internships or entry-level positions, contributing to innovative projects and gaining industry experience.

• Certificate of "PRELIMINARY ENGLISH TEST" at VFSTR University conducted by Cambridge University in 2019
• Certified in the "SOFTWARE TESTING" course conducted by Swayam NPTEL
• Certificate of "ENHANCING OBJECT DETECTION USING MASK R-CNN" project by IEEE 2023

1. Enhancing Object Detection Using Mask R-CNN: 

Object detection in computer vision with applications ranging from autonomous driving to medical image analysis. Mask R-CNN is an extension of the Faster R-CNN architecture, has emerged as a powerful tool for detecting and segmenting objects within images. The application of Mask R-CNN is to enhance object detection from a deep learning perspective, focusing on improving the precision, robustness, and versatility of object detection systems. 

2. Hand written digit recognition Using Machine Learning: 

Hand written digit recognition is designed to automatically identify and classify handwritten numerical digits. It finds application in various fields, including character recognition and optical character recognition (OCR). I developed a machine learning model for handwritten digit recognition, achieving over 99% accuracy on the MNIST dataset. This project demonstrates my proficiency in machine learning and image classification. 

• Member in Public Relations (Travel Club):

Organized and led a campus event, a group trip to the hill station with nearly 20 people.

Managed all aspects of event planning, including logistics, budgeting, marketing, and participant coordination.

Created promotional materials and executed a targeted PR campaign to generate interest, resulting in full participation and positive feedback from attendees.

Paper Title: Enhancing Object Detection with Mask R-CNN: A Deep Learning Perspective

Published in IEEE, September 2023

• https://ieeexplore.ieee.org/document/10276033/
• July 2023 - September 2023
• Implemented Mask R-CNN architecture with a ResNet-50-FPN backbone for efficient object recognition and classification, improving accuracy on Pascal VOC and COCO datasets (89.9% and 95.4%).
• Trained deep-learning models (CNN, VGG-16, Inception Net) for object detection, enhancing feature extraction using pre-trained models.
• Analyzed key components of Mask R-CNN and proposed improvements for applications in autonomous driving, surveillance, and robotics.
• Published research findings on innovative frameworks for machine vision systems, recognized for contributing to advancements in computer vision.