Portfolio Category

Image Processing

Showing 4 Result(s)

Computer Vision Image Search

on

Nowadays, a common way to identify and classify similar images within large image sets is to implement what are known in the computer vision field as visual searching techniques. The aim of this project was to build a visual search tool using some of these techniques and analyze their performance, using MATLAB.

The image classification process is based on computing an accurate image descriptor for a query image manually selected by the user or automatically selected by the system, which will then be represented in an N-dimensional feature space. The rest of the images in the database are then represented in the same feature space. The distance from each image representation as a point in the feature space to the query image point in the same feature space determines how similar the images are.

I completed this project at the University of Surrey, UK. For more information on the project click on the link to the repository.

Project Repository

Machine Learning Search Engine

on

The purpose of this work is to build a large-scale image search engine that searches for images relevant to a given natural language query and return them in order of similarity. The search engine was built using different machine learning techniques and comparing their efficiency. It is coded in Python. This project consisted of a Kaggle competition to be completed to the best of our abilities within approximately a week.

I worked in a team to complete this challenge at Cornell Tech, NYC.

For more information on the full project click on the link to the respository!

Project Repository

Quadtree Encoding of Binary Images

on

During the years, different methods for storing image processing data have been developed. One of the data structures that can be used for this purpose is a quadtree, which is a tree structure in which every node has four children nodes. It can be implemented to represent an image whose size is an integer power of two. In this project a quadtree structure is used for storing a square two-dimensional binary image with a maximum width of 64 pixels.

I completed this project at the University of Surrey, UK. For more information on the project click on the link to the repository.

Project Repository