Naïve Bees: Predict Species from Images

Build a model that can automatically detect honey bees and bumble bees in images.

Start Project

11 Tasks1,500 XP

Loved by learners at thousands of companies

Project Description

Can a machine distinguish between a honey bee and a bumble bee? Being able to identify bee species from images, while challenging, would allow researchers to more quickly and effectively collect field data. In this project, you will use the Python image library Pillow to load and manipulate image data, then build a model to identify honey bees and bumble bees given an image of these insects.

This project is the second part of a series of projects that walk through working with image data, building classifiers using traditional techniques, and leveraging the power of deep learning for computer vision.

Before taking this project, it will help to have completed Naïve Bees: Image Loading and Processing.

Project Tasks

1
Import Python libraries

2
Display image of each bee type
3
Image manipulation with rgb2gray
4
Histogram of oriented gradients
5
Create image features and flatten into a single row
6
Loop over images to preprocess
7
Split into train and test sets
8
Scale training and test features
9
Perform PCA
10
10.Train and score our model
11
ROC curve + AUC

Technologies

Python

Topics

Data Manipulation Data Visualization Machine Learning

Peter Bull

Co-founder of DrivenData

Peter is a co-founder of DrivenData. He earned his master's in Computational Science and Engineering from Harvard’s School of Engineering and Applied Sciences. His work lies at the intersection of statistics and computer science, and he wants to help bring powerful new modeling techniques to the organizations that need them most. He previously worked as a software engineer at Microsoft and earned a BA in philosophy from Yale University.

Emily Miller

Data Scientist at DrivenData

Emily Miller is a Data Scientist at DrivenData. Her personal passion is to combine data science with satellite imagery, text data, and other non-traditional data sources to make poverty alleviation efforts more effective. She was previously a Data Scientist at the Bill & Melinda Gates Foundation and a Data Science Fellow at Metis.