In the second part of this three part series, we will continue using the Intel Image Classification dataset from Kaggle but look at and implement ways to improve our model accuracy. This includes, data normalization, data augmentation, choosing a better model architecture, and more.

If you haven’t read the first part in this series, be sure to check it out here!

Preprocessing the data

The Intel Image Classification dataset contains various images of Natural Scenes around the world. Our goal is to make a model that can take in an image and accurately return one of the six classes: buildings, forest, glacier, mountain, sea, or street. …

In this three-part series, we will create a machine learning model that can classify different “natural scenes”. We will be using the Intel Image Classification dataset from Kaggle.

In this blog post, we will talk about object detection, take a look at our data, and understand and create a simple convolution neural network to classify six different “natural scenes.”

Object detection

Object detection is a computer vision method in which an AI is trained to identify and locate objects in an image or video. This method can be broken into two major steps: object localization and object recognition.

Object localization is locating the presence of objects in an image and finding a bounding box for that object. Object recognition is classifying the objects that the model found. …

Image for post
Image for post

Hi, I am Krish Ranjan. I am currently a freshman in high school. Some of my interests include coding, math, piano, and Artificial intelligence. I am interested in AI because it is a combination of two subjects I enjoy: math and coding. I also think that AI has many applications in the real world that can benefit humans and make our lives easier.

My experience with Inspirit AI was fantastic and made me excited about Artificial Intelligence. I was exposed to the many applications of AI and AI ethics. My instructor was Mr.Will Deaderick. He guided us through the theory behind computer vision and helped us with coding our very own AI. In the second week of AI Scholars, we coded AI that could take a video, deconstruct it into multiple pictures, and feed it into a convolution neural network (CNN). The CNN would output labels — what objects it has detected (car, bus, truck, and more) — and bounding boxes, where those objects are located on the image. The labeled images were then put together to remake the video, except this time it showed all the objects the AI detected. …

Krish Ranjan

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store