liveBook · Manning

Image recognition

Image recognition is the computational task of identifying or classifying objects, patterns, scenes, or other meaningful content in images.

How 3 Manning books explain it

Grokking Machine Learning

The computational task of identifying or classifying objects, patterns, or other content in images.

How it is used
Uses image recognition to illustrate classification, from detecting a dog to classifying handwritten digits.
How deep it goes
Defines pixel-based classification and demonstrates MNIST preprocessing, training, and prediction, while noting perceptron limitations.
Examples
Uses dog detection and handwritten-digit classification, including a 3 misclassified as an 8.
What you can do after
Apply via Keras by preprocessing MNIST images and labels, training a neural network, and predicting digit classes.

Read how Grokking Machine Learning explains image recognition →

The AI Pocket Book

The task of assigning an image to one of several possible classes based on its visual content.

How it is used
Frames image recognition as supervised image categorization, then uses CNNs to explain how visual features become class predictions.
How deep it goes
Explains pixels, learned filters, convolution, downsampling, and abstraction, but stops short of mathematical derivations or implementation details.
Examples
Uses strawberry, plane, dog, and cat images, plus learned filters for blur, color, edges, and directional lines.
What you can do after
Evaluate/understand how CNNs classify images and recognize labeling, generalization, overfitting, and underfitting risks.

Read how The AI Pocket Book explains image recognition →

Grokking Machine Learning, Second Edition

The computational task of identifying objects, patterns, or other meaningful content in images.

How it is used
Uses pixel data to predict which finite class an image represents.
How deep it goes
Descends from classification intuition to reshaping, label encoding, neural-network training, and prediction inspection.
Examples
Uses MNIST handwritten digits and contrasts a correctly classified 4 with a 3 mistaken for an 8.
What you can do after
Builds and tests a Keras neural network that predicts handwritten digits from MNIST images.

Read how Grokking Machine Learning, Second Edition explains image recognition →

Also covered in

What to know first

Related concepts

Questions about image recognition

What is image recognition?

Image recognition is the computational task of identifying or classifying objects, patterns, scenes, or other meaningful content in images.

Which Manning books explain image recognition?

Grokking Machine Learning, The AI Pocket Book and Grokking Machine Learning, Second Edition.

What should I know before learning image recognition?

Manning books that teach image recognition usually introduce classifier, language model, convolutional neural network and pixel first.

What is image recognition a kind of?

Image recognition is a kind of machine learning application. A machine learning application is a software system or practical use case that applies machine-learning methods to perform a task or produce predictions.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.