Book Image

Computer Vision Projects with OpenCV and Python 3

By : Matthew Rever
Book Image

Computer Vision Projects with OpenCV and Python 3

By: Matthew Rever

Overview of this book

Python is the ideal programming language for rapidly prototyping and developing production-grade codes for image processing and Computer Vision with its robust syntax and wealth of powerful libraries. This book will help you design and develop production-grade Computer Vision projects tackling real-world problems. With the help of this book, you will learn how to set up Anaconda and Python for the major OSes with cutting-edge third-party libraries for Computer Vision. You'll learn state-of-the-art techniques for classifying images, finding and identifying human postures, and detecting faces within videos. You will use powerful machine learning tools such as OpenCV, Dlib, and TensorFlow to build exciting projects such as classifying handwritten digits, detecting facial features,and much more. The book also covers some advanced projects, such as reading text from license plates from real-world images using Google’s Tesseract software, and tracking human body poses using DeeperCut within TensorFlow. By the end of this book, you will have the expertise required to build your own Computer Vision projects using Python and its associated libraries.
Table of Contents (9 chapters)

Google Brain im2txt captioning model

Google Brain im2txt was used by Google in a paper 2015 MSCOCO Image Captioning Challenge, and will form the foundation of the image captioning code that we will implement in our project.

The Google's GitHub TensorFlow page can be found at https://github.com/tensorflow/models/tree/master/research/im2txt.

In the research directory, we will find the im2txt file, which was used by Google in the paper, 2015 MSCOCO Image Captioning Challenge, which is available for free at https://arxiv.org/abs/1609.06647. It covers RNNs, LSTM, and fundamental algorithms in detail.

We can check how CNNs are used for image classification and also learn how to use the LSTM RNNs for actually generating sequential caption outputs.

We can download the code from the GitHub link; however, it has not been set up to run easily as it does not include a pre-trained model...