Computer Vision Library
As opposed to deep learning, OpenCV algorithms can be applied in cases where few - or even no - labeled data is available. Our previous OpenCV projects included: - Spotting differences between electrical equipment configurations for compliance purposes, - Pre-processing noisy images to feed our deep learning neural network in a food recognition app to execute automatic detection and billing of the menus.
OpenCV, which stands for Open Source Computer Vision, provides multiple algorithms to extract information from images. Several open OpenCV algorithms don't rely on machine learning and require few, or even no, labeled data to be efficient. Therefore, results are visible from the first days of our projects.
Stars on GitHub
OpenCV’s deployed uses span the range from stitching streetview images together, detecting intrusions in surveillance video in Israel, monitoring mine equipment in China (...) to inspecting labels on products in factories around the world on to rapid face detection in Japan.
OpenCV algorithms can characterize an object using keypoints, also known as descriptors. These descriptors can be specific angles or color variations. Using these keypoints, it becomes easier to find whether an object is present in any given image.
Before applying deep learning tools to your data, an OpenCV pre-processing can clear it from noisy information. Consequently, only the most valuable part of your data will feed the deep learning pipeline, boosting the performance of the solution. Edge detection is one of the most widely used pre-processing methods available in OpenCV and can be applied to live videos.
Related articles written by Sicara's data scientists
Edge Detection in Opencv 4.0, A 15 Minutes Tutorial
This tutorial will teach you, with examples, two OpenCV techniques in python to deal with edge detection.
GAN with Keras: Application to Image Deblurring
A Generative Adversarial Networks tutorial applied to Image Deblurring with the Keras library.
Set up TensorFlow with Docker + GPU in Minutes
Why Docker is the best platform to use Tensorflow with a GPU.