Image recognition, also known as computer vision, allows applications using specific deep learning algorithms to understand images or videos. In these scenarios, images are data in the sense that they are inputted into an algorithm, the algorithm performs a requested task, and the algorithm outputs a solution provided by the image. One common execution for computer vision applications includes facial recognition—whether for tagging friends on Facebook or a police department identifying a potential suspect—solely based on an image. Another use for image recognition is in the medical field, where artificial intelligence, using image recognition, can observe an x-ray and decipher the diagnosis solely based on the image. Some other aspects of image recognition include image restoration, object recognition, and scene reconstruction. These capabilities may be embedded inside intelligent applications or offered as deep learning algorithms inAI platforms.
To qualify for inclusion in the Image Recognition category, a product must:
Image Recognition reviews by real, verified users. Find unbiased ratings on user satisfaction, features, and price based on the most reviews available anywhere.
Microsoft Computer Vision API is a cloud-based API tool that provides developers with access to advanced algorithms for processing images and returning informatio, by uploading an image or specifying an image URL, it analyze visual content in different ways based on inputs and user choices.
OpenCV is a tool that has has C++, C, Python and Java interfaces and supports Windows, Linux, Mac OS, iOS and Android for computational efficiency and with a strong focus on real-time applications, written in optimized C/C++, the library can take advantage of multi-core processing and enabled to take advantage of the hardware acceleration of the underlying heterogeneous compute platform
SimpleCV is an open source framework for building computer vision applications, user can get access to several high-powered computer vision libraries such as OpenCV without having to learn about bit depths, file formats, color spaces, buffer management, eigenvalues, or matrix versus bitmap storage.
And this is where Google's deep dream ideas originate. With simple words you give to an AI program a couple of images and let it know what those images contain ( what objects - dogs, cats, mountains, bicycles, ... ) and give it a random image and ask it what objects it can find in this image.
DeepPy is a MIT licensed deep learning framework that tries to add a touch of zen to deep learning as it allows for Pythonic programming based on NumPy's ndarray,has a small and easily extensible codebase, runs on CPU or Nvidia GPUs and implements the following network architectures feedforward networks, convnets, siamese networks and autoencoders.
Alibaba Cloud Image Search is an intelligent image search service that helps users find similar or identical images. Based on machine learning and deep learning, the product enables end-users to take a screenshot or upload an image to search and find desired products and fulfill other search requests
Microsoft Video API is a cloud-based API that provides advanced algorithms for tracking faces, detecting motion, stabilizing and creating thumbnails from video, it allows user to build more personalized and intelligent apps by understanding and automatically transforming video content.
VLFeat is an open source library that implements popular computer vision algorithms specializing in image understanding and local features extraction and matching, it include Fisher Vector, VLAD, SIFT, MSER, k-means, hierarchical k-means, agglomerative information bottleneck, SLIC superpixels, quick shift superpixels, large scale SVM training, and many others. It is written in C for efficiency and compatibility, with interfaces in MATLAB for ease of use, and detailed documentation throughout. It supports Windows, Mac OS X, and Linux.
CCV is a open source/cross-platform solution for blob tracking with computer vision. that can interface with various web cameras and video devices as well as connect to various TUIO/OSC/XML enabled applications and supports many multi-touch lighting techniques including: FTIR, DI, DSI, and LLP with expansion planned for the future vision applications (custom modules/filters).
Harris Geospatial has developed a suite of deep learning-based tools called MEGA™ that are designed specifically to work with imagery to solve geospatial problems. This technology is currently being used to solve real-world problems in industries that include agriculture, utilities, transportation, and defense
MetaEyes is a reporting service that with the help of image recognition technology analyzes Instagram (plus other services) photos, revealing a wealth of actionable information. MetaEyes can detect: • Faces & Demographics • Explicit/Racy Content • Sentiment • Scenes & Objects • Logos • Locations • Celebrities • Other info Powerful reporting tools to analyze and filter data in myriads of ways. • Summary and granular reports • Filter detailed reports by all MetaEyes attributes • View by date range and different sorting methods • Export as PDF or CSV files for further analysis Photos provide a far more refined insight allowing for novel ways of engagement. •Discover potential fans by attributes previously undetectable • Surface and engage with previously ghost influencers • Find user-generated brand photos and directly contact to use in marketing campaigns • Monitor for brand related crisis situations and engage directly to avoid negative virality
MobileEngine makes it easy for you to add image recognition to your app. You provide a reference database of images (e.g. artwork, consumer packaged goods, book covers, catalog pages, etc.) and when your users photograph that object, MobileEngine finds your matching reference image.
MXNet is a Flexible and Efficient Library for Deep Learning that supports both imperative and symbolic programming, calculates the gradient automatically for training a model, runs on CPUs or GPUs, on clusters, servers, desktops, or mobile phones and supports distributed training on multiple CPU/GPU machines, including AWS, GCE, Azure, and Yarn clusters.