Dataset for Face Recognition Last Updated : 24 Apr, 2025 Comments Improve Suggest changes Like Article Like Report Face recognition means to identify and verify a person by looking at their facial features and it is used in security systems, social media or even unlocking your phone. To build and test these systems researchers and developers need a good quality dataset for training. In this article, we will discuss some of the famous datasets for face recognition.Dataset for Face Recognition1. Labelled Faces in the Wild (LFW)This dataset contains over 13,000 images of people’s faces collected from internet. Each image is labeled with the person’s name. This dataset is widely used for face verification and recognition algorithms.It was created by the University of Massachusetts, Amherst and is used to check how accurate a face recognition model is.2. YouTube Faces DBAs the name suggests this dataset includes videos taken from YouTube. It contains 3,425 videos of 1,595 people. Because these are videos each person’s face appears in many different ways moving, turning, smiling or in different lighting.This makes it very useful for testing how well a face recognition system works when the face is not still just like in real life. The dataset was created by the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT and Tel Aviv University.3. CelebAThis dataset is made up of over 200,000 images of celebrities. But what’s special about it is that each photo comes with 40 different labels like “wearing glasses”, “smiling”, “has beard” and so on.This helps train systems not just to recognize faces but also to detect features and emotions. It’s very useful for tasks like face detection and analyzing facial expressions. This dataset was developed by the Multimedia Laboratory at the Chinese University of Hong Kong.4. CASIA WebFaceThe CASIA WebFace dataset contains approximately 500,000 images of 10,575 individuals sourced from the web. It is primarily used for face recognition research and has been instrumental in advancing deep learning techniques in this area. It was created by the Institute of Automation, Chinese Academy of Sciences. If you're building a strong face recognition system this dataset is a good place to start.5. FERET DatabaseFERET stands for Facial Recognition Technology. This dataset has been for a long time and includes over 14,000 images of 1,199 individuals.These images were taken under very controlled conditions like fixed lighting and camera angles which makes it ideal for comparing the basic performance of different face recognition systems.It was developed by the National Institute of Standards and Technology (NIST).6. PubFigThe Public Figures Face Database (PubFig) contains images of 200 public figures with 58,797 images. The images are collected from the web and include a wide variety of conditions and variations. PubFig is used for evaluating face recognition systems particularly in unconstrained environments. This dataset was created by researchers at the University of Massachusetts, Amherst.7. MS-Celeb-1MThe MS-Celeb-1M dataset is a large-scale face recognition dataset with 1 million images of 100,000 celebrities. Created by Microsoft Research it provides a massive resource for training and evaluating face recognition models. The dataset is designed to address the challenge of large-scale face recognition in different conditions. 8. VGGFace2The VGGFace2 dataset consists of 3.31 million images of 9,131 individuals. It includes a wide range of poses, ages and lighting conditions which make it suitable for training robust face recognition models. It build face recognition models that are more flexible and reliable in real-world conditions. This dataset was created by the Visual Geometry Group at the University of Oxford.9. MegaFaceThe MegaFace dataset is designed to evaluate the performance of face recognition algorithms at a large scale. It includes over 1 million images of 690,000 unique individuals. The primary goal of MegaFace is to test face recognition systems under large-scale and real-world conditions. This dataset was developed by the University of Washington.10. UMDFacesThe UMDFaces dataset contains over 367,000 face annotations for 8,277 subjects collected from web. This dataset includes both still images and video frames and was developed by the University of Maryland.In order to train efficient systems for recognizing people’s faces it is important to have a well selected, vast, diverse and ethically obtained collection of data and you can use any of the dataset for that discussed above. Comment More infoAdvertise with us Next Article Computer Vision - Introduction Anonymous Improve Article Tags : Blogathon Computer Vision AI-ML-DS Blogs DataSets Data Science Blogathon 2024 +1 More Similar Reads Computer Vision Tutorial Computer Vision (CV) is a branch of Artificial Intelligence (AI) that helps computers to interpret and understand visual information much like humans. This tutorial is designed for both beginners and experienced professionals and covers key concepts such as Image Processing, Feature Extraction, Obje 7 min read Introduction to Computer VisionComputer Vision - IntroductionComputer Vision (CV) in artificial intelligence (AI) help machines to interpret and understand visual information similar to how humans use their eyes and brains. It involves teaching computers to analyze and understand images and videos, helping them "see" the world. From identifying objects in ima 4 min read A Quick Overview to Computer VisionComputer vision means the extraction of information from images, text, videos, etc. Sometimes computer vision tries to mimic human vision. It’s a subset of computer-based intelligence or Artificial intelligence which collects information from digital images or videos and analyze them to define the a 3 min read Applications of Computer VisionHave you ever wondered how machines can "see" and understand the world around them, much like humans do? This is the magic of computer vision—a branch of artificial intelligence that enables computers to interpret and analyze digital images, videos, and other visual inputs. From self-driving cars to 6 min read Fundamentals of Image FormationImage formation is an analog to digital conversion of an image with the help of 2D Sampling and Quantization techniques that is done by the capturing devices like cameras. In general, we see a 2D view of the 3D world.In the same way, the formation of the analog image took place. It is basically a co 7 min read Satellite Image ProcessingSatellite Image Processing is an important field in research and development and consists of the images of earth and satellites taken by the means of artificial satellites. Firstly, the photographs are taken in digital form and later are processed by the computers to extract the information. Statist 2 min read Image FormatsImage formats are different types of file types used for saving pictures, graphics, and photos. Choosing the right image format is important because it affects how your images look, load, and perform on websites, social media, or in print. Common formats include JPEG, PNG, GIF, and SVG, each with it 5 min read Image Processing & TransformationDigital Image Processing BasicsDigital Image Processing means processing digital image by means of a digital computer. We can also say that it is a use of computer algorithms, in order to get enhanced image either to extract some useful information. Digital image processing is the use of algorithms and mathematical models to proc 7 min read Difference Between RGB, CMYK, HSV, and YIQ Color ModelsThe colour spaces in image processing aim to facilitate the specifications of colours in some standard way. Different types of colour models are used in multiple fields like in hardware, in multiple applications of creating animation, etc. Let’s see each colour model and its application. RGBCMYKHSV 3 min read Image Enhancement Techniques using OpenCV - PythonImage enhancement is the process of improving the quality and appearance of an image. It can be used to correct flaws or defects in an image, or to simply make an image more visually appealing. Image enhancement techniques can be applied to a wide range of images, including photographs, scans, and d 15+ min read Image Transformations using OpenCV in PythonIn this tutorial, we are going to learn Image Transformation using the OpenCV module in Python. What is Image Transformation? Image Transformation involves the transformation of image data in order to retrieve information from the image or preprocess the image for further usage. In this tutorial we 5 min read How to find the Fourier Transform of an image using OpenCV Python?The Fourier Transform is a mathematical tool used to decompose a signal into its frequency components. In the case of image processing, the Fourier Transform can be used to analyze the frequency content of an image, which can be useful for tasks such as image filtering and feature extraction. In thi 5 min read Python | Intensity Transformation Operations on ImagesIntensity transformations are applied on images for contrast manipulation or image thresholding. These are in the spatial domain, i.e. they are performed directly on the pixels of the image at hand, as opposed to being performed on the Fourier transform of the image. The following are commonly used 5 min read Histogram Equalization in Digital Image ProcessingA digital image is a two-dimensional matrix of two spatial coordinates, with each cell specifying the intensity level of the image at that point. So, we have an N x N matrix with integer values ranging from a minimum intensity level of 0 to a maximum level of L-1, where L denotes the number of inten 5 min read Python - Color Inversion using PillowColor Inversion (Image Negative) is the method of inverting pixel values of an image. Image inversion does not depend on the color mode of the image, i.e. inversion works on channel level. When inversion is used on a multi color image (RGB, CMYK etc) then each channel is treated separately, and the 4 min read Image Sharpening using Laplacian, High Boost Filtering in MATLABImage sharpening is a crucial process in digital image processing, aimed at improving the clarity and crispness of visual content. By emphasizing the edges and fine details in a picture, sharpening transforms dull or blurred images into visuals where objects stand out more distinctly from their back 3 min read Wand sharpen() function - PythonThe sharpen() function is an inbuilt function in the Python Wand ImageMagick library which is used to sharpen the image. Syntax: sharpen(radius, sigma) Parameters: This function accepts four parameters as mentioned above and defined below: radius: This parameter stores the radius value of the sharpn 2 min read Python OpenCV - Smoothing and BlurringIn this article, we are going to learn about smoothing and blurring with python-OpenCV. When we are dealing with images at some points the images will be crisper and sharper which we need to smoothen or blur to get a clean image, or sometimes the image will be with a really bad edge which also we ne 7 min read Python PIL | GaussianBlur() methodPIL is the Python Imaging Library which provides the python interpreter with image editing capabilities. The ImageFilter module contains definitions for a pre-defined set of filters, which can be used with the Image.filter() method. PIL.ImageFilter.GaussianBlur() method create Gaussian blur filter. 1 min read Apply a Gauss filter to an image with PythonA Gaussian Filter is a low-pass filter used for reducing noise (high-frequency components) and for blurring regions of an image. This filter uses an odd-sized, symmetric kernel that is convolved with the image. The kernel weights are highest at the center and decrease as you move towards the periphe 2 min read Spatial Filtering and its TypesSpatial Filtering technique is used directly on pixels of an image. Mask is usually considered to be added in size so that it has specific center pixel. This mask is moved on the image such that the center of the mask traverses all image pixels. Classification on the basis of Linearity There are two 3 min read Python PIL | MedianFilter() and ModeFilter() methodPIL is the Python Imaging Library which provides the python interpreter with image editing capabilities. The ImageFilter module contains definitions for a pre-defined set of filters, which can be used with the Image.filter() method. PIL.ImageFilter.MedianFilter() method creates a median filter. Pick 1 min read Python | Bilateral FilteringA bilateral filter is used for smoothening images and reducing noise, while preserving edges. This article explains an approach using the averaging filter, while this article provides one using a median filter. However, these convolutions often result in a loss of important edge information, since t 2 min read Python OpenCV - Morphological OperationsPython OpenCV Morphological operations are one of the Image processing techniques that processes image based on shape. This processing strategy is usually performed on binary images. Morphological operations based on OpenCV are as follows:ErosionDilationOpeningClosingMorphological GradientTop hatBl 5 min read Erosion and Dilation of images using OpenCV in PythonMorphological operations modify images based on the structure and arrangement of pixels. They apply kernel to an input image for changing its features depending on the arrangement of neighboring pixels. Morphological operations like erosion and dilation are techniques in image processing, especially 3 min read Introduction to Resampling methodsWhile reading about Machine Learning and Data Science we often come across a term called Imbalanced Class Distribution, which generally happens when observations in one of the classes are much higher or lower than in other classes. As Machine Learning algorithms tend to increase accuracy by reducing 8 min read Python | Image Registration using OpenCVImage registration is a digital image processing technique that helps us align different images of the same scene. For instance, one may click the picture of a book from various angles. Below are a few instances that show the diversity of camera angles.Now, we may want to "align" a particular image 3 min read Feature Extraction and DescriptionFeature Extraction Techniques - NLPIntroduction : This article focuses on basic feature extraction techniques in NLP to analyse the similarities between pieces of text. Natural Language Processing (NLP) is a branch of computer science and machine learning that deals with training computers to process a large amount of human (natural) 10 min read SIFT Interest Point Detector Using Python - OpenCVSIFT (Scale Invariant Feature Transform) Detector is used in the detection of interest points on an input image. It allows the identification of localized features in images which is essential in applications such as:  Object Recognition in ImagesPath detection and obstacle avoidance algorithmsGest 4 min read Feature Matching using Brute Force in OpenCVIn this article, we will do feature matching using Brute Force in Python by using OpenCV library. Prerequisites: OpenCV OpenCV is a python library which is used to solve the computer vision problems. OpenCV is an open source Computer Vision library. So computer vision is a way of teaching intelligen 13 min read Feature detection and matching with OpenCV-PythonIn this article, we are going to see about feature detection in computer vision with OpenCV in Python. Feature detection is the process of checking the important features of the image in this case features of the image can be edges, corners, ridges, and blobs in the images. In OpenCV, there are a nu 5 min read Feature matching using ORB algorithm in Python-OpenCVORB is a fusion of FAST keypoint detector and BRIEF descriptor with some added features to improve the performance. FAST is Features from Accelerated Segment Test used to detect features from the provided image. It also uses a pyramid to produce multiscale-features. Now it doesn’t compute the orient 2 min read Mahotas - Speeded-Up Robust FeaturesIn this article we will see how we can get the speeded up robust features of image in mahotas. In computer vision, speeded up robust features (SURF) is a patented local feature detector and descriptor. It can be used for tasks such as object recognition, image registration, classification, or 3D rec 2 min read Create Local Binary Pattern of an image using OpenCV-PythonIn this article, we will discuss the image and how to find a binary pattern using the pixel value of the image. As we all know, image is also known as a set of pixels. When we store an image in computers or digitally, it’s corresponding pixel values are stored. So, when we read an image to a variabl 5 min read Deep Learning for Computer VisionImage Classification using CNNImage classification is a key task in machine learning where the goal is to assign a label to an image based on its content. Convolutional Neural Networks (CNNs) are specifically designed to analyze and interpret images. Unlike traditional neural networks, they are good at detecting patterns, shapes 5 min read What is Transfer Learning?Transfer learning is a machine learning technique where a model trained on one task is repurposed as the foundation for a second task. This approach is beneficial when the second task is related to the first or when data for the second task is limited. Using learned features from the initial task, t 8 min read Top 5 PreTrained Models in Natural Language Processing (NLP)Pretrained models are deep learning models that have been trained on huge amounts of data before fine-tuning for a specific task. The pre-trained models have revolutionized the landscape of natural language processing as they allow the developer to transfer the learned knowledge to specific tasks, e 7 min read ML | Introduction to Strided ConvolutionsLet us begin this article with a basic question - "Why padding and strided convolutions are required?" Assume we have an image with dimensions of n x n. If it is convoluted with an f x f filter, then the dimensions of the image obtained are (n-f+1) x (n-f+1). Example: Consider a 6 x 6 image as shown 2 min read Dilated ConvolutionPrerequisite: Convolutional Neural Networks Dilated Convolution: It is a technique that expands the kernel (input) by inserting holes between its consecutive elements. In simpler terms, it is the same as convolution but it involves pixel skipping, so as to cover a larger area of the input. Dilated 5 min read Continuous Kernel ConvolutionContinuous Kernel convolution was proposed by the researcher of Verije University Amsterdam in collaboration with the University of Amsterdam in a paper titled 'CKConv: Continuous Kernel Convolution For Sequential Data'. The motivation behind that is to propose a model that uses the properties of co 6 min read CNN | Introduction to Pooling LayerPooling layer is used in CNNs to reduce the spatial dimensions (width and height) of the input feature maps while retaining the most important information. It involves sliding a two-dimensional filter over each channel of a feature map and summarizing the features within the region covered by the fi 5 min read CNN | Introduction to PaddingDuring convolution, the size of the output feature map is determined by the size of the input feature map, the size of the kernel, and the stride. if we simply apply the kernel on the input feature map, then the output feature map will be smaller than the input. This can result in the loss of inform 5 min read What is the difference between 'SAME' and 'VALID' padding in tf.nn.max_pool of tensorflow?Padding is a technique used in convolutional neural networks (CNNs) to preserve the spatial dimensions of the input data and prevent the loss of information at the edges of the image. It involves adding additional rows and columns of pixels around the edges of the input data. There are several diffe 14 min read Convolutional Neural Network (CNN) ArchitecturesConvolutional Neural Network(CNN) is a neural network architecture in Deep Learning, used to recognize the pattern from structured arrays. However, over many years, CNN architectures have evolved. Many variants of the fundamental CNN Architecture This been developed, leading to amazing advances in t 11 min read Deep Transfer Learning - IntroductionDeep transfer learning is a machine learning technique that utilizes the knowledge learned from one task to improve the performance of another related task. This technique is particularly useful when there is a shortage of labeled data for the target task, as it allows the model to leverage the know 8 min read Introduction to Residual NetworksRecent years have seen tremendous progress in the field of Image Processing and Recognition. Deep Neural Networks are becoming deeper and more complex. It has been proved that adding more layers to a Neural Network can make it more robust for image-related tasks. But it can also cause them to lose a 4 min read Residual Networks (ResNet) - Deep LearningAfter the first CNN-based architecture (AlexNet) that win the ImageNet 2012 competition, Every subsequent winning architecture uses more layers in a deep neural network to reduce the error rate. This works for less number of layers, but when we increase the number of layers, there is a common proble 9 min read ML | Inception Network V1Inception net achieved a milestone in CNN classifiers when previous models were just going deeper to improve the performance and accuracy but compromising the computational cost. The Inception network, on the other hand, is heavily engineered. It uses a lot of tricks to push performance, both in ter 4 min read Understanding GoogLeNet Model - CNN ArchitectureGoogLeNet (Inception V1) is a deep convolutional neural network architecture designed for efficient image classification. It introduces the Inception module, which performs multiple convolution operations (1x1, 3x3, 5x5) in parallel, along with max pooling and concatenates their outputs. The archite 3 min read Image Recognition with MobilenetImage Recognition plays an important role in many fields like medical disease analysis and many more. In this article, we will mainly focus on how to Recognize the given image, what is being displayed. What is MobilenetMobilenet is a model which does the same convolution as done by CNN to filter ima 4 min read VGG-16 | CNN modelA Convolutional Neural Network (CNN) architecture is a deep learning model designed for processing structured grid-like data such as images and is used for tasks like image classification, object detection and image segmentation.The VGG-16 model is a convolutional neural network (CNN) architecture t 6 min read Autoencoders in Machine LearningAutoencoders are a special type of neural networks that learn to compress data into a compact form and then reconstruct it to closely match the original input. They consist of an:Encoder that captures important features by reducing dimensionality.Decoder that rebuilds the data from this compressed r 8 min read How Autoencoders works ?Autoencoders is used for tasks like dimensionality reduction, anomaly detection and feature extraction. The goal of an autoencoder is to to compress data into a compact form and then reconstruct it to closely match the original input. The model trains by minimizing reconstruction error using loss fu 6 min read Difference Between Encoder and DecoderCombinational Logic is the concept in which two or more input states define one or more output states. The Encoder and Decoder are combinational logic circuits. In which we implement combinational logic with the help of boolean algebra. To encode something is to convert in piece of information into 9 min read Implementing an Autoencoder in PyTorchAutoencoders are neural networks designed for unsupervised tasks like dimensionality reduction, anomaly detection and feature extraction. They work by compressing data into a smaller form through an encoder and then reconstructing it back using a decoder. The goal is to minimize the difference betwe 4 min read Generative Adversarial Network (GAN)Generative Adversarial Networks (GAN) help machines to create new, realistic data by learning from existing examples. It is introduced by Ian Goodfellow and his team in 2014 and they have transformed how computers generate images, videos, music and more. Unlike traditional models that only recognize 12 min read Deep Convolutional GAN with KerasDeep Convolutional GAN (DCGAN) was proposed by a researcher from MIT and Facebook AI research. It is widely used in many convolution-based generation-based techniques. The focus of this paper was to make training GANs stable. Hence, they proposed some architectural changes in the computer vision pro 9 min read StyleGAN - Style Generative Adversarial NetworksStyleGAN is a generative model that produces highly realistic images by controlling image features at multiple levels from overall structure to fine details like texture and lighting. It is developed by NVIDIA and builds on traditional GANs with a unique architecture that separates style from conten 5 min read Object Detection and RecognitionDetect an object with OpenCV-PythonObject detection refers to identifying and locating objects within images or videos. OpenCV provides a simple way to implement object detection using Haar Cascades a classifier trained to detect objects based on positive and negative images. In this article we will focus on detecting objects using i 4 min read Haar Cascades for Object Detection - PythonHaar Cascade classifiers are a machine learning-based method for object detection. They use a set of positive and negative images to train a classifier, which is then used to detect objects in new images. Positive Images: These images contain the objects that the classifier is trained to detect.Nega 3 min read R-CNN - Region-Based Convolutional Neural NetworksTraditional Convolutional Neural Networks (CNNs) with fully connected layers often struggle with object detection tasks, especially when dealing with multiple objects of varying sizes and positions within an image. A brute-force method like applying a sliding window across the image to detect object 8 min read YOLO v2 - Object DetectionIn terms of speed, YOLO is one of the best models in object recognition, able to recognize objects and process frames at the rate up to 150 FPS for small networks. However, In terms of accuracy mAP, YOLO was not the state of the art model but has fairly good Mean average Precision (mAP) of 63% when 7 min read Face recognition using Artificial IntelligenceThe current technology amazes people with amazing innovations that not only make life simple but also bearable. Face recognition has over time proven to be the least intrusive and fastest form of biometric verification. The software uses deep learning algorithms to compare a live captured image to t 15+ min read Deep Face RecognitionDeepFace is the facial recognition system used by Facebook for tagging images. It was proposed by researchers at Facebook AI Research (FAIR) at the 2014 IEEE Computer Vision and Pattern Recognition Conference (CVPR). In modern face recognition there are 4 steps: DetectAlignRepresentClassify This app 8 min read ML | Face Recognition Using Eigenfaces (PCA Algorithm)In 1991, Turk and Pentland suggested an approach to face recognition that uses dimensionality reduction and linear algebra concepts to recognize faces. This approach is computationally less expensive and easy to implement and thus used in various applications at that time such as handwritten recogni 4 min read Emojify using Face Recognition with Machine LearningIn this article, we will learn how to implement a modification app that will show an emoji of expression which resembles the expression on your face. This is a fun project based on computer vision in which we use an image classification model in reality to classify different expressions of a person. 7 min read Object Detection with Detection Transformer (DETR) by FacebookFacebook has just released its State of the art object detection Model on 27 May 2020. They are calling it DERT stands for Detection Transformer as it uses transformers to detect objects.This is the first time that transformer is used for such a task of Object detection along with a Convolutional Ne 7 min read Image SegmentationImage Segmentation Using TensorFlowImage segmentation is a computer method that breaks up a picture into different parts. It looks at the small details of each pixel (the tiny dots that make up the image) and decides what kind of thing it is like a pet, the pet’s outline or the background. The main goal is to give every pixel in a pi 5 min read Thresholding-Based Image SegmentationImage segmentation is the technique of subdividing an image into constituent sub-regions or distinct objects. The level of detail to which subdivision is carried out depends on the problem being solved. That is, segmentation should stop when the objects or the regions of interest in an application h 7 min read Region and Edge Based SegmentationSegmentation Segmentation is the separation of one or more regions or objects in an image based on a discontinuity or a similarity criterion. A region in an image can be defined by its border (edge) or its interior, and the two representations are equal. There are prominently three methods of perfor 4 min read Image Segmentation with Watershed Algorithm - OpenCV PythonImage segmentation is a fundamental computer vision task that involves partitioning an image into meaningful and semantically homogeneous regions. The goal is to simplify the representation of an image or make it more meaningful for further analysis. These segments typically correspond to objects or 9 min read Mask R-CNN | MLThe article provides a comprehensive understanding of the evolution from basic Convolutional Neural Networks (CNN) to the sophisticated Mask R-CNN, exploring the iterative improvements in object detection, instance segmentation, and the challenges and advantages associated with each model. What is R 9 min read 3D ReconstructionPython OpenCV - Depth map from Stereo ImagesOpenCV is the huge open-source library for the computer vision, machine learning, and image processing and now it plays a major role in real-time operation which is very important in today’s systems.Note: For more information, refer to Introduction to OpenCV Depth Map : A depth map is a picture wher 2 min read Top 7 Modern-Day Applications of Augmented Reality (AR)Augmented Reality (or AR), in simpler terms, means intensifying the reality of real-time objects which we see through our eyes or gadgets like smartphones. You may think, How is it trending a lot? The answer is that it can offer an unforgettable experience, either of learning, measuring the three-di 10 min read Virtual Reality, Augmented Reality, and Mixed RealityVirtual Reality (VR): The word 'virtual' means something that is conceptual and does not exist physically and the word 'reality' means the state of being real. So the term 'virtual reality' is itself conflicting. It means something that is almost real. We will probably never be on the top of Mount E 3 min read Camera Calibration with Python - OpenCVPrerequisites: OpenCV A camera is an integral part of several domains like robotics, space exploration, etc camera is playing a major role. It helps to capture each and every moment and helpful for many analyses. In order to use the camera as a visual sensor, we should know the parameters of the cam 4 min read Python OpenCV - Pose EstimationWhat is Pose Estimation? Pose estimation is a computer vision technique that is used to predict the configuration of the body(POSE) from an image. The reason for its importance is the abundance of applications that can benefit from technology. Human pose estimation localizes body key points to accu 7 min read 40+ Top Computer Vision Projects [2025 Updated] Computer Vision is a branch of Artificial Intelligence (AI) that helps computers understand and interpret context of images and videos. It is used in domains like security cameras, photo editing, self-driving cars and robots to recognize objects and navigate real world using machine learning.This ar 4 min read Like