𝐂𝐎𝐌𝐏𝐔𝐓𝐄𝐑 𝐕𝐈𝐒𝐈𝐎𝐍 is a field of artificial intelligence that trains computers to interpret and understand the visual world. Using digital images from cameras and videos and deep learning models machines can accurately identify and classify objects and then react to what they "see". It is the field of computer science that focuses on replicating parts of the complexity of the human vision system and enabling computers to identify and process objects in images and videos.
𝑪𝑶𝑴𝑷𝑼𝑻𝑬𝑹 𝑽𝑰𝑺𝑰𝑶𝑵 𝑺𝑬𝑹𝑰𝑬𝑺
Image classification is used to categorize whether an object is present in the likelihood of an image. Feature extraction is a part of the dimensionality reduction process, in which, an initial set of the raw data is divided and reduced into more manageable groups. Image classification is the process of categorizing and labeling groups of pixels or vectors within an image based on specific rules.
OpenMMLab Image Classification Toolbox and Benchmark
Python 2027 Version:v1.0.0rc5 License: Permissive (Apache-2.0)
PyTorch implementation of image classification models for CIFAR-10/CIFAR-100/MNIST/FashionMNIST/Kuzushiji-MNIST/ImageNet
Python 1204 Version:Current License: Permissive (MIT)
Train the HRNet model on ImageNet
Python 870 Version:PretrainedWeights License: Permissive (MIT)
TensorFlow implementation of GoogLeNet and Inception for image classification.
Python 268 Version:Current License: Permissive (MIT)
PyTorch implementation of "WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation", CVPR 2017
Python 241 Version:Current License: Permissive (MIT)
Object Detection is used to recognize the object with a bounding box in an image. Object detection is an important computer vision task used to detect instances of visual objects of certain classes (for example, humans, animals, cars, or buildings) in digital images such as photos or video frames. The goal of object detection is to develop computational models that provide the most fundamental information needed by computer vision applications.
Object Detection API Tensorflow
Python 274 Version:Current License: Permissive (MIT)
A PyTorch Implementation of Single Shot MultiBox Detector
Python 4883 Version:Current License: Permissive (MIT)
Frontend and backend separated object detection demo build with Flask, TensorFlow.
Python 82 Version:Current License: Permissive (MIT)
Yolov3 Object Detection implemented as APIs, using TensorFlow and Flask
Python 326 Version:Current License: Permissive (Apache-2.0)
AutoGluon: AutoML for Image, Text, and Tabular Data
Python 4341 Version:v0.4.0 License: Permissive (Apache-2.0)
Instance Segmentation is identifying each object instance for every known object within an image. Instance segmentation assigns a label to each pixel of the image. Instance segmentation is the task of detecting and delineating each distinct object of interest appearing in an image.
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
Python 10541 Version:v2.6.0 License: Permissive (Apache-2.0)
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
Python 9098 Version:v0.1 License: Permissive (MIT)
A simple, fully convolutional model for real-time instance segmentation.
Python 4681 Version:Current License: Permissive (MIT)
The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.
Python 1186 Version:Current License: Permissive (MIT)
🖍️ LabelImg is a graphical image annotation tool and label object bounding boxes in images
Python 15699 Version:v1.8.1 License: Permissive (MIT)