Computer-Vision

Datasets

1. COCO 2017 Dataset
2. COCO 2017 Object Detection Dataset
3. COCO 2014 Dataset (for YOLOv3): The MS COCO (Microsoft Common Objects in Context) dataset is a large-scale object detection, segmentation, key-point detection, and captioning dataset. The dataset consists of 164K images.
4. The official homepage of the COCO-Stuff dataset:
5. YOLO: Real-Time Object Detection: You only look once (YOLO) is a state-of-the-art, real-time object detection system. On a Pascal Titan X it processes images at 30 FPS and has a mAP of 57.9% on COCO test-dev.
6. The Complete Playing Card Dataset: This dataset can be a good start for a Computer Vision Beginner. The dataset contains 53 classes and approximately 50 images for each class and the labels are in the Pascal-VOC format, COCO format and YOLO format.
7. Guitar Transcription Dataset: It aims to provide well labeled training data for the purposes of developing automated guitar transcription.
8. American Sign Language Detection using Deep Learning: The users of American Sign Language range somewhere between 250,000 to 500,000 persons. But most of the communication happens among the persons suffering from deafness and those who have learned the American Sign Language. If someone who is not proficient wants to have communication, then he or she needs someone who has learned the American Sign Language. There are experts in sign language who act as moderators between the person who is verbally speaking the disabled person who is using the sign language

Tutorials

1. OPENCV PYTHON TUTORIALS FOR BEGINNERS

2. YOLO: You Only Look Once — is an extremely fast multi object detection algorithm which uses convolutional neural network (CNN) to detect and identify objects.

3. ASL