All language subtitles for 001 Different Computer Vision Tasks

In this video.

We'll explain some of the tasks that are often performed by computer vision.

First image classification.

Image classification is the process of determining the category of an image based on the objects in

it.

The input image classification is an image with one object.

What the output is, what object is in the input image with its probability value.

There is also a localization.

Localization perform classification coupled with determining the location of the object in the form

of a bonding box.

Next object detection.

The main purpose of object detection is to predict the location of objects with bounding boxes and classify

objects in each bounding box.

The input to object detection is an image containing one or more objects.

The output is the prediction of the location of the object with the bounding box and the classification

of the object for each bounding box.

Next Image segmentation.

Image segmentation is a further extension of object detection.

Object detection only predicts the bounding box of the object.

While in image segmentation, we can find out the shape of the object.

There are two types of segmentation instant segmentation and semantic segmentation.

Instant segmentation recognizes an object's boundaries and labels its pixels with a different color.

Semantic segmentation assigns a different color to each pixel in the image, including the background

based on the results of the object classification.

From YOLO.

If you want to YOLO, physics can only be used on object detection.

YOLO v seven can be used for object detection and instant segmentation.

The YOLO v seven is also planning to make YOLO seven semantic segmentation in the near future.

See you then.