[url]https://S E N S O R@ringlayer/convolutional-neural-network-for-object-recognition-and-detection-126a22af8975[/url]


Basically computer vision has 4 main tasks :
1. Object Recognition/Classification
Classify the object in the image.

[img]https://miro.S E N S O Rmax/286/0*njUGkQnEGpI9YhxF[/img]


2.Object Detection
Are there any object that we want to detect in the image? If yes, draw the bounding box around the image

[img]https://miro.S E N S O Rmax/201/0*xM1WIDKG9euh1KAf[/img]


3. Object Localization
Are there any object that we want to detect in the image? If yes, draw the bounding box around the image and show the coordinate of the bounding box.

[img]https://miro.S E N S O Rmax/201/0*EbJFvL-PonDfL1EB[/img]


The (x1, y1) would be the top left corner and the (x2, y2) the bottom right.
And finally … the latest one :
4. Object Segmentation

[img]https://miro.S E N S O Rmax/300/0*SAhXI5jScCCIlnZG[/img]

By accommodating mask rcnn, we can get the exact pixel position for each object. This kind of development is very important for robotic vision.


Continue Reading at

[url]https://S E N S O R@ringlayer/convolutional-neural-network-for-object-recognition-and-detection-126a22af8975[/url]