Mnist Redesign for Object Detection

Inspired by my another paper[3], neural network can detect location and size,so it can do object detection task. I redesign the mnist dataset, to produce different location and different size. Through test on new mnist dataset, the rectangle of number is all right both on absolute function and relu function. The classification accuracy is 97%-98%, the accuracy of location of rectangle is 99%-100%. It is easy for location task than for classification task. It is easy to distinguish black and white for one object, but RGB picture is harder to distinguish. Because the role of neural network is like a function. The location task can achieved by neural network as long as the problem can be expressed by a function. The task can be done as long as there is enough data and enough network complexity. The whole task is suit to study object detection.When we use lidar, the picture we got is like the gray picture listed before, we just to classify and locate the way we can drive through, so one object should be classified and located, the accuracy is high.