# Implementing a simple RNN

In this post we will be implementing two simple Recurrent Neural Networks (RNN) one for classification and the other for regression tasks.

### Classification using RNN

It takes in a binary number and returns the XOR of the number. For example if the input is 10110 then it should output 11011, as Continue reading

# Create your own Object Detector

Creating a custom object detector was a challenge, but not now. There are many approaches for handling object detection. Of all, Haarcascades and HOG+SVM are very popular and best known for their performance. Though Haarcascades which were introduced by Viola and Jones are good in achieving decent accuracy, HOG+SVM proved to outperform the Haarcascades implementation. Here in this post we are going to build a object detector using HOG+SVM model. The output from our detector is something similar as shown below.

# Object Tracking

Object Tracking has been a challenging problem in the field of computer vision and lots of new techniques are being invented. In this post we build an end-to-end object tracker using two simple techniques to track an object in a video stream. The outcome of the project might looks like as shown below.

# Sudoku Solver – 2

In the last post we discussed how to extract the sudoku region from the captured frame of a live stream and then we applied perspective transform to the extracted region and then we slide a window through each cell and recognized the digits in the cells. Now in this post we discuss how to solve the sudoku puzzle using Backtracking algorithm. There are several approaches to solve the sudoku puzzle. For example, you can find some of them in this paper.

Though there are several approaches to solve it, let’s stick to the traditional backtracking algorithm to solve the puzzle. For our understanding, just have a look at how the sudoku is presented below.

A sample sudoku puzzle