 Hello everyone! Welcome back to our channel. I hope you all are safe and sound. From our previous video, you know that you can now make cool artificial intelligence and machine learning projects with our very own PictoBlocks, a graphical programming software based on Scratch blocks. This project is based on one of those cool features. One of the many amazing things that AI can do is recognize objects from images or webcam. We can see it in video surveillance, self-driving cars and at many other places. In this video, we will make a project to call the number of objects and recognize their dimension and type from the image. Pre-requisites are a PC or a computer with latest version of PictoBlocks downloaded, a good internet connection and your choice of image. You can download the image which we have used from the link given in the description box below. Let's begin by adding the object detection extension. Open PictoBlocks. First, select evive as board. Next, click on the add extension button. Once clicked, you will be able to see all the extensions available. To use the extensions of artificial intelligence and machine learning, you need to first sign in to PictoBlocks. Select object detection extension and wait for a little while till the models get loaded. Let's add the square box sprite into the project. Click on the add sprite button. Choose the square box sprite. You can delete toby sprite simply by right clicking on it and select delete from the drop down. Now as we will be detecting objects from the images on the stage, let's add a couple of them as backdrop. Click on choose the backdrop button and click upload. Choose the images of your choice. Now click on the square box sprite to write the script. Drag and drop the when flag clicked heart block to execute the program every time the green flag is clicked. Next, let's process the imaginary stage. Add the analyze image from the camera block and select stage from the drop down menu. Now let's create a variable to store the object count. Click on make a variable button inside the variable palette. Make a variable with the name object and click on OK. Set the object as 0. Now as we need to detect all the objects, add a repeat until block. Drag and drop an equal to block from the operator's palette inside the hexagonal space of the repeat until block. Now to acquire the number of objects from the images, use the get number of objects block inside the first space of the equal to block and place the variable object reporter block into the second empty space. To display the properties of all detected objects one by one, we need to increment our variable by one each time we execute our control logic. Next, set the size of the square box to accommodate the object detected. Drag and drop the set size to block from the looks palette. Add width of object block inside it. Drop the object reporter block into the space given. Next, to move our square box to the location of the object, add go to x and y block from the motion palette. Insert to x position of object block from the object detection palette and choose x position and y position from the respective blocks to obtain the x and y value of the object respectively. Finally, to display the class of recognized object, get the say block from the looks palette and make it say the class of the detected objects. With this, the script is ready. Click on the green flag and watch the magic happen. You can test how many objects it can recognize by trying out different images. Share your results with us by posting your projects in our PictoBlocks community on Facebook. Also, if you like this video, give it a thumbs up and don't forget to subscribe to STEMpedia and follow us on Facebook, Instagram and Twitter. Bye-bye, stay safe.