Hi ! In my previous post I wrote How to create a custom dataset with images to be used on a Azure Machine Learning Designer project. How to use the custom data set and how to train an image classification model. How to publish the model to be used as a WebService / HTTP REST…… Continue reading #AzureML – Sample 🐍 Python app using a WebCam to perform Image Analysis from an image classification AzureML HTTP REST Endpoint
Hi ! Let’s start with some posts using reTerminal with a very simple scenario: Install TensorFlow and Code on reTerminal to run an object recognition app. The desired output is something similar to this one. Live demo in a tweet ! https://twitter.com/elbruno/status/1481002326110445572?s=20 And let´s start with the base commands to install Visual Studio Code. Oficial…… Continue reading #reTerminal – Installing TensorFlow, @Code and recognizing 🐿️🐺 using a Camera 🤳
Hi ! Let’s start with some posts using reTerminal with a very simple scenario: Connect a Camera to the device and show the camera feed in reTerminal display The output is something similar to this one. And let´s start with the base code to run this, based on my previous posts on OpenCV (see references)…… Continue reading #reTerminal – Installing OpenCV, and using a USB WebCam 🤳
Hi ! Quick Friday Tip: How to add a new camera to your PC using an old Android phone. No wires required. So, In my device demos I usually have my main camera with my 😁, and I have a 2nd USB cam to show specific demos or devices. I had a green screen on…… Continue reading #OBS – Use an Android phone 🤳 as an external webcam 🎦. No cables required !
Hi ! LearnOpenCV is an amazing resource to learn about OpenCV. And, it has lot of scenarios of real life problem solved with OpenCV. Most of the samples are in C++ or Python, so I decided to pick one related to pose estimation, and using .Net 5 in a Winforms App, build something like this:…… Continue reading #dotnet – Pose detection from the 🎦 camera feed using #OpenCV and #net5. Home-made #kinect!
Hi ! So I was browsing in the OpenCV documentation and I find a nice sample that uses opencv_dnn module for image classification by using GoogLeNet trained network from Caffe model zoo. So I give it a try, and get a decent .Net 5 Winforms App running at ~30 FPS. The model was trained with…… Continue reading #dotnet – GoogleNet detection from the 🎦 camera feed using #OpenCV and #net5. Bonus: C++ to C# time!
Hi ! Face detected, so next step is to use some prebuild models to perform additional actions: like estimate the Age of a face, and also the Gender. In order to do this, I downloaded a couple of models from here. Disclaimer: these models are just sample models, do not use them in production. These…… Continue reading #dotnet – Age and Gender estimation from the 🎦 camera feed using #OpenCV and #net5
Hi ! In one session around computer vision, someone ask the question about which approach is better Haar Cascades or DNN? And the answer can be show using the video below As you can see Haar Cascades works great for faces looking directly to the camera, with good lights and in optimal conditions. However, once…… Continue reading #dotnet – Detecting Faces, DNN vs Haar Cascades from the 🎦 camera feed using #OpenCV and #net5
Hi ! Let’s do some face detection using a DNN model (See references). As yesterday, I won’t write about details, there are almost 20 years of online documentation available. And, IMHO opinion code is much more useful that long writing, so let’s go there. 1st load the Caffe model and the config file. // download…… Continue reading #dotnet – Detecting Faces using DNN from the 🎦 camera feed in a WinForm using #OpenCV and #net5
Hi ! Let’s do some face detection using one of the most popular methods: Haar Casacades (See references). I won’t write about Cascades, there are almost 20 years of online documentation available. And, IMHO opinion code is much more useful that long writing, so let’s go there. 1st load the cascade definition file. _faceCascade =…… Continue reading #dotnet – Detecting Faces using Cascades from the 🎦 camera feed in a WinForm using #OpenCV and #net5