Skip navigation
Hi! Welcome to our 12th blog post. This would be the final blog post, which will talk about putting it all together to form a harmonious system.   The whole idea behind making this project (and this challenge) was to create an idea which would have some real-world weight for people less fortunate than us. We wanted to build a project which was capable of bringing at least a tiny bit of convenience for those people, and today we're proud to say that we've reached to the end with a device th ...
Hi! Welcome to our 11th blog post. In this post, we will talk about the Arduino MKR1000, its primary functions and the GET/POST requesting done by it.   First, let's talk about what all the Arduino has to do, It has to: Capture an image using the Camera Store the image in the SD Card Upload the image to the server Wait for the processing to end Retrieve the processed .wav file and store it in the SD card Play the .wav file using the speaker   All this logic is handled by 4 prim ...
Welcome to our 10th blog post! In this blog, we'll be talking about a python library, called TTS (Text-to-Speech).   Image captioning is all good and great until we realize that a caption is just a string - it still requires eyes to be read! A visually handicapped person won't find any information in such data as he won't be able to see it in the first place. Clearly, we need to convert the mode of communication from ocular to auditory - and this is where the TTS library comes in.   ...
Welcome to our 9th blog post! In this update we are going to guide you through the process to play .wav files on the MKR1000. The components we have used are -   Arduino MKR1000 PAM 8403 Amplifier (5V with Potentiometer) Speaker (4 Ohms, 3 Watts) Jumper cables                                        ...
Welcome to our 8th blog post! Today, we'll be uploading and deploying our Show and Tell model on a local server, uploading an image and getting the caption.   In order to create a web application, we'll be using a Python microframework called Flask. Flask is a well-known and well-documented micro web framework which acts as a backend for any website. Many large websites like Pinterest, LinkedIn, etc. use Flask in their backend.   Flask mainly revolves around a python file, which cont ...
Welcome to our seventh blog post! We are back with our newest camera module from ArduCAM which is a cracking improvement over the OV7670 that we used for testing the Deep Learning model in the last blog post.   This is called the ArduCAM Mini 2MP which is technically a shield housing the OV2640, a 2 MP image sensor that would normally come with 16 pins on its own without the shield. The advantage of this shield is that it simplifies the number of pins of the module to just 6 from the abo ...
Welcome to our sixth blog post! Apologies for the delay in blogging, we were stuck with some logistics problem with the camera unable to be imported into India from its manufacturer. It took us a lot of time just to procure this camera and we have ordered a better and hopefully last camera for this project, which should arrive in a few days.   In this post, we will describe our experience with the OV7670 Arducam used with Arduino Uno to take pictures and save it to a computer's disk. This ...
Welcome to our fifth blog post! This blog will be a little short, as we're essentially posting an update on the last blog.   We mentioned the Show and Tell model in that blog, and talked about its structure and capabilities of the model. We also mentioned that we will increase the number of iterations as well as finetune the model a little.   First, the outputs from the older model:   This model was trained for 1 million iterations. Now, we trained a new model, this time wit ...
Welcome to our fourth blog post! Today we'll be looking at a potential model for our use-case, the Show and Tell model. The Show and Tell model is a neural image caption generator- It is a deep neural network that learns how to describe the content of input images. e.g.   The Show and Tell model can be broken down into two blocks: the encoder, and the decoder. The encoder is a CNN, which takes an image, performs convolutional operations on it, and outputs a vectorized representation of ...
Welcome to our third blog post! This is just a quick update about our successful setup of SD card using SD Proto Shield and WiFi on Arduino MKR1000.   The aim of this setup was to test the SD Proto Shield along with the WiFi connectivity of the MKR1000. The shield was installed on the MKR1000, and the standard ReadWrite sketch of SD card library was uploaded to the Arduino via USB. The results found are posted below -   Next up we tested the WiFi functionality along with SD card by ...
Welcome to our second blog post! In this blog, we would like to post our progress and findings so far. Over the years, Convolutional Neural Networks, ConvNets, or CNNs have been the top choice for image processing and recognition applications. The main advantage of CNNs compared to other image classification algorithms was that the filters that were hand-engineered in traditional algorithms were learnt by the CNNs themselves, saving a lot of effort and time. Since other models benefited by inc ...
We would like to start off the proceedings by thanking Element14 and Arduino for giving us an opportunity to build a project that can impact a massive segment of the population. We hope that it will benefit a lot of people who need something like this and we pledge our full devotion towards this endeavour.   This is the first blog post so I would like to introduce everyone to our product design and plan of action. AUDIO4VISION is a project for the visually impaired, be it those who are co ...