Description Of Computer Vision Transparently!

The human vision had started billions of years ago when small organisms developed a mutation that made them sensitive to light. Today, life is abundant on the planet which all have very similar visual systems. They include eyes for capturing light, receptors in the brain for accessing it, and visual cortex for processing it.



In the past 30 years, we've made even more strides to extending this amazing visual ability, not just to ourselves, but to machines as well. The first type of photographic camera was invented around 1816 where a small box held a piece of paper coated with silver chloride. When the shutter was open, the silver chloride would darken where it was exposed to light. Now, 200 years later, we have much more advanced versions of the system that can capture photos right into digital form.


So, we've been able to closely mimic how the human eye can capture light and color. But it's turning out that that was the easy part. Understanding what's in the photo is much more difficult. Consider a picture of the flower, the human brain can look at it and immediately know that it's a flower. Our brains are cheating since we've got a couple million years' worth of evolutionary context to help immediately understand what this is.


But a computer doesn't have that same advantage. To an algorithm, the image looks like this, just a massive array of integer values that represent intensities across the color spectrum. There's no context here, just a massive pile of data. It turns out that the context is the crux of getting algorithms to understand image content in the same way that the human brain does. And to make this work, we use an algorithm very similar to how the human brain operates using machine learning.

Machine learning allows us to effectively train the context for a data set so that an algorithm can understand what all those numbers in a specific organization represent.

What if we have images that are difficult for a human to classify? Can machine learning achieve better accuracy?

For example, let's take images of sheepdog and mops where it's pretty hard, even for us, to differentiate between the two. With the machine learning model, we can take a bunch of images of sheepdogs and mops, and as long as we feed it enough data, it will eventually be able to properly tell the difference between the two.

Computer vision is taking on increasingly complex challenges and is seeing accuracy that rivals' humans performing the same image recognition tasks. The specific type of neural network that accomplishes this, is called a convolutional neural network or CNN.


What is Computer Vision?

Computer vision (CV), which is one of the most popular artificial intelligence technologies. Artificial intelligence could recognize a person and a small number of objects. Recognition quality will significantly improve:

  • AI can recognize even an abstractly drawn object.

  • AI will recognize emotions (neutral, angry, happy, sad, surprised).

  • AI will learn to distinguish people by gender (male, female).

  • AI will be able to detect a human's age.

All this is made possible due to the hard and meticulous work of our programmers, developers, and data scientists.

CNN's work by breaking an image down into smaller groups of pixels called a filter. Each filter is a matrix of pixels, and the network does a series of calculations on these pixels comparing them against pixels in a specific pattern the network is looking for. In the first layer of a CNN, it can detect high-level patterns like rough edges and curves. As the network performs more convolutions, it can begin to identify specific objects like faces and animals.



How does CNN know what to look for? and if its prediction is accurate?

This is done through a large amount of labeled training data. When CNN starts, all of the filter values are randomized. As a result, its initial predictions make little sense. Each time the CNN predicts labeled data, it uses an error function to compare how close its prediction was to the image's actual label. Based on this error or loss function, the CNN updates its filter values and starts the process again. Ideally, each iteration performs with slightly more accuracy.


What if instead of analyzing a single image, we want to analyze a video using machine learning?

At its core, a video is just a series of image frames. To analyze a video, we can build on our CNN for image analysis. In still images, we can use CNNs to identify features. But when we move to video, things get more difficult since the items we're identifying might change over time. Or, more likely, there's a context between the video frames that' highly important to labeling.

For example, if there's a picture of a half-full cardboard box, we might want to label it packing a box or unpacking a box depending on the frames before and after it. This is where CNN's come up lacking. They can only take into account spatial features, the visual data in an image, but can't handle time features. How a frame is related to the one before it. To address this issue, we have to take the output of our CNN and feed it into another model that can handle the temporal nature of our videos.


This type of model is called a recurrent neural network or RNN. While CNN treats groups of pixels independently, an RNN can retain information about what it's already processed and use that in its decision making. RNNs can handle many types of input and output data. In this example of classifying videos, we train the RNN by passing it a sequence of frame descriptions-- empty box, open box, closing box, and finally, a label-- packing.

As the RNN processes each sequence, it uses a loss or error function to compare its predicted output with the correct label. Then it adjusts the weights and processes the sequence again until it achieves higher accuracy. The challenge of these approaches to image and video models, however, is that the amount of data we need to truly mimic human vision is incredibly large.


If we train our model to recognize this picture of a duck, as long as we're given this one picture with this lighting, color, angle, and shape, we can see that it's a duck. But if you change any of that or even just rotate the duck, the algorithm might not understand what it is anymore. Now, this is the big picture problem. To get an algorithm to truly understand and recognize image content the way the human brain does, you need to feed it incredibly large amounts of data of millions of objects across thousands of angles all annotated and properly defined.

The problem is so big, that if you're a small startup or a company lean on funding there're just no resources available for you to do that. This is why technologies like Google Cloud Vision and Video can help. Google digests and filters millions of images and videos to train these APIs.

#artificialintelligence #machinelearning #ai #ml #aiml #algorithm #CNN #human vision #data

#RNN #computervision #humanbrain #model #imagerecognition #classification #datascience

#googlecloudvision #APIs #dataanalytics #computerscience #programming #prediction

#advancedai #technews #python #digitalformation #innovations #bigdata #ibm #engineering

#crazztlearners #2020Blog #projects #research #ainews #technology

  • CREATED BY ANMOL VARSHNEY & PALAK GUPTA