Computer vision
Computer vision
Computer vision is a branch of artificial intelligence (AI) that allows computers and systems to extract useful information from digital photos, videos, and other visual inputs, as well as to conduct actions or make suggestions based on that data. If artificial intelligence allows computers to think, computer vision allows them to see, watch, and comprehend.
Human vision is similar to computer vision, with the exception that people have a head start. Human vision benefits from lifetimes of context to teach it how to distinguish objects apart, how far away they are if they are moving, and whether something is incorrect with a picture.
Computer vision teaches computers to execute similar tasks, but using cameras, data, and algorithms rather than retinas, optic nerves, and a visual brain, it must do it in a fraction of the time. Because a system trained to check items or monitor a production asset can assess hundreds of products or processes per minute, detecting faults or issues that are invisible to humans, it may swiftly outperform humans.
How does computer vision work?
A lot of data is required for computer vision. It repeats data analysis until it detects distinctions and, eventually, recognises pictures. To teach a computer to recognise automotive tyres, for example, it must be fed a large number of tyre photos and tire-related materials in order for it to understand the distinctions and recognise a tyre, particularly one with no faults.
Machine learning is a technique that allows a computer to train itself about the context of visual input using algorithmic models. If enough data is supplied into the model, the computer will “look” at the data and learn to distinguish between images. Instead of someone training the machine to recognise an image, algorithms allow it to learn on its own.
The history of computer vision
For almost 60 years, scientists and engineers have been attempting to find ways for robots to comprehend and analyse visual input. In 1959, neurophysiologists presented a cat a series of pictures in order to see whether it could correlate a reaction in its brain. They noticed that it responded to hard edges or lines initially, implying that picture processing begins with basic forms such as straight edges.
The first computer image scanning technology was created about the same time, allowing computers to digitise and capture images. In 1963, computers were able to convert two-dimensional pictures into three-dimensional shapes, marking yet another milestone. AI became an academic topic of study in the 1960s, and it also marked the start of the AI search.
Computer vision applications
In the subject of computer vision, there is a lot of research being done, but it isn’t simply researched. Computer vision is critical in business, entertainment, transportation, healthcare, and everyday life, as demonstrated by real-world applications. The deluge of visual information streaming from smartphones, security systems, traffic cameras, and other visually instrumented devices is a primary driver for the expansion of these applications. This information might be extremely useful in a variety of businesses, but it is currently underutilised. The data serves as a training ground for computer vision applications as well as a launchpad for them to integrate into a variety of human activities:
- For the 2018 Masters golf event, IBM employed machine vision to produce My Moments. After watching hundreds of hours of Masters film, IBM Watson was able to recognise the sights (and sounds) of key scenes. These pivotal moments were chosen and distributed to viewers as individual highlight clips.
- With Google Translate, users can aim their smartphone camera at a sign in another language and get a translation in their favourite language practically instantly.
- Computer vision is used in the development of self-driving vehicles to interpret the visual data from the car’s cameras and other sensors. Other automobiles, traffic signs, lane markings, pedestrians, bicycles, and every other visual information seen on the road must all be identified.
- With partners like Verizon, IBM is bringing sophisticated AI to the edge and assisting automobile makers in identifying quality flaws before a vehicle leaves the plant.
Computer vision examples
Many firms lack the financial means to establish computer vision laboratories and develop deep learning models and neural networks. They may also be unable to handle large amounts of visual input due to a lack of computer capability. IBM, for example, is assisting by providing computer vision software development services. These services provide cloud-based pre-built learning models while also reducing the demand for computer resources. Users utilise an application programming interface (API) to access the services and use them to create computer vision applications.
Here are a few examples of established computer vision tasks:
- Image classification
- Object detection
- Object tracking
- Content-based image retrieval