When most people think of scanning facial images, chances are their thought process will immediately go to facial recognition technology. After all, it’s the most common use case we hear about today: millions of people unlock their smartphones with facial recognition, and anyone watching crime dramas on TV has seen the technology used multiple times. occasions.
The truth is that while facial recognition is one use case for image scanning, it’s not the only one. Countless new use cases are emerging as scanning technology improves, which it must do for more advanced applications that require detailed and highly accurate imaging. Let’s face it, how accurate is your phone’s imaging software if it can be unlocked with a photo, or if a son’s face can unlock his father’s phone?
This is where this challenge lies. How do you take digitization to the next level so you can build advanced applications for healthcare and other verticals? The truth is, it’s not about the image itself, it’s about what you do with the data in the image.
IKIN has been revolutionizing imaging for many years with its holography technology. It brought small and large format helmetless holography to market with a number of use cases. Last year, it demonstrated its technology and officially launched its IKIN academic program for content developers at ITEXPO.
IKIN’s holography is of course dependent on image scan data. So when the company was approached to solve a specific problem during the COVID-19 pandemic, they accepted and rose to the challenge.
Cosmetic companies naturally have to put their products through rigorous testing to understand their effects over time. This is time-consuming and requires detailed views of test subjects’ faces and skin, a process that has become impossible during the pandemic. Of course, high resolution images could be taken, but 2D images are not able to identify small changes in the soft body structure of the face – the level of detail required for cosmetic testing, for example.
A cosmetics company turned to IKIN to help solve the challenge with a solution that would work under all circumstances. IKIN had developed its Cubara dimensional scanning platform which could extract highly accurate image data from high-resolution photos or videos. This data is fed into a convolutional neural network (CNN) that decomposes single images to create a 3D point cloud of the face – or any object.
CNN is used to decompose single images based on a large pool of pre-trained data for object recognition. In this system, a custom CNN is generated at the initial scan point. High-resolution live video is converted to frame-by-frame frame-by-frame scans that provide 98% or greater frame overlap. Subsequently, from the same extracted library, a photogrammetry model and a high resolution mesh are generated and stored with the initial archive. This model is decomposed into an 18-point skeleton based on the formation of CNNs and understanding which points are valuable to the system.
IKIN photogrammetry – the science of making measurements from photographs – using AI and CNNs overcomes the challenges of accurate and repeatable scanning due to the inconsistency of capture and poor rotation compensation.
“I’m impressed with how Cubara is using its CNN to achieve more accurate, error-free, and repeatable analytics,” said Rich Tehrani, CEO of TMC.
But aggressive scanning — called orthomosaic diagnosis — is only part of the story. Once you have the 3D image and data, it all depends on what you can do with it.
“It’s not the ability to scan, but the ability to detect change and use AI and analytics to predict change over time that’s really the big story,” the CEO said. ‘IKIN, Joe Ward.
The detection of Cubara’s diagnostic functions can detect the smallest changes in point cloud measurements, which correlate with changes over time on the scanned object. This includes changes not visible to the naked eye. Thanks to the highly accurate point cloud and 3D facial rendering, the cosmetics company was able to continue testing and, in fact, is likely able to achieve better results than before.
“IKIN’s Cubara scanning technology appears to be as advanced as their hologram technology which has continually impressed us for many years,” noted Tehrani, who first got a glimpse of IKIN’s technology. in 2019.
The cosmetics usage case barely scratches the surface of what IKIN can do with Cubara. The implications are almost endless once you have the ability to create such high density point clouds from images.
As Ward noted, “We really focused on scanning the face and creating something unique that will be able to be positioned across multiple verticals. If you can scan a face, you can scan pretty much n’ whatever.
This is especially true when you consider Cubara’s ability to create 3D models from 2D footage. In healthcare, for example, providers can use technology to examine the condition of wounds over time, where a CNN can be created for each wound to show that it is changing over time.
Industry can use it to better understand wear and damage to mechanical parts by creating temperature maps and understanding stress points in turbine blades, engines and other equipment. Manufacturers and customers can much more accurately predict when products need to be replaced without having to wait for them to break down, avoiding costly downtime and eliminating risk due to malfunction. Even clothing manufacturers can better understand how long their products and different materials will last under various conditions.
“We were just doing scanning for a company for clinical research,” said Taylor Scott, IKIN CTO. “We can use the same skill set for everything on the planet, anywhere you want to see how patterns emerge or change over time.”
As the world continues to digitize, the ability to take contextual data – especially from 2D tools – and create accurate and detailed 3D representations, and then being able to extrapolate the change data brings real-world scenarios in the virtual world to drive process and product improvements across industries.
“Cubara’s dimensional sweep is quite impressive,” Tehrani concluded. “It’s the perfect bridge between the physical and digital worlds.”
Indeed, with the metaverse set to change the way we interact in professional and personal environments, the ability to create highly accurate and realistic representations will redefine the way we perceive virtual environments. Instead of interacting in a cartoon-like virtual world, we may soon be visiting virtual worlds that are much more like the real world.
This connection becomes evident when you think about combining IKIN’s technologies. Once you import Cubara’s data and 3D models into IKIN’s Ryz or Arc holographic platforms, we envision a whole new world of games, training, education, testing and development, and so many other applications – even communications. In fact, with IKIN’s technology, we’re closer than you might think to real-world gesture-based interactivity – think Minority Report – where people can take 3D models and move them around naturally, without bulky and uncomfortable glasses.
“Our mission is to evolve the human-machine interface so that it is more comfortable and creates an emotional connection,” Scott said. “The key is not just a new interface, but a new way of capturing the world. Much of the metaverse is going to capture the world in 3D.
Edited by Erik Linask