More AI-powered Features Coming To Skylum Luminar 4

Skylum Luminar 4

After AI Sky Replacement and AI Structure there is more artificial intelligence to be featured in the upcoming Skylum Luminar 4 (learn more): AI-powered portrait and skin enhancements.

What is Portrait Enhancer?

Portrait Enhancer is a collection of tools that help improve the photo of any person in a natural, yet pleasing way. These tools are brand new to Luminar 4 making it now possible to highlight and improve primary features of a person’s face.

What is AI Skin Enhancer?

Thanks to the AI technology, faces and skin are automatically detected throughout a photo. AI Skin Enhancer allows photographers to automatically remove various skin imperfections like acne, freckles and moles, in addition to smoothing the skin. At the same time, skin pores and other small details like hair and eyelashes are preserved.

Click on the images below for some samples, or learn more on the Skylum Luminar 4 page.

You can pre-order Skylum Luminar 4 at a special early bird price.

The actual version, Luminar 3, can be purchased with an exclusive $10 discount by using code WATCH at checkout.

More about the AI portrait and skin enhancements after the break.

Click here to open the rest of the article

Another AI Powered Feature Is Coming To Skylum Luminar 4, AI Structure

Skylum Luminar 4

The upcoming Skylum Luminar 4 seems to become a pretty powerful photo editing software.

After unveiling a preview of the AI Sky Replacement feature, Skylum teases another Luminar 4 feature powered by artificial intelligence algorithms, AI Structure. The 1 minute video below introduces the feature.

You can pre-order Skylum Luminar 4 at a special early bird price.

The actual version, Luminar 3, can be purchased with an exclusive $10 discount by using code WATCH at checkout.

Skylum Luminar 4 AI Structure explained:

Content-aware

Boosting details with traditional Clarity and Structure tools often make parts of a photo look horrible. Luminar 4 automatically identifies objects (including people and faces, clouds, water, buildings and more) and improves them in an intelligent, content-aware way.

Human-aware

The AI Structure tool automatically detects people in a photo and doesn’t overprocess them. As a result – faces and skin look natural, while the objects around them looks deeper and richer.

No noise, no halos, no artifacts

AI Structure is excellent at improving dynamic range and adding texture and clarity. What’s even better – it doesn’t add noise, halos or other artifacts.

No manual selections needed

There’s no need to make a selection. You don’t have to use layers or masks. In traditional editors, you cou

Canon security cameras deliver real-time analysis of emotions, report

Security Cameras

Canon is investing in artificial intelligence systems. Here is another application.

Nikkei Asian Review reports:

TOKYO — A Canon unit is launching a new security camera system that performs double duty, providing surveillance while also enhancing customer service.

Canon Marketing Japan’s system analyzes facial expressions in real time — a feature envisioned as a marketing tool allowing retailers and entertainment venues to interpret customers’ reactions moment by moment.

The technology detects three emotions — joy, sadness and anger — as well as age and gender. Software analyzes footage sent to the cloud, automatically tracking and charting the level of a particular emotion as a percentage.

A theater, for instance, could monitor an audience to see when and how often they laughed. Canon MJ expects plenty of business from relatively small retailers, such as supermarkets, along with amusement parks and other clients that want detailed insight into customer satisfaction.

The technology is being launched under the company’s cloud-based image management service, VisualStage, with emotion analysis software developed by Tokyo-based security imaging company Aroba.

Read the article at Nikkei Asian Review.

Canon working on AI powered predictive camera control system, patent suggests

Another pretty interesting patent that shows how much Canon is investing in research. Canon patent application US20180077345 discusses a predictive camera control system that takes viewers interests into account, for instance during a sport event.

Such a system is capable to recognise where people in a stadium is looking, what captures their interest most at a given time, and then can adjust its cameras to point in the same direction. A system that learns from user behaviour what gets the most attention by the viewers. This AI powered system (using neural networks) tracks the eyes of the viewers to learn where they are looking at, and is able to recognise which player attracts most looks from viewers. The system’s cameras are then set to capture what captures the interest of the crowd. I guess this may change the rules for future coverage of big sport events (but the system can virtually be used also for other purposes).

From the patent literature:

A computer-implemented method and system of selecting a camera angle is described. The method comprises determining a visual fixation point of a viewer of a scene using eye gaze data from an eye gaze tracking device; detecting, from the eye gaze data, one or more saccades from the visual fixation point of the viewer, the one or more saccades indicating a one or more regions of future interest to the viewer; selecting, based on the detected one or more saccades, a region of the scene; and selecting a camera angle of a camera, the camera capturing video data of the selected region using the selected angle.

[…] A system, comprising: an eye gaze tracking device for detecting eye gaze data of a viewer of a scene; a multi-camera system configured to capture video data of the scene; a memory for storing data and a computer readable medium; and a processor coupled to the memory for executing a computer program, the program having instructions for: detecting, using the eye gaze tracking data, a visual fixation point of the viewer and one or more saccades of the viewer relative to the visual fixation point; determining an object of interest in the scene based on at least the detected one or more saccades of the viewer, the object of interest being determined to have increasing relevance to the viewer of the scene; and selecting a camera of the multi-camera system, the selected camera having a field of view including the determined object of interest in the scene, the second camera capturing video data of the determined object of interest.

US20180077345A1

More Canon patents.