RSS
 

Posts Tagged ‘technology’

Adobe Photoshop Elements and Premiere Elements 2022 announced with new Sensei-powered technology

07 Oct

Adobe has announced the 2022 versions of its Photoshop Elements and Premiere Elements software. The applications are designed to make creative photo and video editing accessible and fun.

To that end, Photoshop Elements and Premiere Elements include what Adobe calls ‘Guided Edits.’ These are step-by-step interactive tutorials you can use on your photos and videos to achieve specific editing tasks. The new applications add four new Guided Edits, bringing the total to 87.

There’s a new Guided Edit in Photoshop Elements 2022 for editing pet photos. Credit: Adobe

The four new Guided Edits include a couple in Photoshop Elements, and the other two are in Premiere Elements. In Photoshop Elements, you can use a new Guided Edit to edit pet photos and extend photo backgrounds. For pet photos, you can adjust color and lighting, select and refine detailed edges like fur, remove collars and leashes and more. In the Guided Edit for extending photo backgrounds, you can use Content-Aware Fill technology to extend your image beyond its original crop, either to change an aspect ratio or just change up the framing.

Using Content-Aware Fill, you can extend the background of your photo. Credit: Adobe

In Premiere Elements, there’s a new Guided Edit to add animated overlays to your videos, such as fun butterfly animations. The other new Guided Edit shows you how to adjust shadows and highlights in your video, allowing you to bring out additional details.

Looking now at just Photoshop Elements 2022, the new software uses more Adobe Sensei AI technology than last year’s release. You can use Adobe Sensei to transform your photographs into painting-inspired images. You can select from different artistic effects inspired by famous artwork and other popular styles.

Credit: Adobe

Another Sensei-powered feature is the ability to warp photos to fit any shape. You can place one photo inside another by wrapping it around an object, like a mug, or fit the image into shapes, like the sunglasses example above.

Within Photoshop Elements 2022, you can combine still and motion photography with animated frames. You can place different moving overlays like snowflakes, hearts and sparkles to your still photos and then export the motion image as an .MP4 to share on social media.

Adobe Photoshop Elements 2022 also includes new slideshow styles, a revised Organizer that lets you view GIFs in motion, and automatic software updates.

Premiere Elements 2022 includes animated overlays. Credit: Adobe

Adobe Premiere Elements 2022 includes new aspect ratio options. Many users share videos on social media, which sometimes includes vertical video and square aspect ratios. In Premiere Elements, you can edit and export videos in social-friendly formats without losing content. You can also add motion titles, mattes and backgrounds designed for vertical videos.

Premiere Elements 2022 includes new aspect ratio options for editing and exporting. Using these ratios doesn’t affect your original video file. Credit: Adobe

Another new tool is Sensei-powered auto-reframe. This tool allows the software to automatically re-frame your subject to ‘keep the most important part of the action in the frame.’

Premiere Elements 2022 includes a slider for video compression. If you’re editing and exporting a video for social media, you probably don’t need it to be a high-quality 4K video. Instead, you can use a compression slider in Premiere Elements to reduce the size of your movies, making them more suitable for uploading to the web or social media or sending to friends and family in a message.

Auto-reframe is powered by Adobe Sensei AI technology and keeps your subject front and center in different aspect ratios. Credit: Adobe

Adobe Photoshop Elements 2022 and Premiere Elements 2022 are available now. The applications are available for macOS and Windows and can be purchased standalone or in a bundle. Standalone versions are $ 99.99 for new users and $ 79.99 to upgrade. The bundle is $ 149.99 or $ 119.99 for eligible upgrades. Education pricing is also available. For the full details and to purchase the software, click here.

Articles: Digital Photography Review (dpreview.com)

 
Comments Off on Adobe Photoshop Elements and Premiere Elements 2022 announced with new Sensei-powered technology

Posted in Uncategorized

 

Google shares a deep dive into its new HDR+ with Bracketing technology found in its latest Pixel devices

26 Apr

Google has shared an article on its AI Blog that dives into the intricacies of the HDR capabilities of its most recent Pixel devices. In it, Google explains how its HDR+ with Bracketing technology works to capture the best image quality possible through clever capture and computational editing techniques.

To kick off the article, Google explains how its new ‘under the hood’ HDR+ with Bracketing technology — first launched on the Pixel 4a 5G and Pixel 5 back in October — ‘works by merging images taken with different exposure times to improve image quality (especially in shadows), resulting in more natural colors, improved details and texture, and reduced noise.’

Using bursts to improve image quality. HDR+ starts from a burst of full-resolution raw images (left). Depending on conditions, between 2 and 15 images are aligned and merged into a computational raw image (middle). The merged image has reduced noise and increased dynamic range, leading to a higher quality final result (right). Caption and image via Google.

Before diving into how the behind-the-scenes work is done to capture the HDR+ with Bracketing images, Google explains why high dynamic range (HDR) scenes are difficult to capture, particularly on mobile devices. ‘Because of the physical constraints of image sensors combined with limited signal in the shadows […] We can correctly expose either the shadows or the highlights, but not both at the same time.’

Left: The result of merging 12 short-exposure frames in Night Sight mode. Right: A single frame whose exposure time is 12 times longer than an individual short exposure. The longer exposure has significantly less noise in the shadows but sacrifices the highlights. Caption and image via Google.

Google says one way to combat this is to capture two different exposures and combine them — something ‘Photographers sometimes [do to] work around these limitations.’ While this works fairly well with cameras with larger sensors and more capable processors inside tablets and laptops to merge the images, Google says it’s a challenge to do on mobile devices because it requires ‘Capturing additional long exposure frames while maintaining the fast, predictable capture experience of the Pixel camera’ and ‘Taking advantage of long exposure frames while avoiding ghosting artifacts caused by motion between frames.’

Google was able to mitigate these issues with its original HDR+ technology through prioritizing the highlights in an image and using burst photography to reduce noise in the shadows. Google explains the HDR+ method ‘works well for scenes with moderate dynamic range, but breaks down for HDR scenes.’ As for why, Google breaks down the two different types of noise that get into an image when capturing bursts of photos: shot noise and read noise.

Google explains the differences in detail:

One important type of noise is called shot noise, which depends only on the total amount of light captured — the sum of N frames, each with E seconds of exposure time has the same amount of shot noise as a single frame exposed for N × E seconds. If this were the only type of noise present in captured images, burst photography would be as efficient as taking longer exposures. Unfortunately, a second type of noise, read noise, is introduced by the sensor every time a frame is captured. Read noise doesn’t depend on the amount of light captured but instead depends on the number of frames taken — that is, with each frame taken, an additional fixed amount of read noise is added.’

Left: The result of merging 12 short-exposure frames in Night Sight mode. Right: A single frame whose exposure time is 12 times longer than an individual short exposure. The longer exposure has significantly less noise in the shadows but sacrifices the highlights. Caption and image via Google.

As visible in the above image, Google highlights ‘why using burst photography to reduce total noise isn’t as efficient as simply taking longer exposures: taking multiple frames can reduce the effect of shot noise, but will also increase read noise.’

To address this shortcoming, Google explains how it’s managed to use a ‘concentrated effort’ to make the most of recent ‘incremental improvements’ in exposure bracketing to combined the burst photography component of HDR+ with the more traditional HDR method of exposure bracketing to get the best result possible in extreme high dynamic range scenes:

‘To start, adding bracketing to HDR+ required redesigning the capture strategy. Capturing is complicated by zero shutter lag (ZSL), which underpins the fast capture experience on Pixel. With ZSL, the frames displayed in the viewfinder before the shutter press are the frames we use for HDR+ burst merging. For bracketing, we capture an additional long exposure frame after the shutter press, which is not shown in the viewfinder. Note that holding the camera still for half a second after the shutter press to accommodate the long exposure can help improve image quality, even with a typical amount of handshake.’

Google explains how its Night Sight technology has also been improved through the use of its advanced bracketing technology. As visible in the illustration below, the original Night Sight mode captured 15 short exposure frames, which it merged to create the final image. Now, Night Sight with bracketing will capture 12 short and 3 long exposures before merging them, resulting in greater detail in the shadows.

Capture strategy for Night Sight. Top: The original Night Sight captured 15 short exposure frames. Bottom: Night Sight with bracketing captures 12 short and 3 long exposures. Caption and image via Google.

As for the merging process, Google says its technology chooses ‘one of the short frames as the reference frame to avoid potentially clipped highlights and motion blur.’ The remaining frames are then aligned with the reference frame before being merged.

To reduce ghosting artifacts caused by motion, Google says it’s designed a new spatial merge algorithm, similar to that used in its Super Res Zoom technology, ‘that decides per pixel whether image content should be merged or not.’ Unlike Super Res Zoom though, this new algorithm faces additional challenges due to the long exposure shots, which are more difficult to align with the reference frame due to blown out highlights, motion blur and different noise characteristics.

Left: Ghosting artifacts are visible around the silhouette of a moving person, when deghosting is disabled. Right: Robust merging produces a clean image. Caption and image via Google.

Google is confident it’s been able to overcome those challenges though, all while merging images even faster than before:

Despite those challenges, our algorithm is as robust to these issues as the original HDR+ and Super Res Zoom and doesn’t produce ghosting artifacts. At the same time, it merges images 40% faster than its predecessors. Because it merges RAW images early in the photographic pipeline, we were able to achieve all of those benefits while keeping the rest of processing and the signature HDR+ look unchanged. Furthermore, users who prefer to use computational RAW images can take advantage of those image quality and performance improvements.’

All of this is done behind the scenes without any need for the user to change settings. Google notes ‘depending on the dynamic range of the scene, and the presence of motion, HDR+ with bracketing chooses the best exposures to maximize image quality.’

Google’s HDR+ with Bracketing technology is found on its Pixel 4a 5G and Pixel 5 devices with the default camera app, Night Sight and Portrait modes. Pixel 4 and 4a devices also have it, but it’s limited to Night Sight mode. It’s also safe to assume this and further improvements will be available on Pixel devices going forward.

You can read Google’s entire blog post in detail on its AI blog at the link below:

HDR+ with Bracketing on Pixel Phones

Articles: Digital Photography Review (dpreview.com)

 
Comments Off on Google shares a deep dive into its new HDR+ with Bracketing technology found in its latest Pixel devices

Posted in Uncategorized

 

Halide developers break down the technology powering Apple’s new ProRAW image format

16 Dec

Apple’s new ProRAW format is now available to iPhone 12 Pro and 12 Pro Max users running iOS 14.3. The new format promises the power of Apple’s image processing capabilities with the flexibility of a Raw image. But what exactly is a ProRAW image, how useful is the format and what sort of results can we expect from it?

Ben Sandofsky, one of the developers behind the iOS camera app Halide, has answered all of those questions and more in a thorough overview of the ProRAW technology, with illustrations and example photos from Halide designer, Sebastiaan de With.

Sandofsky’s overview is effectively broken down into three parts. That first part explains how a digital camera ‘develops’ an image using the data from the sensor. The second part explains the pros and cons of traditional Raw files. And the third part is where we learn what’s unique about Apple’s ProRAW technology and why it ‘changes the game’ despite ‘its few remaining drawbacks.’

We suggest taking Sandofky’s advice and grabbing a coffee if you plan on reading the entire post, but we’ll summarize a few of the standout details here on DPReview as well in the case you’re in a rush or are out of coffee.

Since most DPReview readers are familiar with how a camera processes data from the sensor, as well as the pros and cons of Raw files, we’re going to skip right to Sandofky’s rundown of the new ProRAW technology from Apple.

Sandofsky gets straight to the point, answering a question we’ve seen a few people ask in the comments of previous articles on Apple’s new ProRAW technology — ‘Technically, there’s no such thing as a ProRAW file.’ ProRAW image files, as he explains, are simply regular DNG files that use little known features in the DNG file format specifications, as well as a few new features Apple worked with Adobe to implement in the new 1.6 specification.

Specifically, Adobe and Apple worked together to add a new set of tags for the open Raw format that enable much of what Apple is doing with its ProRAW-branded DNG files. In fact, the new DNG 1.6 specification went live the day Apple released the iOS 14.3 public beta, showing just how closely the two worked together on the new specification.

As Sandofsky points out, Apple opting to use the DNG format means, despite their attempt at rebranding the technology as its own Raw format, nothing about the resulting files is proprietary. The photos should, in theory, be able to work with any other device or program that chooses to make the most of the new DNG 1.6 standard.

Sandofsky goes on to state that ProRAW images store pixel values after the demosaic step. These demosaiced color values still contain all of the original colors and dynamic range of the scene, he says, they just cut out the step of choosing what demosaic algorithm will be used on that data—something usually done in post-processing based on the editing software you’re using.

Sandofsky argues that, aside from saving time and taking another step out of the equation, it’s ‘quite possible that iOS can do a better job demosaicing your images than any third-party RAW editor’ considering Apple’s strength of its vertical integration of hardware and softrware. That is, Apple ‘know[s] exactly the sensor you’re using, and how it behaves with different ISO settings.’ Sandofsky even points out that with Apple’s image recognition technology, iOS could apply a specific demosaic algorithm depending on the scene to achieve an optimal result.

One example he uses is a set of starscape images from photographer Austin Mann, who has also shared a detailed breakdown of the new ProRAW technology on his website alongside a beautiful collection of images.

A ProRAW file before and after editing.

Another benefit of this approach is Apple could, in theory, start to develop its own sensors, eschewing the current bayer sensors they use. By doing so, they could tailor-make the best sensor possible for their smartphones and as long as the resulting image is saved as a ProRAW file, ‘it would work from day one in every pro photography process and app like Lightroom without having to wait for Adobe to write a new demosaic algorithm’ for the new sensor.

Next, Sandofsky explains how Apple is baking in the ‘local tone mapping and other computational photography goodies’ right inside the DNG using the new tags found in the DNG 1.6 standard. By using the new tags, Apple is able to apply its Smart HDR and Deep Fusion technology to the ProRAW images. While Halide is opting to not use all of this technology — Sandofsky explains why in detail within his post — it’s still there to leverage in the image editor of your choice or use with another third-party camera app should the developers choose to. ProRAW images also store semantic maps — the depth data used in Portrait mode — which gives developers yet another piece of information to work with.

A comparison image showing the semantic maps of an image next to the original photo.

Sandofsky goes on to explain the file size flexibility of ProRAW files. A standard ProRAW file, captured with the default 12-bit data, is roughly 25MB. But it’s possible for developers to drop that to 10-bit, which roughly halves the file size while still getting ‘most of the ProRAW benefits.’ If that’s not small enough, it’s also possible for developers to use lossy compression on ProRAW files, which drops the files down to as little as 1MB, but as Sandofsky notes, this results in a ProRAW file that isn’t much more versatile than a standard 8-bit JPEG.

A list of Raw and ProRAW shooting options the Halide team has implemented into its camera app.

Another neat trick is that it’s possible to store a fully-processed JPEG version of an image directly inside the DNG file. Apple doesn’t do this by default in its iOS Camera app, third party developers can choose to do this, which would ensure apps that don’t support DNG files, such as Instagram, can still use the processed JPEG image. Halide says it’s added this option in its app, but do note it will add an extra 4MB or so to the file size, due to the extra baggage.

In conclusion, Sandofsky notes that ProRAW ‘is a leap forward for everyone, but it will be especially impactful for beginning photographers.’ With Apple supporting Raw editing directly in its iOS Photos app, even casual photographers will be able to have the flexibility of editing a ‘Raw’ file format — even if they’re not using more advanced editing apps such as Affinity Photo, Adobe Lightroom, Capture One, etc.

Sandofsky wraps up his post talking about how the Halide team is further pushing the boundaries of ProRAW with its app, but we’ll let you read that over on the full post, linked below. You can download the Halide camera app in the iOS App Store.

Understanding ProRAW


Image credits: All images and illustrations by Halide, used with permission.

Articles: Digital Photography Review (dpreview.com)

 
Comments Off on Halide developers break down the technology powering Apple’s new ProRAW image format

Posted in Uncategorized

 

Xiaomi announces retractable lens technology for future smartphones

06 Nov
Xiaomi has introduced its self-developed Retractable Wide-aperture Lens Technology at its annual developer conference. Image credit: Xiaomi

Chinese technology company Xiaomi has officially kicked off its annual Mi Developer Conference (MIDC 2020) in Beijing. During the conference, Xiaomi has showcased numerous new technologies and breakthroughs, including retractable wide-aperture lens technology for smartphone devices.

If you have been following along with new smartphone announcements over the last few years, you’ll have noticed a strong emphasis on improvements in image quality, camera performance and lens quality. Drawing inspiration from traditional camera and lens design, Xiaomi has developed new Retractable Wide-aperture Lens Technology. This advancement in design lodges a compact optical structure in the smartphone, which can be extended when necessary.

Xiaomi promises that this new design will result in a breakthrough in performance. The company states, ‘This design allows the retractable telescopic camera to have a larger aperture to increase the amount of light input by 300%, as well as showcase better performance in portrait photography and night photography compared to currently-used camera structures.’ Further, the design incorporates a new image stabilization technology which ‘offers a larger anti-shake angle’ and increases sharpness by 20%.

The telescoping design has the primary benefit of allowing a camera not in use to be compact and easy to slip into a pocket, while still offering optical zoom when in use and capturing photos. In the case of a smartphone and its camera design, it’s even more critical to consumers that the device remain thin, compact, and lightweight.

Retractable lens designs have most frequently been seen in fixed-lens compact cameras, such as the Sony ZV-1 seen above. By utilizing a retractable lens design, engineers can strike a balance between performance when the camera is in use and a compact form factor when you aren’t capturing images.

Photography advancements from Xiaomi have been fast and furious this year despite the impact of the pandemic. This August, Xiaomi introduced its 3rd-generation under-display camera, which promised a high-quality, hidden camera under the smartphone’s display. This technology relies upon a revised pixel arrangement solution, allowing light to pass through gaps between the sub-pixels in the display.

Xiaomi’s advancements in camera technology don’t exist solely in the future. To celebrate its 10th anniversary this summer, Xiaomi launched the Mi 10 Ultra smartphone. This device incorporates a quad-camera array, including a long telephoto lens which offers a 120mm equivalent focal length and includes a 48MP image sensor. On the wide end of its camera array, there is a 12mm equivalent focal length and 20MP image sensor.

The Xiaomi Mi 10 Ultra smartphone, introduced this August, highlights the company’s fast-paced camera technology advancements with its 12mm and 120mm cameras. Click to enlarge.

It remains to be seen what the real-world performance of a telescoping lens in a smartphone will be, but Xiaomi intends to utilize its new camera technology in upcoming smartphones. The company’s goal is to deliver ‘professional photography to hundreds of millions of smartphone users around the world’ with its expanding portfolio of image technology improvements.

Articles: Digital Photography Review (dpreview.com)

 
Comments Off on Xiaomi announces retractable lens technology for future smartphones

Posted in Uncategorized

 

DxO announces PhotoLab 4 with new DeepPRIME AI technology

22 Oct

It’s been a busy week for photo editing software announcements. The day after Adobe announced the latest versions of Lightroom and Photoshop, DxO has joined the party with its announcement of DxO PhotoLab 4.

PhotoLab 4 includes numerous new features and improvements, but the highlight is DxO’s new DeepPRIME technology. DeepPRIME utilizes artificial intelligence to perform improved demosaicing and denoising in a single step. DxO has used machine learning and millions of images to train the DeepPRIME algorithm. The result is that all images, particularly those captured at high ISO settings or with smaller sensors, will look better than ever before. DxO also states that photos captured with early-generation cameras will experience a pronounced gain in overall quality.

A traditional approach to processing raw images comprises demosaicing and noise reduction separately. However, with DeepPRIME and its deep learning, these two steps are combined into one ‘to deliver exceptional performance.’ Compared to DxO’s previous denoising algorithm, DxO PRIME, DeepPRIME ‘delivers a gain of around two ISO sensitivity values at a comparable level of quality.’

Of DeepPRIME, Jérôme Ménière, DxO’s CEO, says, ‘There are a number of applications for DxO DeepPRIME. [It] creates new creative opportunities by helping expert photographers overcome digital noise or a lack of light. For amateur photographers, DxO DeepPRIME compensates the drawbacks of the smaller sensors on compact and bridge cameras, which can typically only take high-quality images in bright light. Lastly, it can also be used to revamp photos taken by less advanced cameras from the start of the digital era.’ The idea of breathing new life into old images is certainly appealing and it will be interesting to see how much of an improvement DeepPRIME delivers.

DxO’s new DeepPRIME algorithm promises improved performance and image quality compared to the former DxO PRIME tech. DxO states that the most noticeable gains will be experienced when working with high ISO images and photos captured using small or older image sensors. Image credit: DxO

In addition to the new DeepPRIME technology, DxO PhotoLab 4 incorporates a new workspace, dubbed DxO Smart Workspace. The workspace is centered around a system of filters accessible via the toolbar. DxO describes it as follows, ‘It allows users to show tool palettes by correction type, only display their pre-selected favorite palettes, or only show palettes with activated corrections.’ You can also utilize a dedicated search field to locate a specific tool. DxO states that the new workspace will not only allow experienced PhotoLab users to work more efficiently, but it will also allow new users to acclimate to the software and its available tools more quickly.

Another workflow improvement includes the ability to batch rename multiple files at once. This can be achieved via the DxO PhotoLibrary or Photo Browser. You simply select multiple files and then use a dedicated dialog box to rename the files.

The new DxO Smart Workspace promises improved access to image editing tools plus a new search function, allowing experienced and novice users alike to track down a specific tool. Image credit: DxO

There’s a new History palette in DxO PhotoLab 4 as well. This displays all edits in chronological order and shows the specific edits made to an image, allowing you to go back at any time to a specific change you made to your image. For example, if you adjust exposure, it will show this adjustment and the amount that exposure was adjusted. Adjustments can also be grouped by type and then hidden if you don’t need to see the full list.

Similarly, PhotoLab 4 allows the user to selectively copy and paste edits across multiple selected images. DxO states, ‘From the Photo Browser, users can select the specific edits they want to apply to one or several other images by editing type, such as lighting, color, detail, local adjustments, geometry, or watermarking.’

In order to protect your images when sharing them online, PhotoLab 4 includes a new Instant Watermarking feature. You can embed text and/or an image on selected photos simultaneously and get a live preview of the watermarking. You can adjust placement, scale, orientation, opacity, and margins. There are also seven available blend modes, something DxO says is unique to PhotoLab 4.

DxO believes its new Instant Watermarking tool is the best in the business. Image credit: DxO

More than 60,000 camera and lens combinations are supported in PhotoLab 4, including new camera support for the following cameras: Canon EOS R5, EOS R6, and EOS 850D, the Nikon D6 and Z5; the Olympus OM-D E-M10 Mark IV; and the Panasonic Lumix S5 cameras.

DxO PhotoLab 4 is available now from DxO on Windows and macOS. Until November 19, DxO is offering promotional prices. DxO PhotoLab 4 Essential Edition is available for $ 99.99 USD and the Elite Edition is $ 149.99. This represents a savings of around $ 30 and $ 50, respectively. Existing owners of PhotoLab 3 can purchase an upgrade license by signing into their customer account on this webpage. You can also download a fully-functional one-month trial. For more information, visit DxO.

Articles: Digital Photography Review (dpreview.com)

 
Comments Off on DxO announces PhotoLab 4 with new DeepPRIME AI technology

Posted in Uncategorized

 

Microsoft’s latest computer vision technology beats humans at captioning images

16 Oct
Seeing AI. Photo by Microsoft

Microsoft has expanded its existing efforts to improve life for the visually impaired by developing an AI system capable of automatically generating high-quality image captions — and, in ‘many cases,’ the company says its AI outperforms humans. This type of technology may one day be used to, among other things, automatically caption images shared online to aid those who are dependent on computer vision and text readers.

Computer vision plays an increasingly important role in modern systems; at its core, this technology enables a machine to view, interpret and ultimately comprehend the visual world around it. Computer vision is a key aspect of autonomous vehicles, and it has found use cases in everything from identifying the subjects or contents of photos for rapid sorting and organization to more technical use cases like medical imaging.

In a newly published study [PDF], Microsoft Researchers have detailed the development of an AI system that can generate high-quality image captions called VIsual VOcabularly (VIVO), which is a pre-training model that learns a ‘visual vocabulary’ using a dataset of paired image-tag data. The result is an AI system that is able to create captions describing objects in images, including where the objects are located within the visual scene.

Test results found that at least in certain cases, the AI system offers new state-of-the-art outcomes while also exceeding the capabilities of humans tasked with captioning images. In describing their system, the researchers state in the newly published study:

VIVO pre-training aims to learn a joint representation of visual and text input. We feed to a multi-layer Transformer model an input consisting of image region features and a paired image-tag set. We then randomly mask one or more tags, and ask the model to predict these masked tags conditioned on the image region features and the other tags … Extensive experiments show that VIVO pre-training significantly improves the captioning performance on NOC. In addition, our model can precisely align the object mentions in a generated caption with the regions in the corresponding image.

Microsoft notes alternative text captions for images are an important accessibility feature that is too often lacking on social media and websites. With these captions, individuals who suffer from vision impairments can use dictation technology to read the captions, giving them insight into the image that they may otherwise be unable to see.

The company previously introduced a computer vision-based product described specifically for the blind called Seeing AI, which is a camera app that audibly describes physical objects, reads printed text and currency, recognizes and reports colors and other similar things. The Seeing AI app can also read image captions — assuming captions were included with the image, of course.

Microsoft AI platform group software engineering manager Saqib Shaikh explained:

‘Ideally, everyone would include alt text for all images in documents, on the web, in social media – as this enables people who are blind to access the content and participate in the conversation. But, alas, people don’t. So, there are several apps that use image captioning as a way to fill in alt text when it’s missing.’

That’s where the expanded use of artificial intelligence comes in. Microsoft has announced plans to ship the technology to the market and make it available to consumers through a variety of its products in the near future. The new AI model is already available to Azure Cognitive Services Computer Vision customers, for example, and the company will soon add it to some of its consumer products, including Seeing AI, Word and Outlook for macOS and Windows, as well as PowerPoint for Windows, macOS and web users.

Articles: Digital Photography Review (dpreview.com)

 
Comments Off on Microsoft’s latest computer vision technology beats humans at captioning images

Posted in Uncategorized

 

Video: How Kodak became yet another victim of the juggernaut of changing technology

27 Sep

The Eastman Kodak Company, better known as Kodak, was co-founded by George Eastman and Henry A. Strong way back in 1888. In the more than 130 years since, the company has been through a lot. It once was a dominant force in the photography industry, at times being almost as synonymous with photography as the Apple iPod once was with respect to music. For all but the youngest in society, we have all heard the phrase, ‘Kodak moment.’

However, with the advent of digital photography, Kodak began to lose its place at the forefront of photography. Interestingly, Kodak itself patented the first handheld digital camera in 1978, eventually shelving the product in order to better preserve its film business. With the benefit of hindsight, we can see that Kodak created its own demise a few decades in advance.

Believing in the long-term viability of a predominantly analog photography industry, Kodak missed critical opportunities to diversify, a mistake Fujifilm didn’t make, as is evidenced by the Japanese company’s impressive lineup of digital photography cameras and lenses.

Kodak’s meteoric rise to near-total market dominance and the precipitous fall from grace is a fascinating story. The Wall Street Journal recently produced a short documentary covering the story of Kodak, which can be viewed below. The video begins with the origins of the company before ramping up to Kodak’s prime and its eventual decline.

In Kodak’s heyday, the company focused on creating simple and easy-to-use still and video cameras for everyday people. This goal, one the company had long met successfully, resulted in Kodak employing more than 145,000 people in 1988. It was Kodak’s best-ever year. At the time, Fujifilm was the biggest threat to Kodak’s business. In 1989, Fujifilm managed to capture an 11% share of the U.S. film market. The next few years saw Kodak’s position of power further eroded, and the company brought in a new CEO from outside in an attempt to right the slowly sinking ship.

Kodak’s digital camera shipments in the United States from 2008 through 2011. Image credit: The Wall Street Journal. Data credit: IDC.

Losses continued to pile up and jobs were cut as Kodak moved to a new CEO at the turn of the 21st century. Kodak continued to produce new digital photography product and jumped into new product sectors, such as printers, but Kodak was fighting a losing battle. The advent of smartphone photography added further difficulties for Kodak, as no longer were consumers as inclined to buy a dedicated camera to capture life’s most important moments. No longer was there a desire to create ‘Kodak moments.’

Kodak’s stock prices have trended very downward since 2014. Image credit: Wall Street Journal. Data credit: Factset.

Eventually, the financial challenges became too great and Kodak shuttered its camera business and filed for bankruptcy in 2012. However, the story of Kodak didn’t end there. Desperate times call for desperate measures. Kodak began licensing its very identity, resulting in the Kodak name being plastered on many different products. Kodak even made a cryptocurrency in 2018. However, its stock price kept falling.

With the ongoing coronavirus pandemic, Kodak found a new opportunity to pivot. On July 28, President Trump announced Kodak would receive a $ 765M government loan under the Defense Production Act. Kodak, a company long known for producing products using its chemical expertise, is poised to move into pharmaceuticals. Trump’s announcement sent Kodak stock skyrocketing. However, the deal is currently being held up as the US Securities and Exchange Commission (SEC) investigates the deal and Kodak itself for insider trading.

Kodak is far from the only company that has faltered in the digital age of photography. However, Kodak may be one of the most famous examples of how changing photographic technology can sink a company.

Articles: Digital Photography Review (dpreview.com)

 
Comments Off on Video: How Kodak became yet another victim of the juggernaut of changing technology

Posted in Uncategorized

 

Profoto’s new A10 speedlight works with smartphones via AirX Bluetooth technology

24 Sep

Profoto has unveiled the A10, its third and latest round-head speedlight in its A1 lineup. Much like the A1X was nearly identical to the A1, the A10 is effectively an A1X with built-in Bluetooth and AirX technology for making the most of the speedlight, even with a smartphone.

Profoto showed off its AirX technology back in July with its B10 and B10 Plus monolights, and more recently, its C1 and C1 Plus LED lights, but until now, it wasn’t available for its speedlights. The A10 changes that, making it easier to get pro-level lighting with your smartphone when using the compatible Profoto app (Android, iOS). Of course, the A10 will also work with other DSLR and mirrorless camera systems with dedicated models for Canon, Fujifilm, Nikon and Sony cameras.

Aside from the new AirX Bluetooth syncing, none of the specifications have changed from the A1X. It features the same round-head design with support for Profoto’s Click Light Shaping tools, a large hi-res display for changing settings and navigating the menu, an LED modeling light, a maximum 76Ws output, a recycle time between 0.05–1 second and a built-in Li-ion battery rated for up to 450 full-power flashes.

Below is a video walkthrough of the A10 from Profoto:

The Profoto A10 is currently available to purchase for $ 1,095 (Adorama, B&H, Wex). Be sure to select the correct model for your camera brand when making a purchase. All units come with the flash, an included Li-ion battery, a charger, a dome diffuser, a bounce card, a stand, a dedicated bag and Profoto’s two-year limited warranty.

Articles: Digital Photography Review (dpreview.com)

 
Comments Off on Profoto’s new A10 speedlight works with smartphones via AirX Bluetooth technology

Posted in Uncategorized

 

Apple patent shows its working on panoramic light field capture technology

04 Apr

A newly-published Apple patent, filed back in September 2019, details a light field panorama camera system seemingly intended for use in future iPhone and iPad devices. The technology would enable the average consumer to capture large light field panoramas of a particular scene by moving their device using gestures. The resulting content could be rendered and viewed on the device or using some type of head-mounted display (HMD), including VR headsets.

According to Patently Apple, which first spied the patent, Apple details technology that would build upon its current AR efforts by enabling its consumer devices to capture complex 3D scenes. To do this, the user would need to move their light field-equipped iPhone or iPad in a gesture, such as moving the device in a swooping infinity symbol, to capture light field images of the environment from multiple angles.

A flow-chart provided within the patent filing that shows the process of capturing, processing and viewing the resulting imagery.

A rendering engine would process the individual images into a 3D panorama with six degrees of freedom (6DOF) made possible using the light field technology. As a result, the viewer would have the ability to look above and behind objects, zoom in on areas of the scene and view different angles of the environment. The patent follows Google’s acquisition of light field camera technology company Lytro in 2018.

Unlike conventional cameras, a light field camera system captures both the intensity of the light from a scene and the direction the light rays are traveling in space. The additional data gathered by light field camera systems enable new types of experiences, including the one detailed by Apple.

The patent indicates that Apple’s system may use the sensors in the iPhone and iPad to capture position, motion and other similar metadata alongside the images, the combination of which would contribute to the final light field panorama. The combination of captured images and metadata could then be used to render different views of the same 3D scene, according to the patent, ultimately giving the user six degrees of freedom for exploring the panorama using an HMD like a VR headset.

This would differ substantially from a traditional 360-degree panorama, which is captured from a single point, only allowing the viewer to move their head around within the rendered 3D scene. Light field panoramas will appear more realistic, keeping objects in their correct positions as the user moves around within the scene, which could realistically render from different angles as the user has a look around.

It’s no secret that Apple has been heavily focusing on augmented reality technologies; its most recent iPad Pro model underscores this effort with the inclusion of a LIDAR sensor.

Just a few of the possible movements you could use to capture the scenery using your Apple mobile device.

In its announcement of the 2020 iPad Pro last month, Apple said the new LIDAR sensor ‘delivers cutting-edge depth-sensing capabilities, opening up more pro workflows and supporting pro photo and video apps,’ specifically with augmented reality in mind. The sensor works by measuring the distance of objects that are as far as 5m (16ft) away.

Apple went on to explain:

‘New depth frameworks in iPadOS combine depth points measured by the LiDAR Scanner, data from both cameras and motion sensors, and is enhanced by computer vision algorithms on the A12Z Bionic for a more detailed understanding of a scene. The tight integration of these elements enables a whole new class of AR experiences on iPad Pro.’

The future expansion of these capabilities using light field technology wouldn’t be surprising, particularly in light of ongoing rumors Apple is working on AR/VR gear. With that said, and as with any patent, it is possible we’ll never see this technology make its way into a consumer product. Per usual, Apple has not commented on the patent.

Articles: Digital Photography Review (dpreview.com)

 
Comments Off on Apple patent shows its working on panoramic light field capture technology

Posted in Uncategorized

 

Samsung files trademark for its ‘Nonacell’ technology destined for its 108MP sensor

09 Feb

Back in December, a rumor went around that Samsung’s Galaxy S11+ smartphone will use a new 108-megapixel sensor with ‘Nonacell’ technology. Not much is known about the sensor still, but it seems the rumor holds a little more clout now that Samsung has officially trademarked the ‘Nonacell’ nomenclature.

As first discovered by Dutch technology site LetsGoDigital, Samsung has filed a trademark in the United Kingdom for the ‘Nonacell’ name. As addressed in our initial coverage, ‘nona’ is Latin for ‘nine.’ As such, it’s expected that Samsung’s ‘Nonacell’ technology will use a three-by-three color filter array to merge nine pixels into a single, larger one. If combined with the much-anticipated 108MP ISOCELL Bright HMX sensor, the ‘Nonacell’ technology would yield a 12MP still.

Plenty of details remain about the rumored S11+ smartphone from Samsung, but we shouldn’t have to wait much longer with the series expected to launch sometime this month.

Articles: Digital Photography Review (dpreview.com)

 
Comments Off on Samsung files trademark for its ‘Nonacell’ technology destined for its 108MP sensor

Posted in Uncategorized