Blog

Have you ever tried to take a perfect vacation photo in Toronto, only to find your friend’s face is a mysterious smudge and the CN Tower looks like it’s melting? Blur has a way of sneaking into our lives, and it is everywhere. Sometimes it is more fascinating than you might think.

The smudge you see in your photo is blur. Blur has existed since the first camera was invented because film or sensors need time to gather light. If either the subject or the camera moves during this exposure time, the image appears blurred. In our discussion, we will focus on motion blur caused by fast movement, rather than unrelated effects like pixelation or mosaic artifacts. You might have experienced motion blur when taking a shaky phone photo, wearing foggy glasses, or watching a baseball fly past at incredible speed. But blur is not always a flaw.

In the world of art, blur has often been a feature rather than a mistake. Think of Claude Monet’s Water Lilies (link, copyright by The MET — highly recommend seeing it in person and viewing it from different distances): soft edges, blended colors, shapes shimmering in the light. Or consider long-exposure photographs of city traffic, where headlights stretch into glowing ribbons. In these cases, blur captures motion, mood, and mystery, transforming the ordinary into something extraordinary. Even in classic cinema, motion blur helps create a sense of speed or dreamlike atmosphere. In sports, blur can tell an entire story. The fastest recorded baseball pitch reaches 105.8 miles per hour, far too fast for the human eye to follow clearly. To freeze it, cameras must shoot at over 1,000 frames per second. A racecar streaking past the finish line or a sprinter in motion may appear as streaks of color, yet our brains still understand exactly what is happening. Motion blur, in these cases, is not a mistake; it is evidence of speed and energy.

In science, blur can reveal a very different kind of truth. Consider echocardiography, an ultrasound imaging method for the heart. These moving pictures help doctors assess heart function, blood flow, and valve performance. Yet even the tiniest shake of the probe, a restless patient, or the natural motion of the heartbeat can smear crucial details. There is even a trade-off between frame rate and depth of view: a typical knee ultrasound operates at around 20 frames per second, while heart ultrasound often reaches about 50 frames per second. A blurry heart chamber is more than an inconvenience; it can obscure the clues doctors need to make the right decision. Other imaging fields, such as X-ray or MRI, face similar challenges with motion blur. Interestingly, scientists also study the patterns of blur to improve image quality, since sometimes the “smudge” itself contains useful information about movement or structure.

Blur can be playful, expressive, and at times essential. It reminds us that seeing clearly is not always straightforward and that what appears imperfect can still hold meaning. From the sweep of a painter’s brush to the rhythm of a beating heart on a screen, blur reflects a world that is always moving and changing. Sometimes, beauty and truth live within that very imperfection.

Now for the fun part — using blur in a sentence by the end of the day:
Serious: Did you notice the blur in the long-exposure shot of the city at night? The headlights look like flowing rivers of light.
Less serious: While running to catch the bus, I accidentally created a blur of people in my phone photo. What a perfect accidental art piece.

…I’ll see you in the blogosphere.

Qifan Yang

Look! You’ve finally made it to Canada! You gloriously take in the view of Lake Ontario when your friend beside you exclaims, “Look, they have beaver tails!” You excitedly scan the lake, asking, “Where?” 

“There!”

“Where?”

“There!”

You see no movement from the lake. It isn’t until your friend pulls you to the front of a storefront says “BeaverTails” with a picture of delicious pastries that you realize they didn’t mean actual beavers’ tails. It turns out you were looking at the wrong place the whole time!

Often times, it’s easy for us to quickly identify objects because we know the context of where things should be. These are the kinds of things we take for granted, until it’s time to hand the same tasks over to machines. 

In medical imaging, experts label what are called Regions of Interests (ROIs), which are specific areas of a medical image that contain pathology, such as the specific area of a lesion. Having labelled ROIs are important, as it can help prevent extra time from being wasted on analyzing non-relevant areas of an image, especially since medical images contain complex structures that take time to interpret. But in the area of machine learning (ML) in medical imaging, having labelled ROIs is also useful because it can help with training ML models that classify whether a medical image contains a pathology or not; with ROIs identified, cropping can be done during the preprocessing of images so that only relevant areas of images are compared for the model to learn differences between positive and negative images faster.

In fact, having ROIs is so important, there is an entire field in artificial intelligence dedicated to it: Computer Vision. The field of computer vision focuses on automating the extraction of ROIs in images or videos, which plays a critical role in the mechanization of tasks like object detection and tracking for things like self-driving cars. In object detection, for example, things like ROI Pooling can be utilized; this is where multiple ROIs are used to obtain input feature maps, from which maximum values are used to detect the presence of features, giving rise to the ability to identify many objects at once – this is extremely useful, especially once you’re on the road and there are 10 other cars around you!

Now, the fun part: using Region of Interest in a sentence!

Serious: The coordinates of ROIs are given for the positive mammogram images in the dataset I’m using. Maybe I could use Grad-CAM to see if the ML breast cancer classification model I’m using uses the same regions of the image to arrive at its classification decision; this way, I can see if its decision making aligns with the decision making of radiologists.

Less serious: I forced my friend to watch my favorite movie with me, but I can’t lie – I think the attractive male lead was her only region of interest!

See you in the blogosphere,

Yan Qing Lee

According to the dictionary, the term “adversarial” refers to a situation where two parties or sides oppose each other. But what about the “adversarial example”? Does it imply an example of two opposing sides? In a way, yes.

In machine learning, an example is one instance of the dataset. Adversarial examples are examples with calculated and imperceptible perturbation that tricks the model into the wrong prediction but look the same to humans. So “adversarial”, in this case, indicates opposition between something (or human) and the model. The adversarial examples are intentionally crafted to trick the model by exploiting its vulnerabilities.

How it works? There are many ways to find weak spots and generate adversarial examples, but FGSM is one classic way, and the goal is to make small changes to a picture such that it outputs the wrong prediction. First, we input the model with the picture. Assume the model outputs the correct prediction, so the loss function, which represents the difference between the prediction and the true label, will be low. Second, we compute the gradient of the loss function to tell us whether we should add or subtract a certain value epsilon to each pixel to make the loss bigger. Epsilon is typically very small, resulting in a tiny change to the value. Now, we have a picture that looks the same as the original but will trick the model into the opposite prediction!

One exciting property of adversarial examples is their transferability. It is known that adversarial examples created for one model can also trick other unknown models. This might be due to inherent flaws in the pattern recognition mechanisms of all models and, sometimes, model similarities, allowing these adversarial examples to exploit common vulnerabilities and lead to incorrect predictions.

Now, use “adversarial example” in a sentence by the end of the day: 

Kinda Serious: “Oh I can’t believe my eyes. I am seeing a dog right here and the model says it’s a cupcake…So you’re saying it might be an adversarial image? What even is that? The model is just dumb.”

Less Serious: Apparently, the movie star has an adversarial relationship with the media, but which stars have a good relationship with the media nowadays?

See you in the blogosphere,

Yuxi Zhu

Imagine you’re trying to compare two images—not just any images, but complex medical images like MRIs or X-rays. You want to know how similar they are, but traditional methods like simply comparing pixel values don’t always capture the whole picture. This is where Learned Perceptual Image Patch Similarity, or LPIPS, comes into play.

Learned Perceptual Image Patch Similarity (LPIPS) is a cutting-edge metric for evaluating perceptual similarity between images. Unlike traditional methods like Structural Similarity Index (SSIM) or Peak Signal-to-Noise Ratio (PSNR), which rely on pixel-level analysis, LPIPS utilizes deep learning. It compares images by passing them through a pre-trained convolutional neural network (CNN) and analyzing the features extracted from various layers. This approach allows LPIPS to capture complex visual differences more closely aligned with human perception. It is especially useful in applications such as evaluating generative models, image restoration, and other tasks where perceptual accuracy is critical.

Why is this important? In medical imaging, where subtle differences can be crucial for diagnosis, LPIPS provides a more accurate assessment of image quality, especially when images have undergone various types of degradation, such as noise, blurring, or compression.

Now, let’s use LPIPS in sentences!

Serious: When evaluating the effectiveness of a new medical imaging technique, LPIPS was used to compare the generated images to the original scans, showing that it was more sensitive to perceptual differences than traditional metrics.

Less Serious: I used LPIPS to compare my childhood photos with recent ones. According to the metric, I’ve definitely “degraded” over time!

See you in the blogosphere!

Jingwen (Lisa) Zhong