Zebra Technologies Corporation (ZBRA) Earnings Call Transcript & Summary

All right. Well, welcome. Thank you for joining us for a live demonstration of Zebra's deep learning-based OCR tool found in our Aurora Vision software. Before we begin, allow me to take a moment to introduce our main presenter for today, Mr. Armando Lopez. Armando holds more than 15 years experience in machine vision, acting as one of our primary sales applications engineers here at Zebra, and he holds an electronics engineering degree from Monterrey Institute of Technology in Mexico and also carries the certified Vision Professional Certification from A3 Vision -- A3 Vision and imaging. Chances are if you have a question about machine vision, Armando is going to know the answer. So welcome, Armando. Thank you for joining us. To introduce myself, my name is Timothy Libre Cameron. I serve as inside sales for North America here at Zebra. I've worked in machine vision for almost 5 years now, having joined Zebra from the team at Matrox Imaging. And I act as the first point of contact for incoming machine vision inquiries. So we may have spoken before. And I help with marketing initiatives such as this webinar. So let's jump right in. We're, like I said, looking at deep learning OCR today. Conventionally, optical character recognition can be an extremely challenging application. There's a lot of variables at play, as you probably know. What we here at Zebra have essentially solved that challenge with our deep learning OCR. It's a pretrained CNN that allows for easy setup and deployment of almost any optical character recognition projects, essentially saving you the time and cost that would typically be associated with a project of this potential complexity. So today, we're going to show you the power, the versatility and the ease of use of our Aurora software while using the deep learning OCR module on, I think, some pretty challenging images. After the demo today, we are going to be conducting a live Q&A with the audience. So please feel free to use that Q&A board. You see the right of your screen should you have any questions during the presentation, and we're going to do our best to get to answer as many of those questions as possible given our short time together this afternoon. So with that, I'm going to hand the mic over to Armando. Armando teach us why deep learning OCR is such a powerful machine vision tool.

It is. It is. Well, first of all, Tim, I'm going to invite you to all of my meetings with a fantastic voice. I don't have that voice. Sorry about that, right? I would just have a...

Just a fancy microphone. It has nothing to do with my actual voice.

I need that microphone. So yes, we have a lot to cover today. We're going to just jump into -- I'm going to turn off my camera. I just wanted to say high, right? I'm a real person, right? I'm going to chatGPT, Robot, right? I'm going to talk and show you why this is cool and why this is nice and why this is going to help you, right? Nobody buys smart cameras or visional systems because they are cool, right? We buy them because they're going to help us, right, somehow. So before I actually stop showing my face or before I turn off my webcam, I'm just going to let you know what kind of equipment I'm using. I'm using this smart camera, right? Now this algorithm, this super cool OCR algorithm that we have, we can use it in any of our smart cameras and also in our PC-based platform. I just wanted to show you right what we're using today. Okay. Well, I'm going to turn off my video for a second. You don't need to see me. And let's just jump into it. Just like Tim said, I've been doing machine vision for many years, almost 15 years. And there's -- I've seen a lot of different applications, right? And one of the least favorite application of engineers is usually OCR, right? Why OCR? Because it's kind of picky. It's kind of -- it's very strict, right? And you're going to see that through the presentation, but you need to have very controlled scenarios, deep learning OCR opens is all for more things. Okay. So let me just change screens in here. So this is a quick overview of what we're going to cover, right? A quick history lesson about reading, right? It's reading easy for humans, right? What is OCR? A super cool demo, not just them super cool demo. What is deep learning? And what are the differences, right, between deep learning OCR and conventional or teachable OCR? Are they friends? Or are they enemies?What do you think, Tim, are they friends or enemies? We'll see. We'll see.

We'll see in the upcoming belt.

All right, let's start right is like, "Oh my god, let's just start. I can't wait anymore.

That's my actual picture, but...

So easy to reading, easy for humans right? I don't know if you remember how it was learning how to read, but it took few years most likely, right, or maybe months if you're a savant genius, but most likely took you years to learn how to read. It's very difficult, right? It requires a lot of skills, a lot of focus, a lot of trying, a lot of going over and over and over, right? The coding, language structure, vocabulary background, world recognition, you need to see what you're trying to read you need to understand that comprehension to be able to read right acumen to be able to read. It takes a lot of time. It takes a lot of effort, right, is very -- actually, it's very difficult, right? Going again, just a quick lesson, right? I mean talking or speech, that's just natural for humans, right? The baby would talk just by being exposed to adults, right? The human brain has mechanisms or building systems to handle that, right? Opposing to talking reading is a cultural invention, right? Reading is obviously related to writing. We invented writing maybe 4,000, 5,000 years ago, right? So reading is a complex focalized scale that needs to be taught, a skill that takes time to master. I have a 2-year-old daughter, and I'm trying to teach her how to read already, and it's not an easy task, right? Now how is this related to Machine Vision is like, well, I don't want to talk about humans, right? Let's talk about cameras, right? How is this related to machine vision or image processing? Well, vision system algorithms or machine vision is trying to mimic, is an abstraction of humans, right? If you think about it, eyes, brains is cameras processing, right? A camera is trying to do what a human is trying to do, specifically OCR, right, the camera is trying to read. So what is OCR, right, for 100 Zebra points, what is OCR? Team already spoil it, right, is optical character recognition, right? So no points for anybody. Optical character recognition. Now what is that? Well, it's a processing technology that extracts text content from an image, right? Or if we put it in a different word, it's a camera being able to read from a picture, right? And we have that cute little robot, my daughter liked that robot. That's why I chose it, right? Is OCR new? No. OCR has been around for many, many, many years, right? Around 50 years, right? Someone invented OCR, roughly 50 years ago. Who invented OCR. We don't have time for that, right? You can Google that on your own time. Does OCR works well, conventional OCR? Yes, it works well. If where you're trying to read is consistent or if it's the same as what you were expecting. Meaning what are you talking about, Armando. Well, conventional OCR is going to work well or traditional teachable OCR is going to work well. If you're trying to read maybe a basic standard format like OCRA, for example, and if the image always looks the same, then conventional OCR is going to work just fine. Or if you take the time to train in the vision system software, the characters that you're trying to read, if you say, I have a lot of time, yes, let me -- I'm just going to start saving all the synergies, and I'm going to start teaching all these different letters with different lighting and different positions and different angles and different backgrounds and whatever, right? Conventional OCR is going to work fine if where you're trying to read is very consistent, same font, same size and color, same background, if the contrast is the same or if the contrast is something you're expecting the contrast, same light, same reflectivity, if the new image that is coming has the same focal plane sharpness, that is not blurry, that is not like it has to be exactly the same. Conventional OCR is going to work well if everything is exactly the same as you were expecting.

But we don't live in a perfect world, do we?

Not anymore. No. Now that's a lot of ifs, right? That's a lot of ifs. I don't live in that world. So let me give you a visual, right, it's like what do you mean, but it has to be the same settings or the same conditions? Well, let's try this. Let's say, you are with your friend, OCR, having a drink, hey, OCR with this, right? And your friend, the OCR algorithm is going to say, no problem, I got you. That says Zebra. I'm already trained to understand those letters and the way they look. I know those letters. I know that contrast. I know that size, that font, that says Zebra. Perfect. Conventional OCR is amazing. Now -- but what happens if something changes, a, conventional OCR now with this, I don't like it. I don't like it. I'm not sure it kind of looks similar to what I know. But no, it's too different. I don't know what that is. Conventional OCR is going to struggle. Now what's the difference between the first image and the second image for 100 Zebra points? Well, the difference is who knows, Tim, do you know?

Yes. Well, exposure contrast.

Of course. The difference between that second image is overexposed, right? So less contrast. So our friend, OCR is struggling with that one. He doesn't like it, right? So just in summary, if the material changes, the reflectivity, the contrast, the background, if something changes, if something is out of control, if something is unexpected, conventional OCR is not going to like it, right? So now if you think about it, I just put some examples in here. These are very different scenarios, right? We have the same part, but with different contrast. We have maybe this is like dot printing, right, maybe a consumer product, expiration date. This is ink printing. We have maybe images that have very little contrast or we have images that are core parts that are very noisy. This is a terrible image. Or we have things within consistent backgrounds, right? There's a diagonal across the [indiscernible] this line. Now you -- if you are a machine vision experts, you're going to say, "Hey, I can make it work." Of course, I can make that work. I just have to teach, save all these images and create a very rich, very powerful library for funds. I just had to teach all this every single time. Yes, okay, yes, you can do that. Good luck with that, right? I mean how much time it's going to take you to do all of this. And you need to have skills, maybe you have the skills, perfect. But still, it's going to take you time. It's going to take your time to teach your library to take all of this. And what if the next credit card, this is my credit card on write down this number. What if the next credit card has a different background? It might not work anymore. So what do we do? It's like, "Oh my, what do I do? Well, what if I told you -- this is on the matrix. What if I told you that Zebra has a deep learning-based OCR algorithm that can read all of that just out of the box without doing pretty much anything, right? Like Armando, you're crazy, yes, yes. Someone clapping. Yes. We are going to do it, right? How? Show me the deep learning. That's also. Okay. Let's do it. Let's do a super cool demo, right? Please let me know if you can see my screen. Can you see my screen?

Yes, we see it.

Now these images might look familiar right, is what I had in the PowerPoint. Is this live image? Yes, this is a live image. That's number two. That's number three, right? That's my only hand. Now this is Aurora focus. You can use also this algorithm in any of our platforms like the Design Assistant, but where you think today the Aurora focus. Now how am I going to -- let's say, my application is, I need to read all these different types of words, and I just have 2 minutes because I want to go for lunch, right? My friends are waiting in the parking lot. I had 2 minutes to make all of this work. Well, here in the identification tool bucket, we have deep learning-based OCR, I'm just going to drag and drop, right? And I'm going to move this box somewhere on the screen, right? So for example, if I move it here, you might see that I'm already reading. I haven't touched any of the settings. I'm going to say that again, I haven't touched any of the settings. Now can I be specific and just read some type of letters or some type of color of the letter or some type of size? Yes, of course, you could be specific. But a, I want to read just out of the box. I don't want to do anything, okay? Debit, we're reading the word debit here. I'm going to zoom in because it might look small. Now is this a beautiful image? No, it's kind of ugly, right? I intentionally make this very challenging, right? But we're reading this. Now what if I want to read now a ZIP code, for example, this ZIP code over here? Yes, we are also reading the ZIP code over here, right? Now what if I want to read this ink printing in here? Now if you have tried to read this before, with whatever vision system you're using, you might know that this is usually complicated, right? And again, is this a clean super cool image? No. Do this image be better? Yes. But I intentionally did it kind of ugly. Now we read debit, we read this ZIP code number, we read this Videojet in printing or whatever with the same settings. Now let's try to read the words Zebra down here, right? And can we read that? Well, let's try, right? If I put it here, Zebra, no problem. Can we read this one in here? What does it say? I can barely see it. Well, let's see. I'm going to put it here. I'm just going to make this a little larger. And I'm just going to move it, and I'm going to put it here. And we are reading, I'm going to zoom in. I don't believe your mind, let me zoom in. Don't believe me, don't believe anybody. We can read it, right? Now can we read this one in here this lens? This one is extremely ugly, right? And when I was trying to do this and showing these to people like I'm going to show this them, they say, no, don't do it man. No, this is crazy. No, it's fine, right? Can you see now again, if you have tried to do machine vision OCR in the past, you do know that this is extremely ugly, extremely complicated. I'm going to do one more. I'm going to move this one here, right? And if you notice, we are reading right away. This one, for me, is particularly interest because we have in here different scenarios. We have in here on the left bright background. We have in here a dark background, and we have a diagonal going across the 0 and the 9, and it reads right away, right? Again, the beauty of deep learning OCR is that it's going to read pretty much anything that is readable on it without you having to touch any of the settings in here, right? Remember, and I'm going to -- maybe I said this already 2 times. I'm going to say it one last time. We've read all of these with the default settings without pretty much without touching anything, right? Can you be specific? Yes, of course. You can say -- you'll say, I just want to read this type of thing or that type of thing or only numbers or only letters. But I just wanted to show you that we can do something like this with the fall settings. I'm going to show you one more thing and then we're going to go to the PowerPoint. One of my managers told me back in the day, Armando, if the demo went well, just stop them or in place. Let's just do one more, right? Do you want to see one more? So now what I'm going to do here is I just do the poker chip and that says Zebra. And I'm holding this. And that's kind of like never do an OCR handholding. Well, let me just show you this very quickly, right? Try to do this, I will give you the homework of trying to do this with whatever system you're using right now. And I would bet -- well, maybe betting is not good. I would challenge you to get these type of results with default settings again. And you would know that introducing this type of distortion or variability is never good, right? Conventional OCR is going to say does not comment, don't change anything, don't change the lighting, don't change, don't introduce optical distortion. This is just going to work well. What do you think, Tim?

I am shocked and amazed. I mean, really, if you've seen and no conventional OCR, yes, exactly. That is -- that should be your reaction when you see that because it's taking all of those variables of the equation that would normally stump conventional OCR. So amazing. It was a worthy gamble as the last row there. Good job.

Now going back to what I use demo, I mean, that's what I show you were like really ugly images, right? Of course, I mean, if you in your production line or in your scenario, if you help algorithm a little, right? If you try to honor the basic machine vision and try to get a decent better image is going to work even better, faster, right? Now what just happened is like, oh, my god, what did I just see, right? What you just saw was a deep learning-based OCR? Now what is deep learning, right? Let's take a step back. What is deep learning? Well, deep learning is a method in artificial intelligence or AI, right, that teaches computers to process data in a way that simulates the behavior of the human brain. Wow, there's a lot of fancy words in there. But basically, what it is, is think about it this way, right? You are not an adult human, right? You're a human. You can read pretty much anything right? Any type of text with your eyes because your brain has been taught already to be prepared for something like that, different fonts, different conditions, different lighting conditions, different positions, colors, backgrounds. Your brain has been trained with hundreds of thousands of images over your lifespan, right? You have seen a lot of different pieces of paper or different words, try your brain already has model, right? Your brain already has a mesh of options or a convolutional neural network, right, in your head? Your brain is awesome, right? If you think about it, what we can achieve, right, as a machine vision, right, if you would, is remarkable, right? So that's how deep learning works, right? It's trying to mimic the way humans read letters, right? So Armando then, are you saying then that Zebra deep learning OCR reads without training as an adulthood because the algorithm already has a convolutional neural network model that has been trained with hundreds of thousands of images to accommodate for different scenarios? That is correct, right? We did all the heavy lifting for you already. So you just have to draw a box and go for lunch, right? Then, if that's true, and I tell the truth, even when I lie, then if that's true, then conventional OCR is like instead of asking an adult to read is like asking a kid that is just starting to learn how to read. That kid, he will just be able to understand the few letters that he knows and the type, color or fonts that he has seen. So he has a limited spectrum of opportunities, right? That is correct. So that's the fundamental difference. Conventional OCR is like asking if I ask my daughter, Sofia. Sofia, can you read this? And if he has seen that word a million times, she's going to tell me, right? Yes, that's a Zebra. But if I show her a different cardboard with a different word or with a different size of letters or a different fonts or a different color, she might say, I don't know what that is, right? That's the difference between deep learning-based OCR and conventional OCR.

Good analogy.

Then if that is true, and everything I say is true, right, even when I lie, then if that is true, Armando, why is conventional OCR still around, right? If deep learning OCR is so amazing and it is. Why is conventional OCR still around? Are they friends or are they enemies. Well, neither, right? They are more like far cousins kind of. They are different, right? They both read the ultimate product or the ultimate result for any of those 2 algorithms is a readout, right? They both read. But really, which one to choose depends on what is beyond reading, right? Not just the reading aspect, what is beyond that reading, right? Well, yes, if you could be an example, that will be great, right? That's a meme, right, must be meme. Well, for example, if you need to read something out of the box and you don't want to go over training a library or having to know about lighting techniques or having to worry about the contrast, to what type of font it is or what if something changes, what is the position of the power changes? Well, if you just want to do something plug and play out of the box, deep learning OCR is what you want to use, okay? Quick and easy, right? But if you need to read ABC and you want to make sure that is ABC and not ABC, then you should use conventional OCR, right? Why? Because the last ABC visually is different than the first ABC and maybe that is relevant for your application. Maybe you want to make sure that you're reading in a specific type of font, for example, that that's just one. Are there more examples or differences between deep learning OCR and conventional OCR? Yes, there's much more to discuss, but we don't have time for that. Okay. I hope this was useful for you. I just try to show you very briefly. I mean, this topic is very big. We could talk about this for hours, but we don't have time for that, right? I'm going to pass it along to Tim, and we are happy to answer any questions that you may have.

Yes. Yes. Amazing Armando. As always, you managed to make all of this Wizardry seems so easy. From the looks of our Q&A section here, we do actually have quite a few raised eyebrows in the group. So let's go ahead and move on to the Q&A component of our webinar today. Don't worry, if we -- we are going to be following up with everybody after the show. So if there are questions that come up afterwards, we're going to be in touch, and you can feel free to reach out to us as all. So ready to get grilled Armando?