The model used in the post (LeNet) is very small compared to what we typically think of in terms of modern deep neural networks. The LeNet architecture itself was published in the 1990s and was designed for character recognition so this is a natural application of it. kNN would work for many characters in this example, but you would run into a problem with overlapping text. kNN on raw pixel intensities requires a nice segmentation of the ROI. More image processing/segmentation/morphological operations could be applied to help in that case, but given a small network architecture that will naturally learn these filters a tiny CNN works well with little preprocessing.
Hi, Adrian here, author of the book you are referencing. You are referring to the highest tier of the book. There are other lower tiers as well that are cheaper.
The highest tier (again, which you are referring to) includes 800+ pages, detailed experiment journals on how to reproduce the state-of-the-art publications (ResNet, SqueezeNet, VGG, etc.) on ImageNet (which is 1.2 million images). I demonstrate how to implement each model from scratch and then train them, detailing which parameters to change and when. The highest tier is for people looking to train really large networks on massive datasets where you could be spending thousands of dollars in the cloud for GPU costs (you can't train these networks without a GPU, or ideally multiple GPUs). I've also included the pre-trained models as well if people want to get started with them and skip training. This tier is really for researchers/practitioners who need to save time and finances by starting with experiment journals that detail how to replicate the results.
The lower tiers are for people just (1) getting started with deep learning in context of computer vision and/or (2) looking to apply best practices. Each book also includes video tutorials/lectures once I have finished putting them together. Realistically I should rebrand the book as a course as it's much more in line with something you would get from Udacity (only with more theory and more detailed code and implementations).
If anyone has any questions about the book do feel free to ask.
No offense, but your book website looks lot like a late night TV ads and frankly leaves a bad taste.
The way I like to buy a book is go to Amazon, look at table of content, read few pages and most importantly read some reviews. Your book currently doesn't even appear in Amazon search (or even Google search). Despite myself being quite active in the field, I had never heard about your book before (I know of at least other dozen books on the subject). I wonder this is why you might have relatively much lower volume and such a high price to make up for your revenue target. I would think putting your book on Amazon would increase your volume by an order of a magnitude (or two) and help reduce price to may be 1/7th or 1/8th without requiring tiered pricing (which again is a huge turnoff) while increasing your net revenue actually more than before (probably by an order of magnitude). You might want to look in the theory and economics of price-volume curves.
The biggest problem with your book website is that you as an author comes out as hard-selling hard-charging marketer who wants to maximize profits and make a sell like an old car salesman to anyone who is walking by rather than experienced calm expert for who learning, teaching, academic honesty and integerity is more important than making money. Again, not saying this is who you are, it just feels that way from the style and content of the book website. Hope this helps.
I feel this advice is well intentioned but fails to reflect the realities of building and marketing these types of niche products and courses.
Setting aside issues of style and what other sites are doing it's very clear what the book is about, what's included and what makes that valuable.
The prices certainly are steep compared a "book", but it really is quite a bit more (more like a self study course in ML) and really targeted towards businesses that need to make this happen within their organizations.
I don't know about his books(courses?), but his site PyImageSearch is one of the more well known sites regarding computer vision. I certainly got a lot of help from the site (Thanks Adrian).
It's pretty standard landing page style these days for self-published books (plus ____), because it works.
If there was a way to tone it down for the referrals coming through Medium from HN (tough to track through 2 sites) or using some is-logged-in-to-HN hack (which would probably piss off people even more if detected) maybe it could be dialed back a hair to catch people like you, but it's probably not worth the effort.
I see. Rebranding as a course might help. If I were you I'd also consider A/B testing without the hard-sell/marketing hype style page. Personally I equate these sorts of 'You're probably wondering... "Is this book right for me?"' things as massive scammy red flags and a complete turn-off.
A/B testing is absolutely on my roadmap. I'm finishing up a few bonus chapters for the book/course now. Based on previous A/B tests on the site (for other products) I have a good idea of what works well for the general audience of my viewers. But I totally understand that the messaging will not work for everyone and it's something I hope I can address in 2018. Thanks for the comment.
You should absolutely rebrand as a course/training material, since it seems you're shipping much more than a printed book. As a researcher, experiment journals are really valuable, since in countless occasions I find the final, published articles / sample codes are 100% "draw the rest of the fucking owl" [1] material.
PS: Typo in the #release_bar: "has been offically released!"
Adrian here, author of the PyImageSearch blog. I'll add doing a tutorial on cheque recognition (at least the routing and account numbers) to my queue. Thanks for the great suggestion.
Adrian here, author of PyImageSearch. Thanks for mentioning the blog. If anyone has any questions regarding learning computer vision, please see my reply to "sphix0r" below.
Hey, amazing blogs. Currently working on degraded scanned documents. Are there algorithms distinguishable for documents and natural images?
I am using open cv to process the documents, curious if I am missing out chunk of cv algorithms specially for scanned administrative documents (financial,personal documents)?
I'm not sure what you mean by "algorithms distinguishable for documents and natural images" -- can you elaborate? OpenCV itself doesn't have builtin functionality to take documents and fit them to a pre-defined template, that tends to be part of a specific use-case/niche of computer vision for document processing. The general idea is to take a document a user has filled out and "fit" it to a blank template, where you know exactly where each field is. That way you can exact the information from the document.
"The general idea is to take a document a user has filled out and "fit" it to a blank template" - I agree point to point. However, I am struggling with templatization due to poor quality of the document images. To process those documents (denoise, super resolution, HE - etc. etc.), the OpenCV algorithms are not working good enough, requires a lot of tuning varying with each document.
So, I was wondering if those algorithms work better for natural images (buildings, people, things etc) than document images (text, graphics) and if so, there must exist algorithms to process such documents I am unaware of.
Adrian here, author of the PyImageSearch blog. Thank you for mentioning it, I appreciate it. If anyone has any questions about computer vision, deep learning, or OpenCV, please let me know.
Within the next month I'll be launching PyImageJobs which will connect PyImageSearch readers (especially the Gurus course graduates) with companies/startups that are looking to hire.
Hey, Adrian here -- I actually run PyImageSearch.com. I don't want to sell you on the course, I think the content speaks for itself. But if you want to talk to members who have gone through the course and see the value they got out of it, just let me know. Send me a message (http://www.pyimagesearch.com/contact/) and then I'll connect you with graduates. Also, if there is a specific topic you're looking to study just let me know and I can see if the course is a good fit for you.
Combining the Raspberry Pi + Python + OpenCV is a lot of fun. If you feel like sharing the details on your project I might be able to point you in the right direction.
