DEV Community

Cover image for 80 Blog Posts to Learn Computer Vision
Indie Developer
Indie Developer

Posted on

80 Blog Posts to Learn Computer Vision

Harnessing Artificial Intelligence to teach computers and systems how to obtain meaningful information from Images. We look at tricks of the trade, evolving techniques and so forth.

1. How to Recognize a Knife in an Image with Machine Learning

For a fun challenge, I started learning a little bit of AI and Machine Learning. I’ve been studying the excellent Fast.AI course. This is a series of videos which takes you from zero to hero with Machine Learning for free.

2. Computer Vision: The Future of the Future in More Ways Than One

All around us — and most of the time without us even realizing it — computer vision (CV) is being used to enhance our lives. With our iPhones and its Face ID technology to unlock your smartphone as a case in point, not to mention the countless other services and apps that have pooped up on the market of late, we’re headed in the right direction as far as innovation is concerned.

3. 8 Companies Using Machine Learning in Cool Ways

When asked what advice he'd give to world leaders, Elon Musk replied, "Implement a protocol to control the development of Artificial Intelligence."

4. Traffic Sign Classification

Having just finished the semester at NYU, I thought I’d share the results of one of the more interesting homework assignments that I had. As the title suggests, this will be another post about the traffic sign classification competition found at http://benchmark.ini.rub.de/.

5. Face Recognition On The Wall; Google's AutoML Edge Democratizes ML For All

Machine learning can be complex and overwhelming. Luckily Google is on its way to democratize machine learning by providing Google AutoML, a Google Cloud tool to handle all the complexity of machine learning for common use cases.

6. Understanding YOLO

This article explains the YOLO object detection architecture, from the point of view of someone who wants to implement it from scratch. It will not describe the advantages/disadvantages of the network or the reasons for each design choice. Instead, it focus on how it works. You should have a basic understanding of neural networks, specially CNNS, before you read this.

7. RaspberryPi Home Surveillance with only ~150 lines of Python Code.

I owned a Raspberry Pi long ago and it was just sitting in my tech wash box. After watching a Youtube session of creative Raspberry applications, with envy , I decided to try something by myself. The first obvious idea to me was a home security system to inspect your house while you are away.

8. Top 10 Computer Vision Papers of 2021: HackerNoon Edition

The 10 most interesting computer vision papers in 2021 with video demos, articles, code, and paper reference.

9. How to Build an Image Search Engine to Find Similar Images

After reading this article, you will be able to create a search engine for similar images for your objective from scratch

10. 5 Companies Developing Computer Vision Technology in 2020

Computer vision technology is the poster child of artificial intelligence. It is the sector of the industry that gets the most media attention because of the tools and benefits the technology can provide. From autonomous vehicles and drones to cancer detection and augmented reality, technologies that once only existed in science fiction are now at our doorstep.

11. Introducing best-in-class image annotation tools for computer vision applications

September brought many new features and updates to Labelbox. But most notable is that the image annotation interface has undergone a massive upgrade.

12. Can you solve a person detection task in 10 minutes?

Spoiler: sure, you can! 💪

13. A Brief History of Computer Vision (and Convolutional Neural Networks)

Although Computer Vision (CV) has only exploded recently (the breakthrough moment happened in 2012 when AlexNet won ImageNet), it certainly isn’t a new scientific field.

14. 10 Must-Try Open Source Tools for Machine Learning

Machine learning is the future. But will machines ever extinct humans?

15. Launching my Company, A Scholarship and A Webinar

Its been about three months since I publically announced that “I swear to take Machine Learning as my future career path.”

16. A Definitive Guide To Build Training Data For Computer Vision

Tech giants like Google, Microsoft, Amazon, and Facebook have declared their product strategies with the AI first approach. The AI effect has influenced the product roadmaps of all enterprise companies which now have prominent AI based applications getting launched each quarter to automate their business processes. Computer Vision, specifically, is being vastly explored and applied across industries from traditional banking to cutting edge self-driving cars.

17. The best image annotation platforms for computer vision (+ an honest review of each)

We at Humans in the Loop are constantly on the lookout for the best image annotation platform that offers multiple functionalities, project management tools and optimization of the annotation process (even 1 second less per image matters when you have to annotate 50k images!).

18. Fundamentals of display technologies for Augmented and Virtual Reality

Head-mounted devices for virtual and augmented reality come in different shapes and sizes from the minimal Google Glass to the fully immersive HTC vive. At it’s core, head-mounted displays (HMDs) consist of two primary structural elements: optics and image displays.

19. Key-point detection in flower images using deep learning

In this article we describe how we used a Convolutional Neural Network (CNN) to estimate the location of key-points in flower images. Key-points such as stem position and flower position are needed to render these images on a 3D model.

20. Top 20 Image Datasets for Machine Learning and Computer Vision

Computer vision enables computers to understand the content of images and videos. The goal in computer vision is to automate tasks that the human visual system can do.

21. Computer Vision Is Solving Problems That Weren't Even On Our List

Replicating human interaction and behavior is what artificial intelligence has always been about. In recent times, the peak of technology has well and truly surpassed what was initially thought possible, with countless examples of the prolific nature of AI and other technologies solving problems around the world.

22. Running a TensorFlow model on iOS and Android

After that stripping the model was as simple as running the following command

23. My Machine Learning Path

With a Decent GPU in place, I think I’m ready to start on this Journey that I have been aiming for since freshman year.

24. How to Measure Quality when Training Machine Learning Models

Training data quality is critical for a machine learning model’s performance. Quality is measured by both the consistency and the accuracy of labeled data. The industry standard methods for calculating training data quality are benchmarks (aka gold standard), consensus, and review. As a data scientist in AI, an essential part of your job is figuring out what combination of these quality assurance procedures is right for your project.

25. Computer Vision — The Impact on Financial Services

Propel Venture Partners recently celebrated its one year anniversary, with our first annual Summit taking place in April. At the Summit, I had the opportunity to share some thoughts on computer vision, and its impact on financial services.

26. Interview with Kaggle Competitions Grandmaster: KazAnova (Rank #3): Dr. Marios Michailidis

This is another very special version of the series.

27. Interview with Deep Learning Freelancer Tuatini Godard

I have very recently started making some progress with my Self-Taught ML Journey. But to be honest, it wouldn’t be possible at all without the amazing community online and the great people that have helped me.

28. Adversarial attacks: How to trick computer vision

In 2014, the publication of a study from a Google-led AI research team opened up a new field of hacking called an adversarial attack. The techniques the paper demonstrated not only changed our understanding of how machine learning operates but also showed in practical terms how one of the most commercially promising and highly anticipated aspects of the AI revolution could potentially be undermined.

29. How to unwrap wine labels programmatically

How to unwrap wine labels programmatically

30. Interview with the Author of PyImageSearch and Computer Vision Practitioner: Dr. Adrian Rosebrock

If you’re interested, you can find the Index to all the other “Interviews with ML Heroes” here

31. MIT 6.S094: Deep Learning for Self-Driving Cars 2018 Lecture 4 Notes: Computer Vision

All Images are from the Lecture Slides.

32. How to debug neural networks. Manual.

Debugging neural networks can be a tough job even for field expert. Millions of parameters stuck together where even one small change can break all your hard work. Without debugging and visualization all your actions is popping a coin, and what worse it eating your time. Here i gather practices that will help you find problems earlier.

33. How Far Are We from a Fully Autonomous Driving World?

The MIT Deep Learning for Self-Driving Cars course just released their First lecture video (alternatively Here are the lecture notes if you want a quick read)

34. Building Silicon Valley’s Hot Dog App in One Night

After watching the latest episode of HBO’s Silicon Valley and seeing the Not Hotdog iOS app that was built, I wanted to see if I could build the same thing as a Twitter bot.

35. Introducing theHolopix50k Dataset for Image Super-Resolution

Depth estimation and stereo image super-resolution are well-known tasks in the field of computer vision. To help researchers get high-quality training data for these tasks, industry-leading lightfield hardware provider Leia Inc. used their social media app, Holopix™, to create Holopix50k, the world’s largest “in-the-wild” stereo image dataset.

36. How to measure the latency of a WebCam with OpenCV

In this quick tutorial, you will learn how to measure the latency of your webcam to make the assessment whether it is capable to handle image capturing task with a higher real-time demand compared to doing a still image capturing.

37. Interview with Kaggle Kernels Expert: Aakash Nain

I have very recently started making some progress with my Self-Taught Machine Learning Journey. But to be honest, it wouldn’t be possible at all without the amazing community online and the great people that have helped me. In this Series of Blog Posts, I talk with People that have really inspired me.

38. Data Set and Data Augmentation for Face Detection and Recognition

When it comes to building an Artificially Intelligent (AI) application, your approach must be data first, not application first.

39. New Meaning to Grab and Go: Alibaba Unveils its Unmanned Store

Alibaba’s the Tmall Future Store shows how technology can help offline merchants thrive in the e-commerce age

40. Interview with the Creator of DeOldify, fast.ai student: Jason Antic

Today, we’re talking to a very special “Software Guy, currently digging deep into GANs” — The author of DeOldify: Jason Antic.

41. SINGLE OBJECT DETECTION PART - 2

(Read Part 1 here)

42. Histogram Equalization in Python from Scratch

Histogram Equalization is one of the fundamental tools in the image processing toolkit. It’s a technique for adjusting the pixel values in an image to enhance the contrast by making those intensities more equal across the board. Typically, the histogram of an image will have something close to a normal distribution, but equalization aims for a uniform distribution. In this article, we’re going to program a histogram equalizer in python from scratch. If you want to see the full code, I’ve included a link to a Jupyter notebook at the bottom of this article. Now, if you’re ready, let’s dive in!

43. How To Become A Machine Learning Engineer

We will walk you through all aspects of machine learning from simple linear regressions to the latest neural networks, and you will learn not only how to use them but also how to build them from scratch.

44. Is Object Detection a Done Deal?

A few years back it was widely known that Object Detection was a hard problem to solve. The comic below was just a few years back. Things have changed in this short time quite drastically.

45. How to make SnapChat Lenses?

We all love SnapChat lenses/filters, but ever wondered how you can make your own? This article explains how you can use python and computer vision libraries like opencv and dlib to create your own “glasses and mustache lens” with as few as 80 lines of code.

46. Machine Learning for ISIC Skin Cancer Classification Challenge

This is part 1 of my ISIC cancer classification series. You can find part 2 here.

47. The Problem(s) With Amazon GO

48. Interview with Deep Learning and NLP Researcher: Sebastian Ruder

This is another very special version of the series.

49. Interview with Kaggle Grandmaster, Senior CV Engineer at Lyft: Dr. Vladimir I. Iglovikov

Today, I’m honored to be talking to another great kaggler from the ODS community: (kaggle: iglovikov) Competitions Grandmaster (Ranked #97), Discussions Expert (Ranked #30): Dr. Vladimir I. Iglovikov

50. Interview with Deep Learning Researcher and The GANfather: Dr. Ian Goodfellow

This is another very special version of the series.

51. Rare Datasets for Computer Vision Every Machine Learning Expert Must Work With

Have you ever being in a situation to guess another person’s age? Well May be YES!! How about playing games like finding things in minimum time? or about finding the written character where your doctor wrote in the prescription when you are sick?

52. Image Annotation Types For Computer Vision And Its Use Cases

There are many types of image annotations for computer vision out there, and each one of these annotation techniques has different applications.

53. How to Make a Gaming Bot that Beats Human Using Python and OpenCV

Learn to create a Python bot that plays an online game and achieves the highest score in the leaderboard beating humans.

54. 10 Best Image Classification Datasets for ML Projects

To help you build object recognition models, scene recognition models, and more, we’ve compiled a list of the best image classification datasets. These datasets vary in scope and magnitude and can suit a variety of use cases. Furthermore, the datasets have been divided into the following categories: medical imaging, agriculture & scene recognition, and others.

55. A beginner’s guide to Computer Vision in Retail

Anyone with a wet finger in the air will by now have heard of the “retail apocalypse” sweeping through the developed world’s malls. “People aren’t spending in stores anymore”, your quarter-informed uncle complains, before moaning that youths are too busy Instagramming their avocado brunches to burn crosses on people’s lawns. Indeed, the old retailing models aren’t working as well as they used to. The fact that they were terrible models to start with probably had something to do with it.

56. Robotic Vision: Connecting Asus Xtion Live Depth Camera to Raspberry Pi

An important part of the robot is its eyes and perception of the outside world. For this purpose, the Depth Camera is well suited.

57. How to Implement Gaussian Blurs

A Gaussian blur is applied by convolving the image with a Gaussian function. We’ll take the Gaussian function and we’ll generate an n x m matrix.

58. A Python Library for Face Detection and Extraction with OpenCV Using HOG/Neural Network

Many people, including me, use a combination of libraries to work on the images, such as: OpenCV itself, Dlib, Pillow etc. But this is a very confusing and problematic process. Dlib installation, for example, can be extremely complex and frustrating.

59. Using Reinforcement Learning to Build a Self-Learning Grasping Robot

Tips and tricks to build an autonomous grasping Kuka robot

60. How to Create Hidden Secret Messages in Images using Python

Today, we are gonna learn how to apply coding skills to cryptography, by performing image-based stenography which hiding involves secret messages in an image.

Stenography has been used for quite a while. Since World War II, it was heavily used for communication among allies so as to prevent the info being captured by enemies

61. Interview with Radiologist, fast.ai fellow and Kaggle expert: Dr. Alexandre Cadrin-Chenevert

Today, I’m super excited to be interviewing one of the domain experts in Medical Practice: A Radiologist, a great member of the fast.ai community and a kaggle expert: Dr. Alexandre Cadrin-Chenevert.

62. How to Classify Animal Images via a Convolutional Neural Network

Identifying patterns and extracting features on images using deep learning models

63. This AI Creates Realistic Animated Looping Videos from Static Images

This model takes a picture, understands which particles are supposed to be moving, and realistically animates them in an infinite loop!

64. ICCV 2019: Papers that indicate the future of computer vision (Satellites to 3D reconstruction)

If you couldn’t make it to ICCV 2019 due to visa issues, no worries. Below is a list of top papers everyone is talking about!

65. We Built a Face and Mask Detection Web App for Google Chrome

Face and mask detection in browser using TensorFlow.js, openCV.js. Investigate results with different implementations.

66. Image Processing Algorithms: Adjusting Contrast And Image Brightness

Let's take a look at the common approaches for implementing image contrast adjustments. We'll go over histogram stretching and histogram equalization.

67. Introductory Guide To Real-time Object Detection with Python

Researchers have been studying the possibilities of giving machines the ability to distinguish and identify objects through vision for years now. This particular domain, called Computer Vision or CV, has a wide range of modern-day applications.

68. Ten Trending Academic Papers on the Future of Computer Vision

If you couldn’t make it to CVPR 2019, no worries. Below is a list of top 10 papers everyone was talking about, covering DeepFakes, Facial Recognition, Reconstruction, & more.

69. How Does DALL·E mini Work?

Dalle mini is amazing — and YOU can use it!

70. Machine Learning for the ISIC Cancer Classification Challenge #2: Deep learning on AWS

(The full list of lesion types types to classify in the ISIC dataset. We’ll be focusing on Melanoma vs. non-Melanoma)

71. Image to Image Translation and Segmentation Tutorial

In this article and the following, we will take a close look at two computer vision subfields: Image Segmentation and Image Super-Resolution. Two very fascinating fields.

72. Build a Custom-Trained Object Detection Model With 5 Lines of Code

These days, machine learning and computer vision are all the craze. We’ve all seen the news about self-driving cars and facial recognition and probably imagined how cool it’d be to build our own computer vision models. However, it’s not always easy to break into the field, especially without a strong math background. Libraries like PyTorch and TensorFlow can be tedious to learn if all you want to do is experiment with something small.

73. [Tutorial] Build a Gender Classifier for Live Webcam Stream using Tensorflow and OpenCV

Training a Neural Network from scratch suffers two main problems. First, a very large, classified input dataset is needed so that the Neural Network can learn the different features it needs for the classification.

74. 3 Common Types of 3D Sensors: Stereo, Structured Light, and ToF

Over the past decade, 3D sensors have emerged to become one of the most versatile and ubiquitous types of sensor used in robotics.

75. Facial Recognition Comparison with Java and C ++ using HOG

HOG - Histogram of Oriented Gradients (histogram of oriented gradients) is an image descriptor format, capable of summarizing the main characteristics of an image, such as faces for example, allowing comparison with similar images.

76. Visual Generative Modeling: Using GANsformers to Generate Scenes

They basically leverage transformers’ attention mechanism in the powerful StyleGAN2 architecture to make it even more powerful!

77. OpenAI's New Model is Amazing! DALL·E 2 Explained Simply

Last year I shared DALL·E, an amazing model by OpenAI capable of generating images from a text input with incredible results. Now is time for his big brother, DALL·E 2. And you won’t believe the progress in a single year! DALL·E 2 is not only better at generating photorealistic images from text. The results are four times the resolution!

78. The Full Story behind Convolutional Neural Networks and the Math Behind it

Convolutional Neural Networks became really popular after 2010 because they outperformed any other network architecture on visual data, but the concept behind CNN is not new. In fact, it is very much inspired by the human visual system. In this article, I aim to explain in very details how researchers came up with the idea of CNN, how they are structured, how the math behind them works and what techniques are applied to improve their performance.

79. This AI Performs Seamless Video Manipulation Without Deep Learning or Datasets

New research by Niv Haim et al. allows us to perform infinite video manipulations without using deep learning or datasets.

80. Introducing Total Relighting by Google

In a new paper titled Total Relighting, a research team at Google presents a novel per-pixel lighting representation in a deep learning framework.

computer-vision

Photo credit, HackerNoon AI

Top comments (0)