INTRODUCTION
Humans use their eyes and brain to recognize objects and notice details whereby computers do not see in the same way. They receive images as numbers and use mathematical operations and trained models to identify objects and make predictions.
Computer vision is simply a way computers use to process and understand visual information.
IMAGE PROCESSING
This is a way the image is changed, improved, analyzed by a computer to get useful information from it.
It comprises processes like;
Sharpening : making image more clear and identifying details
Grayscale : removing colors from an image and replaing it with shades of gray, black and white.
Blurring : making an image smoother by removing sharp details
Edge detection : help a computer to analyse the boundaries and shape of an image
COMPUTER VISION TASKS
Image classification : identifies what an image contains or what is in an image
Object detection : identifies an object in an image and shows where they are located using boxes and confidence
Image segmentation : identifies the number of pixels of each object
COMPUTER VISION MODELS FAILURES AND IMPERFECTION
Things such as poor lighting, blurry images, and unusual angles can affect their results. This is because the results depend on how much the model was trained. So the model needs to be tested with a variety of images so that it gets familiar.
This image shows how some details where not mentioned maybe because the model was not trained enough to know about those predictions. Some of the predictions are right others are wrong and some of them are not even in the image.
This image shows different predictions of the same image just because it was it was slightly changed and the model was not trained enough to predict same output.
CHALLENGES I FACED WITH THIS UNIT
Some challenges i faced where that the tasks are all relating to the image yet they perform differently. One notices an object another where its located and the other one the number of pixels belonging to it.
COMPUTER VISION APPLICATIONS IN REAL LIFE
It can help identify objects in security systems, support medical image analysis, and allow self-driving cars to recognize their surroundings without causing accidents. Also, the way our phones recognise our faces with the FaceID feature.
CONCLUSION
This unit helped me understand more of how computers see and make sense of what they see by analysing and making predictions from what they are seeing yet they've not seen it before. It's just a matter of training the model.
Top comments (3)
I really enjoyed reading your blog! ❤️ I learned that computer vision helps computers understand images using numbers and trained models. I also understood the difference between image classification, object detection, and image segmentation, which was something I found interesting. I liked how you explained image processing techniques like grayscale, blurring, sharpening, and edge detection, as well as the real-life applications of computer vision.
One thing I think you could improve is adding more practical examples or small code snippets to show how these techniques work in real life. You could also explain a little more about how to solve the challenges you faced. Overall, this was a helpful and beginner-friendly blog, and it helped me understand computer vision better. Great work! 👏💗
Great work explaining the basics of computer vision! I like how you're building your understanding of how computers interpret images. Keep exploring through hands-on projects with Python and OpenCV, experiment with filters and edge detection, and gradually dive into CNNs and image classification. You're building a great foundation—keep going and enjoy the learning journey! 💪🚀
I liked how you explained computer vision in simple language, especially the differences between image classification, object detection, and image segmentation. The images were also helpful in showing how computer vision models make predictions and how their results can be affected by changes in image quality.
You could improve the explanation of the model’s incorrect predictions by giving a specific example of what the model detected incorrectly and why that might have happened. It would also be helpful to explain a little more about how image processing techniques, such as grayscale and edge detection, support computer vision tasks. A few grammar corrections would also make the article clearer and easier to read.
Overall, this is a good beginner-friendly introduction to computer vision. I appreciate how you connected the concepts to real-life applications and shared the challenges you faced while learning. Keep exploring and experimenting—you’re making good progress!