8
votes
Accepted
Is it okay to use publicly available Instagram videos to train an AI?
Under US copyright law, this is probably fair use
...but beware of memorization. You may run into more trouble if the AI outputs things very similar to the original work.
Also, consult a lawyer to ...
- 196
7
votes
Accepted
What are the main algorithms used in computer vision?
There are many computer vision (CV) algorithms and models that are used for different purposes. So, of course, I cannot list all of them, but I can enumerate some of them based on my experience and ...
- 37k
5
votes
Image-in image-out neural network architectures
I think the second approach will be the best because it only requires that your training set is annotated with four labels for each of the four corners of the paper sheet.
This is sort of the idea of ...
- 179
4
votes
Does each filter in each convolution layer create a new image?
For a 3 channel image (RGB), each filter in a convolutional layer computes a feature map which is essentially a single channel image. Typically, 2D convolutional filters are used for multichannel ...
- 156
4
votes
Accepted
Does each filter in each convolution layer create a new image?
You are partially correct. On CNNs the output shape per layer is defined by the amount of filters used, and the application of the filters (dilation, stride, padding, etc.).
CNNs shapes
In your ...
- 156
4
votes
Does each filter in each convolution layer create a new image?
About the images inside the CNN layers: I really recommend this article since there is no one short answer to this question and it probably will be better to experiment with it.
About the RGB input ...
- 96
4
votes
Is there any existing attempt to create a deep learning model which extracts vector paths from bitmaps?
If we seek proven working source code to plug into a GPLv2-licence compatible solution, we should at least consider autotrace. Its source code is open for review. It can be tested against the example ...
- 7,375
4
votes
Accepted
Why is AI Super Resolution Reconstruction more than just guessing?
Yes, it's guessing. In the training phase, you show it lots of coarse and detailed pictures, and the algorithm learns a mapping from course to detailed. Then you present it a new coarse image, and it ...
- 5,242
4
votes
Accepted
Musical notes interpretation
AI/ML can solve the task described, a solution is as below:
Regular image processing algorithm (pixel row with min black pixels, adjacent rows are considered as 1) to split the sheet music (as image) ...
- 1,283
4
votes
Does the order of a Numpy array matter for CNN classification?
It shouldn't matter for the accuracy of the network. But note that tensorflow/keras uses the (N, W, H, C) convention whereas pytorch uses the (N, C, W, H). So depending on what library you use, you ...
- 346
3
votes
Autoencoder produces repeated artifacts after convergence
Perhaps you are getting checkerboard artifacts Explained here, solutions involve changing the kernel and stride size to prevent them from being not divisible. Besides that, a solution could be to ...
3
votes
Accepted
What are some references that describe known filters (or kernels) and how we can create new ones?
I'd suggest you better understand edge detectors such as Robert or Sobel operators first to understand better how convolution operation on images extract features by constant value kernels.
Would ...
- 1,379
3
votes
Accepted
Can I shuffle image channel data as a form of data augmentation?
As a rule of thumb for image data augmentation, look at the augmented images:
Can you correctly classify or measure your target label from the augmented images?
Could something similar to the ...
- 26.5k
3
votes
Accepted
Aesthetics analysis with deep learning
Aesthetics of images has a strong subjective element and possibility of multiple dimensions depending on purpose of the media. That means:
It is hard to define what we mean by scoring aesthetics.
...
- 26.5k
3
votes
Accepted
What is a convolutional neural network?
(Of course, similar questions have been asked in the past and there are many sites, papers, video lessons, online that explain how CNNs work, but I think it's still a good idea to have a reference ...
- 37k
3
votes
What are the main algorithms used in computer vision?
Computer vision is a wide field, and besides the fact that deep learning dominates, there are still many, many other algorithms that see widespread use in both academia and industry.
For tasks such as ...
- 86
3
votes
Why do we resize images before using them for object detection?
There are different questions and even different lines of thought here. Let's go through them
On resizing
Why do we need to resize? To fit the network input which is fixed when nets are no Fully ...
- 1,058
3
votes
Accepted
What amount of ressources is involved in building an image recognition system?
One answer is infinite amount of time because it can always be better.
Another answer is:
10k for training set
A PC with a GPU (3~4k USD), google colab (10 USD per month), or other cloud service (...
- 1,259
3
votes
Is it okay to use publicly available Instagram videos to train an AI?
Disclaimer that every attorney will give unless formally engaged: This does not constitute formal legal advice.
This data was published with the expectation of public view
Viewing that data is a ...
- 6,177
2
votes
How do I determine whether a truck is inside its lane?
One possible approach will be to use an algorithm which detects lines (Ex. Hough lines or any deep neural net trained to detect lanes) and use some threshold range so that we can get the lane and the ...
- 21
2
votes
How should we pad an image to be fed in a CNN?
If the computational components of the forward feed through the network have no curvature, which is normally the case in a sum of products, then it can be proven that any constant pixel value is ...
- 7,375
2
votes
What is the difference between image processing and computer vision?
The Wikipedia article related to computer vision gives, in my opinion, a good description of the field and its relation to image processing. Below, I will only cite the most relevant parts of the ...
- 37k
2
votes
Turn photos right-side up?
I don't know if there is an existing pretrained NN that does this but it wouldn't be very hard to modify one to do this.
First, I'd take a pretrained image classification NN (e.g. VGG, ResNet), drop ...
- 3,143
2
votes
How can I detect moving objects in a video by OpenCV without using deep learning techniques?
After a quick scan, it would seem that, in the history of object detection, machine learning has always been at the forefront. Before then, it would just be a heuristic approach.
For a quick answer, ...
- 1,316
2
votes
Accepted
How to calculate the size of a 3d object from an image?
There are hundred of papers on this task some older than I am! Normally this is done by trying to form a box shape around the image than estimate the volume. This task is typically done with multiple ...
- 545
2
votes
How can I "measure" an object using Computer Vision techniques and neural networks?
If the measurements you want from the object aren't too complicated (ie. length of a clearly defined feature), and if you are able to acquire a training dataset of images of the objects similar to ...
- 121
2
votes
How can I "measure" an object using Computer Vision techniques and neural networks?
Father Ted explains why this is a hard problem.
Seriously -- if you have stereo images it should be possible, since that's what we use for depth perception. If you know how far away points x1 and x2 ...
- 121
2
votes
Accepted
How can I make the kernels non-learnable and set them manually?
In most modern neural network frameworks, the update rules for training can be selectively applied to some parameters and not others.
How to do that is dependent on the framework. Some will have the ...
- 26.5k
2
votes
Accepted
Why do we get a three-dimensional output after a convolutional layer?
If you have a $h_i \times w_i \times d_i$ input, where $h_i, w_i$ and $d_i$ respectively refer to the height, width and depth of the input, then we usually apply $m$ $h_k \times w_k \times d_i$ ...
- 37k
2
votes
Accepted
Should I apply image processing techniques to the inputs of convolution networks?
The whole interest of using deep learning-based solutions is that you don't have to do all those pre-processings, i.e. binarization, segmentation of background. CNNs, such as YOLO or FasterRCNN, can ...
- 381
Only top scored, non community-wiki answers of a minimum length are eligible