Tag Info

4

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 images. This can be a single filter applied to each layer or a seperate filter per layer. These filters are looking for features which are independent of the color,...

4

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 example, your input is 30 x 30 x 3. Assuming stride of 1, no padding, and no dilation on the filter, you will get a spatial shape equal to your input, that is ...

4

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 images: When needed to train on RGB pictures it is not advised to split the RGB channels, you can think of it by trying to identify a fictional cat with red ears,...

4

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 knowledge. Of course, this answer will only give you a flavor of the type of algorithm or model that you will find while solving CV tasks. For example, there are ...

3

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 images we have and, if it works fine, called by our GPLv2 software. We can even use the calling code in Inkscape's plug-in image tracing implementation as a ...

3

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 personally recommend Gonzales and Woods for this, as it gives a pure mathematical explanation to how and why these features are extracted. Essentially the ...

3

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. Given any well-constrained definition, it is then time-consuming to collect relevant data. However, there is some interest in the machine-learning community, as ...

3

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 (probably more expensive than colab) One developer, 1 day lol Two kinds is easier than multiple kinds There is no paper that seeks to answer your question the way ...

2

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 edges of truck, then after extracting the lines, you can easily find the distance between them. Then you need to experiment out on few images to get the ...

2

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 equivalent in terms of effect on convergence results. We wouldn't expect a proof for that, since it would be too trivial to spend time writing up for publication. ...

2

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 article. Computer vision is an interdisciplinary scientific field that deals with how computers can be made to gain high-level understanding from digital images or ...

2

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 its final layer and replace it with one with 4 neurons, representing the 4 orientations (so that you know which way to rotate it). Then I'd take again a ...

2

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 images so the two can generate a more clear picture of the size of the object than one image alone. An object could be 'infinitely' large but its mass could be ...

2

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 what your model will see in your use case (same scale/distance), their bounding boxes and their measurements, a model you could try to implement is a Multi-Task ...

2

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 are, then you can measure distance using trigonometry. No neural networks needed, I guess. https://en.wikipedia.org/wiki/Triangulation_(computer_vision)

2

For a simulation of SNES or N64, the resolution is probably not that high. You can use either online credits or buy new hardware. For online credits, it is recommended if you do teh simulation/training for only several dozens hours, as eache hour costs around 5-10 dollars. AWS is a good choice as it have a large variety of choice for hardware. For higher ...

2

Apart from the multitudes of traditional image segmentation techniques (Watershed, Clustering or Variational methods), newer Segmentation schemes using Deep Learning are actively being used, which provide better results and are better for real-time applications, owing to minimum computation overheads involved. The following blog provides a detailed review ...

2

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 concept of "freezing" a layer, preventing parameters in it being updated. Keras does this for example. Others will do the opposite and expect you to provide a ...

2

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 apply Gaussian smoothing to minimize the artifacts. For example, using Gaussian smoothing in OpenCV with your image results in import cv2 img = cv2.imread('s.png') #...

2

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, here: https://towardsdatascience.com/real-time-object-detection-without-machine-learning-5139b399ee7d That goes over object detection without using machine ...

2

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 $m$ $h_k \times w_k \times d_i$ kernels (or filters) to this input (with the appropriate stride and padding), where $m$ is usually a hyper-parameter. So, after the application of $m$ kernels, you ...

2

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 learn how to retrieve that information by themselves.

2

(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 answer that hopefully will give you the main ideas behind CNNs.) A convolutional neural network (CNN) is a neural network that performs the convolution (or cross-...

2

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 image classification / object recognition, the typical paradigm is some CNN architecture such as a ResNet or VGG. There has been lots of works to extend and ...

2

Some research areas that come to mind which can be useful when faced with a limited amount of data: Regularization: Comprises different methods to prevent the network from overfitting, to make it perform better on the validation data but not necessarily on the training data. In general, the less training data you have, the stronger you want to regularize. ...

2

Mathematically, the convolution is an operation that takes two functions, $f$ and $g$, and produces a third function, $h$. Concisely, we can denote the convolution operation as follows $$f \circledast g = h$$ In the context of computer vision and, in particular, image processing, the convolution is widely used to apply a so-called kernel (aka filter) to an ...

2

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 Convolutional Networks (FCN) What if my net is FCN? Still makes sense to resize to bound the dimension of the input features you want to detect (a person on a small ...

2

To verify the accuracy of the classification stage, you will need labeled images with a single car. To train and verify accuracy of the detection stage and full system, you can: in the datasets with images with multiple cars, manually, mark the image rectangles that contains one car. from previous, split the image in one or more ones, each one containing a ...

2

There are many papers on this but the following is a good start: How to unwrap wine labels programmatically. The author includes source code in Python. You mentioned you do not want to do a panoramic view but that has more than one meaning. If I assume you mean you do not want to rotate the can while taking multiple photos, or you don't want to take ...

2

It depends on your application. In case of text recognition, non-uniform kernels are used since the information about text is less on the horizontal axis and more on the vertical axis. If in your case it is applicable then, it will be good idea. But, if it is not you are better off using a smaller uniform kernel (2x2, maybe). You can also zero-pad your image ...

Only top voted, non community-wiki answers of a minimum length are eligible