Questions tagged [computer-vision]
The computer-vision tag has no summary.
52 questions
3 votes
2 answers
338 views
1 vote
0 answers
78 views
Is there any way to run segmentation model SAM2?
I would like to run sam2: https://github.com/facebookresearch/segment-anything-2. Does ServiceConnect allow us to connect to meta.ai or llama 3.1 to do things like ...
- 3,880
2 votes
0 answers
260 views
Straightening out rumpled striped bedsheets
I was motivated to investigate this from an seeing a Greg's Hurst answer for a different question. I was curious how to find out what the sheet would look like when flattened with proper size and all ...
- 687
4 votes
1 answer
374 views
Recognizing a Higher Percentage of Multiple Barcodes from an Image
I would like a path or way to find barcodes in an image and read more of them and ideally quicker (It is very slow for an image). So, BarcodeRecognize[] already ...
- 687
1 vote
0 answers
72 views
Any image captioning networks available yet?
Looking for an image captioning network to run in a notebook. I didn't see any on the NN Repo. Has anyone imported one successfully?
- 31.9k
16 votes
0 answers
777 views
How to reconstruct 3d meshes from 2d images of a scene?
The new ImageStitch was nice functionality added in v13, but is there anything available for constructing meshes (with color textures) from a bag of 2D images (...
- 31.9k
1 vote
0 answers
83 views
Is it possible to add new concept to ImageContents
I was hoping to use ImageContents to locate some specific objects in a series of images with a bounding box. However, ...
- 5,094
2 votes
0 answers
179 views
Find the best place to overlay text on an image?
I need to put text over a background image to make a nice looking banner. In order to find the best place to put it, I'd like to know the "focus points" of the image (basically the centers ...
- 3,880
5 votes
1 answer
331 views
Noisy and vague shape recognition
Consider the following image: Imagine I have several images (let's say 40), that look like this one but with slightly different cloud shapes, pixel count intensities and distances between the clouds. ...
- 1,014
3 votes
0 answers
452 views
Displacing / warping an image using a pre-existing optical flow image
ImageDisplacements provides a way to calculate the displacements between two images (e.g for optical flow purposes) and return a two channel image containing the dx,...
- 26.3k
4 votes
2 answers
415 views
Robust method to find vertical lines in image
Consider the following images with vertical grid lines. They can be loaded in mathematica by the following code: ...
- 7,933
2 votes
0 answers
123 views
Detect pentagon in image
Problem: Given a UK Energy Performance Certificate (EPC) image, detect the pentagons containing integers between 1 and 100. (these are isosceles right pentagons) Example EPC image 1: ...
- 7,933
1 vote
0 answers
64 views
ImageCorrespondingPoints[] using my own lists of unmatched points
ImageCorrespondingPoints[] finds a set of matching interest points in two images and returns their pixel coordinates. The doc says it "uses ...
- 227
2 votes
0 answers
245 views
Shape-from-shading algorithms?
Before I go to the effort of writing my own code, I was wondering if there is code available for shape-from-shading algorithms. These take an image (such as a black-and-white image, such as this) and ...
- 43k
2 votes
0 answers
67 views
Faster alternative to ImageCorrespondingPoints?
I'm trying to use ImageCorrespondingPoints to register frames in a video sequence. Computational speed is an important consideration for the application I am ...
- 381