Questions tagged [computer-vision]
The computer-vision tag has no usage guidance.
48
questions
1
vote
0
answers
45
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?
- 31.2k
16
votes
0
answers
608
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 (...
- 31.2k
1
vote
0
answers
48
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, ...
- 4,272
2
votes
0
answers
140
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 ...
- 3,621
5
votes
1
answer
246
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.
...
- 964
3
votes
0
answers
310
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,...
- 24k
4
votes
2
answers
295
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:
...
- 7,349
2
votes
0
answers
91
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:
...
- 7,349
1
vote
0
answers
40
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
186
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 ...
- 40k
2
votes
0
answers
44
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
4
votes
0
answers
219
views
Find nearest crop of image within another image
ImageAlign[ref, i] works well when image i is fully contained within the reference image ref,...
- 31.2k
1
vote
0
answers
33
views
ImageContents not working on Wolfram Cloud iOS app
I tried using the experimental ImageContents[] function, introduced in MMA 12, on my PC (using Mathematica) as well as on my iPad (using Wolfram Cloud app). On my ...
- 1,524
0
votes
1
answer
896
views
Best laptop specs for a better and faster numerical simulations [closed]
Hope all is well! I am planning to buy a laptop (Windows) and looking for your help to decide the specs that we need to speed up the numerical simulations using Mathematica. The Mathemtica code I used ...
- 313
8
votes
1
answer
376
views
How to detect rectangles with certain colors in an image?
I'd like to find the red bordered rectangles in this image:
Here are my example images:
...
- 31.2k
5
votes
2
answers
382
views
Extract partitions of images after edge detection
Given a edge detected image like this:
I would like to extract each character into a sub-image, i.e so that each new picture only have one character. Is there a simple way of doing this in ...
6
votes
1
answer
265
views
How to track a deformable rod in video?
I have a video of nanotubes in solution taken with a confocal laser microscope. I typically track these nanotubes with Fiesta or Fiji, but in this case, there is variation in brightness that is ...
- 31.2k
0
votes
0
answers
128
views
Use FacialFeatures in Python Web API?
Under the hood, FacialFeatures uses the net-model ResNet-101 Trained on Augmented Casia WebFace Data. I would like to see a tutorial-style answer on how one would ...
- 3,621
7
votes
0
answers
153
views
How to extend ImageCases?
I was very excited to see ImageCases being documented in version 12. But I immediately desired a mechanism for adding more entities to ...
- 31.2k
0
votes
1
answer
143
views
Robust face detection
FindFaces doesn't work when people are far away from the camera. I'm looking for a single accurate method of detecting one or more people in an images, at all ...
- 3,621
10
votes
2
answers
250
views
Efficient multicolor search
I'm hoping someone can help me improve the following fun code-snippet, which takes a target color and searches through a set of images to find the ones that most closely match:
...
- 31.2k
18
votes
2
answers
954
views
How to TextRecognize a screenshot of code?
Are there any specific tricks or options to help TextRecognize work on a screenshot of an Input Cell or code in general?
For example, here's a screenshot that ...
- 31.2k
3
votes
1
answer
360
views
Extract names from a document [closed]
If I have a document, any document, it can be a book, an article, etc, how could I extract people's names from there?
For example, if the input is an article, the output of the function would be the ...
- 101
3
votes
0
answers
224
views
Fourier image correlation is likely to be wrong [closed]
I have images of two identical ellipses, which differ by the orientation.
I want to obtain the difference angle between them by means of phase corelation method (https://en.wikipedia.org/wiki/...
- 307
1
vote
0
answers
130
views
Performance of ImageCorrelate with a masked kernel (via custom distance function)
Context
For an image in-painting task (filling in missing regions in an image, see image below; missing region printed red) I'd like to try a template matching approach.
The idea is to use parts of ...
- 8,399
3
votes
0
answers
745
views
Accessing advanced ZXing settings for BarcodeRecognize
Usual algorithms for detecting the presence of a QR-code in an image seem to have trouble detecting a code when it is tilted (especially at 45°). This is dependent on the resolution as well. The ...
- 8,399
1
vote
2
answers
202
views
How to do the "Sketch colorization" like Project Scribbler using Mathematica? [closed]
Recently, the Adobe release the Project Scribbler
Adobe Max 2017.
The picture is from the P. Sangkloy, J. Lu, C. Fang, F. Yu and J. Hays. Scribbler: Controlling Deep Image Synthesis with Sketch and ...
- 31
0
votes
1
answer
131
views
Removal Background with Shadows on HUE
I have an image of a leaf on a poorly white screen and need to find out just the leaf:
The problem is that it contains greenish shadows, so simple color-based methods are not enough. Thus, I need ...
user53890
4
votes
1
answer
173
views
Speeding up ImageCorrespondingPoints
I have the following problem: I am taking free-handedly photographs from the same scene during e.g. hiking, because sometimes I don't want to lug around a tripod. The goal is e.g. to create later on ...
- 1,255
1
vote
0
answers
258
views
Rectangular object boundary detection
I would like to find the boundaries of an object:
I have looked that the YOLO algorithm but it looks like the results cut off parts of the object a lot. What kind of algorithm can I use to achieve ...
- 111
1
vote
0
answers
530
views
Apply a four-point transform crop to an image
I am attempting to straighten and crop an image by using Edge Detection. The original image looks like this. By using edge detection and finding the max and min values for the points regarding the ...
- 11
9
votes
1
answer
246
views
Adding computer vision datasets?
I find having ResourceData/Objects for machine learning datasets to be extremely useful, with their "TrainingData", "TestData" properties:
Right now there's only a handful:
And even fewer for ...
- 31.2k
48
votes
2
answers
8k
views
Object detection and localization using neural network
Four important computer vision tasks are classification, localization, object detection and instance segmentation (image taken from cs224d course):
These four tasks are all built on top of the deep ...
- 27.4k
2
votes
1
answer
564
views
How to import Robinhood screenshots?
I use an iPhone app called Robinhood to trade stocks and I wanted to play with the portfolio with Mathematica's finance tools. So I took some screenshots of the app and I'm trying to import the ...
- 31.2k
0
votes
0
answers
62
views
Improved version of FindFaces [duplicate]
The built-in function FindFaces seems to miss faces a lot, for example
...
- 31.2k
5
votes
1
answer
262
views
How to write a RCNN (region-cnn)?
Has anyone end-to-end trained a single net that can find the location of objects in an image (with v11.1)? Here's an example of a region-cnn in action, and this is a good description of the approach.
- 31.2k
5
votes
0
answers
479
views
How to train a visual attention model?
In version 11.1 there is a new layer type SequenceAttentionLayer[]. I'm interested in how might this be used to train a recurrent visual attention model (see the ...
- 31.2k
1
vote
2
answers
134
views
What is the algorithm applied by ImageAdjust[image,{c,b,gamma}]
I want to know how ImageAdjust work to change the pixel values by specifying all parameters b,c and gamma.
In openCV, the transformation is linear ...
- 1,976
6
votes
0
answers
578
views
How to recognize multiple objects in an image
I'm trying to do multi-object detection and recognition using Mathematica.
For example, in this image:
img = Import["https://i.stack.imgur.com/lbSwV.jpg"];
the ...
- 166
15
votes
3
answers
6k
views
Nontrivial background removal
I have an image of a product on a poorly made green screen and need to segment out just the product:
The problem is that it contains a mirror, so simple color-based methods are not enough.
I tried ...
- 31.2k
18
votes
3
answers
1k
views
Find lane lines
A crucial step in self-driving car is to detect lane lines. I'm wondering whether this can be achieved robustly using Mathematica's rich image processing tools.
For example how can I take camera ...
- 27.4k
1
vote
0
answers
107
views
List of all valid categories for ImageIdentify? [closed]
Can anyone give a list of valid categories for the second argument of ImageIdentify?
- 31.2k
17
votes
3
answers
1k
views
How to place path lines on an image
I have a "sugarcane crop" image taken from above (with a Drone) which was pre-processed with the MorphologicalPerimeter and EdgeDetection functions of Mathematica, resulting in binary image with a ...
- 434
8
votes
2
answers
387
views
How to detect discolorations in an image?
I'm evaluating the technical quality of an images and I'd like to scan it for defects from dirty sensors. Are there any filters to quickly detect a blob of discoloration? Here are a few examples:
- 31.2k
24
votes
1
answer
1k
views
How can I detect locations of Go (aka Baduk, Weiqi) stones on a board?
The Goal
There are a couple apps that score a Go board from a photo. I was wondering if something like that would be possible with Mathematica. The key step is to detect the positions of the stones ...
- 1,123
2
votes
1
answer
460
views
How to get a full closed contour image [closed]
In this program, I need to select the point on the contour image that has the same abscissa as the center of the contour and has the highest ordinate. However, since the contour is not full closed, ...
- 1,976
1
vote
0
answers
111
views
Using Classifier with NearestNeighbors methods
I am using a Machine learning toolbox on mathematica. I have 8 classes.
Training data: for each class, there 100 samples with size 160.
I used this code.
...
- 1,976
4
votes
2
answers
1k
views
How to label my training images?
I'm switching over Matlab, but I have a problem. Matlab has a GUI tool called the "Training Image Labeler" (shown below) that I use all the time to label my training data for my computer vision ...
- 1,529