Questions tagged [computer-vision]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
45
votes
2answers
7k 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 ...
24
votes
1answer
741 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 ...
18
votes
3answers
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 ...
16
votes
3answers
845 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 ...
16
votes
2answers
369 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 ...
14
votes
3answers
5k 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 ...
10
votes
2answers
215 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: ...
9
votes
1answer
209 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 ...
8
votes
1answer
114 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: ...
8
votes
2answers
300 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:
6
votes
1answer
180 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 ...
6
votes
0answers
497 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 ...
5
votes
1answer
233 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.
5
votes
0answers
108 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 ...
5
votes
0answers
440 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 ...
4
votes
2answers
177 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 ...
4
votes
1answer
161 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 ...
4
votes
1answer
137 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 ...
4
votes
1answer
915 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 ...
3
votes
0answers
166 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/...
3
votes
0answers
380 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 ...
2
votes
1answer
221 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 ...
2
votes
1answer
394 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
vote
2answers
96 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
vote
2answers
165 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 ...
1
vote
0answers
90 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 ...
1
vote
0answers
210 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 ...
1
vote
0answers
360 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 ...
1
vote
0answers
69 views

List of all valid categories for ImageIdentify? [closed]

Can anyone give me a list of valid categories for the second argument of ImageIdentify?
1
vote
0answers
103 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. ...
0
votes
1answer
116 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 ...
0
votes
0answers
119 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 ...
0
votes
1answer
102 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 ...
0
votes
0answers
60 views

Improved version of FindFaces [duplicate]

The built-in function FindFaces seems to miss faces a lot, for example ...