Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [image-segmentation]

120 questions
11
votes
1 answer

Why is my Keras model not learning image segmentation?

Edit: as is turns out, not even the model's initial creator could successfully fine-tune it. This is most likely a problem of implementation, or possibly related to the non-intuitive way in which the Keras batch normalization layer works. I'm trying…
Matt
  • 219
  • 1
  • 9
6
votes
2 answers

Why do we need to concatenate in a U-Net?

You might be familiar with the U-Net, a machine learning network deceived for image segmentation. It's basically an encoder/decoder network with some direct links between encoder and decoder segments: I would like to better understand the reason…
henry
  • 163
  • 1
  • 4
5
votes
2 answers

DBScan for image segmentation and clustering: how does it work?

I think I have understood the DBScan algorithm for 2D data points. We can consider the example in scikit-learn. They generate a set of data points: from sklearn.datasets import make_blobs from sklearn.preprocessing import StandardScaler centers =…
LearningAlgorithm
  • 114
  • 2
  • 18
4
votes
2 answers

Tool for annotation of images for semantic segmentation

I have been searching around for a software tool, that I can use for annotating images. More specifically I want to do annotation to be used for semantic segmentation, meaning I want to create masks. I want to be able to create training data for…
lo2
  • 41
  • 1
3
votes
1 answer

How can I create .nii (nifti) file from 3D Numpy array

I have a prediction numpy array. How can I make a .nii or .nii.gz mask file from the array?
Eren Kallikci
  • 31
  • 1
  • 2
3
votes
2 answers

How can I use my own dataset for Image segmentation using Tensorflow

I have a huge problem using my own created dataset for image segmentation using Tensorflow. The dataset that I've build contain images like the one shown below: The problem that I have is: How do I use my own dataset specifically for image…
thegendolz
  • 31
  • 1
3
votes
1 answer

Segmentation Network produces noisy output

I've implemented a SegNet and SegNet ReLU variant in PyTorch. I'm using it as a proof-of-concept for now, but what really bothers me is the noise produced by the network. With ADAM I seem to get slightly less noise, whereas with SGD the noise…
Ælex
  • 31
  • 5
3
votes
2 answers

Splitting a pdf containing batch of scanned documents

My question is primarily: is there any ML research paper about splitting a pdf containing a batch of scanned documents (eg bank statements) into individual documents? I have searched for this but I have not found any relevant research paper or any…
Outcast
  • 1,117
  • 3
  • 14
  • 29
3
votes
0 answers

Are more target labels in a multi-label classification always better?

Context We work on medical image segmentation. There are a lot of potential labels for one and the same region we segment. There can be different medically defined labels like anatomical regions, more biological labels like tissue types or spatial…
Spenhouet
  • 131
  • 4
3
votes
1 answer

Algorithms to do a CTRL+F (find object) on an image

We all know the CTRL+F "Find text..." feature in text editors / browsers. I'd like to study the available algorithms to do something similar on an image. Example of UI/UX: let's say you have an electronic schematic. You draw a rectangle around a…
Basj
  • 180
  • 2
  • 18
2
votes
0 answers

Instance Segmentation using the predefined bounding boxes

I want to do Instance Segmentation using the images in my dataset which are already annotated and I don't want to train the model but use the pre-trained model. I was following this colab notebook. Here I can upload my image and do the instance…
duddal
  • 41
  • 2
2
votes
1 answer

Segmentation model to predict face forward and profile parts of the face

I am developing a model for feature counting on a person's face that consumes three photos (one face forward and two profile pictures). My model can already detect features, but it counts some features twice. Consider the image below. There are only…
sixtytrees
  • 213
  • 1
  • 10
2
votes
1 answer

Transfer Deep Learning from one aerial imagery datset to many others

I am new to Deep Learning but have been able to use RasterVision successfully to predict building footprints within a set of aerial imagery. This aerial imagery data set is for a province of New Zealand. Now that I have a model that predicts…
Aeolian
  • 31
  • 3
2
votes
1 answer

Photorealistic synthetic data for object segmentation

Let's say that we have a very small labelled dataset for instance segmentation and there is a photorealistic physics engine available that can produce synthetic data for us. Looking on the web I haven't found any paper about a similar issue. Has…
Dimimal13
  • 85
  • 8
2
votes
1 answer

Ways of calculating the area of colored regions in a map

Background I am a PHD student trying to improve my data science. One of my research projects, has me tasked with determining the size of the clusters in a colored image of regions. Here is an example image I am using. The coloring is natural as it…
Gabriel Fair
  • 257
  • 1
  • 3
  • 8
1
2 3 4 5 6 7 8