Image segmentation arises in computer vision and digital signal processing. The goal of image segmentation is to partition a digital image into pieces, where each piece corresponds to some semantically important concept. Usually, this means that each pixel is assigned to one of the concepts. An simple example is dividing a picture of a person into the subject (the person in the foreground) and the background (whatever is behind and around the subject).
Questions tagged [image-segmentation]
98 questions
17
votes
1 answer
What are the difference between Dice, Jaccard, and overlap coefficients?
I come across three different statistical measures to compare two sets, in particular to segmentation on images (e.g., comparing the similarity between the ground truth and the segmented result).
What are the differences between these measurements…
RockTheStar
- 11,277
- 31
- 63
- 89
12
votes
3 answers
Loss function for semantic segmentation?
Apologizes for misuse of technical terms. I am working on a project of semantic segmentation via convolutional neural networks (CNNs) ; trying to implement an architecture of type Encoder-Decoder, therefore output is the same size as the input.
How…
Florin Lucaciu
- 121
- 1
- 1
- 3
5
votes
1 answer
SVM for Image Segmentation?
I turn to this forum for advice with the following problem. If you could please shed some light on any aspect of this question I'd be very grateful.
Problem decription:
I'm trying to use an SVM to segment a grayscale image of a puncture in polymer…
Jacob
- 81
- 1
- 7
5
votes
2 answers
CRF or MRF energy functions for image segmentation
I am currently working on image segmentation for the purposes of computer vision. I have read many papers and a few books dealing with MRFs and CRFs for computer vision. All of them define an energy function based on the single pixel and…
RCountZero
- 103
- 6
4
votes
1 answer
Training an Object Detection Model Using with Artificial Data from Video Games
I had an interesting idea of using artificial data gathered from screen shots of a high-resolution video game as a cheap substitute for labeled real data, which can be quite expensive or difficult to obtain. I've seen variants of this idea in the…
Surgical Commander
- 369
- 1
- 3
- 9
4
votes
0 answers
BatchNorm after ReLU
I am currently experimenting with different settings for a U-Net (https://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/) based image segmentation and I was unable to find out if it makes any sense to place a BatchNorm layer after a…
disputator1991
- 73
- 1
- 5
4
votes
5 answers
is K-Means clustering suited to real time applications?
I want to segment a sequence of RGB images (basically it's a video) based on their colors in real time. KMeans is an easy and intuitive algorithm to use in this case, but it's execution time is very sensitive to the clusters' centers initialization…
S.E.K.
- 139
- 1
- 2
- 8
4
votes
1 answer
Identify region of interest in image
I'm currently trying to work on the challenge https://www.kaggle.com/c/noaa-right-whale-recognition; I've done basic image recognition work before (Identifying plankton), but this particular challenge requires an additional step: identifying where…
user2187656
- 141
- 2
3
votes
3 answers
Overlap-tile strategy in U-Nets
I was reading the U-Nets paper and there is a mention of some "overlap-tile strategy" in it that I am not quite familiar with. Here is the paragraph from the paper where it has been introduced:
What do they mean by "only us[ing] the valid part of…
Wololo
- 191
- 6
3
votes
0 answers
In image segmentation, is Dice score usually reported as an average between classes?
Dice Similarity or Dice Score is a common evaluation metric for segmentation projects with high class-imbalance. It measures the overlap agreement between discrete classes from two images, ranging between 0 - 1 per class. Usually papers report one…
hirschme
- 750
- 1
- 7
- 21
3
votes
1 answer
Combining semantic segmentation with image classification (FCN + CNN)
I am currently working on a project that involves classifying each image as Good/Bad/Failed. We have a working convolutional neural network approach that works decent.
I also have trained a Fully convolutional neural network to do segmentation. THe…
user27108
- 53
- 4
3
votes
1 answer
Fully Convolutional Neural Network Exploding Logits and Loss
I am trying to train a fully convolutional neural network for 3D medical image segmentation, I have started from the architecture of this paper with the differences being that I have images of varying sizes so I train the network one image at a time…
Miguel
- 1,323
- 8
- 22
3
votes
1 answer
Using pretrained segmantation network for unseen motives
For a research project, I need to do a segmentation on images. Since the motivation is nothing any of the big networks was ever trained on, I would ask if it still makes sense to use pretrained segmentation networks like SegNet to do the…
Luca Thiede
- 657
- 6
- 13
3
votes
1 answer
Can U-Net be used for counting objects?
If I understand the U-Net paper correctly, the NN output is segmentation of known objects on the image from the background. In other words, the network will try to mark all the pixels which are part of the detected objects, but it won't distinguish…
johndodo
- 171
- 3
2
votes
4 answers
Hints on this computer vision / machine learning problem
I've been working for a while on a pet problem. The task is to identify and segment out the dark lines and possibly the wiggly ones too.
I'm not looking for anyone to solve this problem for me...I'm just at the point where I feel I'm losing my…
user1269942
- 228
- 3
- 7