Questions tagged [image-segmentation]

For questions related to image segmentation (in computer vision and related AI fields).

Filter by
Sorted by
Tagged with
24
votes
5answers
27k views

How can I deal with images of variable dimensions when doing image segmentation?

I'm facing the problem of having images of different dimensions as inputs in a segmentation task. Note that the images do not even have the same aspect ratio. One common approach that I found in ...
9
votes
1answer
2k views

Deep learning for bitmap tracing: extract simple svg paths from bitmaps

I need an algorithm to trace simple bitmaps which only contain paths with a given stroke width. It is obviously very easy to generate bitmaps from vector paths, so creating data for a machine ...
5
votes
1answer
68 views

Do models train better if the labelling information is more specific (or dense)?

I'm working on a project where there is a limited dataset of videos (about 200). We want to train a model that can detect a single class in the videos. That class can be of multiple different types of ...
4
votes
1answer
896 views

What do the words “coarse” and “fine” mean in the context of computer vision?

I was reading the well know paper Fully Convolutional Networks for Semantic Segmentation, and, throughout the whole paper, they talk use the term fine and coarse. I was wondering what they mean. The ...
4
votes
2answers
125 views

What are the best algorithms for image segmentation tasks?

I recently started looking for networks that focus on image segmentation tasks related to biomedical applications. I could not miss the publication U-Net: Convolutional Networks for Biomedical Image ...
4
votes
0answers
37 views

How can I improve the performance of a model trained to detect vehicle poses?

I'm looking for some suggestions on how to improve our vehicle image recognition. We have an online marketplace where customers submit photos of their vehicles. The photos need to meet certain ...
4
votes
0answers
35 views

What are some neural network models that can use auxiliary info during training for image segmentation?

What are some deep learning models that can use supplementary information other than RGB channels for image segmentation? For example imagine a poorly shot image of a river (blue) that shows a gap, ...
3
votes
1answer
6k views

What is a fully convolution network?

I was surveying some literature related to Fully Convolutional Networks and came across the following phrase, A fully convolutional network is achieved by replacing the parameter-rich fully ...
3
votes
1answer
77 views

What is the use of the regular convolutional layer in expansion path of U-Net?

I was going through the paper on U-Net. U-net consists of a contracting path followed by an expanding path. Both the paths use a regular convolutional layer. I understand the use of convolutional ...
3
votes
2answers
594 views

Which evaluation methods can I use for image segmentation?

I implemented an image segmentation pipeline and I trained it on the DICOM dataset. I compared the results of the model with manual segmentation to find the accuracy. Is there other methods for ...
3
votes
1answer
73 views

How to incorporate a symmetry constraint in the loss function to train a CNN?

I have a task of extremely sparse binary segmentation, i.e. the segmentation mask contains either 0 or 1, and there are ~95% zeros and only ~5% ones. I use the focal loss to address the sparseness (...
3
votes
1answer
43 views

Can neural network help me with detecting center coordinates of particles in an image?

I have an image of some nano particles that was taken with Scanning Electron Microscope (SEM) attached here. I want to obtain center points coordinates (x,y) for each particle. Doing it by hand is ...
3
votes
0answers
34 views

Validation accuracy higher than training accurarcy

I implemented the unet in tensorflow for the segmentation of MRI images of the thigh. I noticed I always get a higher validation accuracy by a small gap, independently of the initial split. One ...
3
votes
2answers
122 views

Is such a captcha AI-resistant?

Let's say we have a captcha system that consists of a greyscale picture (of a part of a street or something akin to re-captcha), divided into 9 blocks, with 2 missing pieces. You need to choose the ...
3
votes
3answers
154 views

If I trained a model to perform semantic segmentation on images with only one object, would it also work on images with multiple objects?

I'm working on semantic segmentation tasks in the medical space using the U-Net. Let's say that I train a U-Net model on medical images with the goal of segmenting out, say, ligaments, from a medical ...
2
votes
1answer
53 views

What are some references that describe known filters (or kernels) and how we can create new ones?

I'm pursuing a master's degree in Artificial Intelligence. My final work is about Convolutional Neural Networks. I was looking for information about filters (or kernels) of the convolutional layers. I ...
2
votes
1answer
173 views

What make a CNN suitable for image classification or for semantic segmentation?

I've just started with CNN and there is something that I haven't understood yet: How do you "ask" a network: "classify me these images" or "do semantic segmentation"? I think it must be something on ...
2
votes
1answer
107 views

Why everyone is using CNN for image segmentation?

I'm a newbie in artificial intelligence. I have started to research how to do image segmentation and all the papers that I have found are about CNN. Most of them use the same network, U-net, but with ...
2
votes
1answer
51 views

How many ways are there to perform image segmentation?

I'm new in Artificial Intelligence and I want to do image segmentation. Searching I have found these ways Digital image processing (I have read it in this book: Digital Image Processing, 4th edition)...
2
votes
1answer
163 views

“Outside-in” versus “Inside-out” machine learning

A little background... I’ve been on-and-off learning about data science for around a year or so, however, I started thinking about artificial intelligence a few years ago. I have a cursory ...
2
votes
1answer
110 views

How to add some data input in a CNN?

There is this problem I have encountered, I was trying to classify the pixels from input image into classes, sort of like segmentation, using a encoder-decoder CNN. The “interested” pixels usually ...
2
votes
0answers
16 views

Predicting the the motion of a 3D object when the motion of a set of markers is known

trying to figure out where to get started with this: I have a few hundred CT images where certain three-dimensional features in the image (anatomy) are moving in a correlated fashion with a set of ...
2
votes
0answers
69 views

Semantic segmentation - background or ignore for non-target classes?

I am training a deep learning model for semantic segmentation. I am using the cityscapes dataset for training/evaluation. In cityscapes, there are 34 classes, and of which, we consider only 19 classes ...
2
votes
0answers
37 views

How and why do state-of-the-art models in medical segmentation differ from general segmentation models?

I am just getting into medical image segmentation and have been able to understand the state-of-the-art architectures, like Double UNet, UNet++, and Multiresunet. What I haven't understood yet: Why ...
2
votes
0answers
29 views

Loss function decays linearly in segmentation MRI fascia

I am working on a segmentation of MRI images of the thigh. I am trying to segment the fascia, there is a slight imbalance between the background and the mask. I have about 1400 images from 30 patients ...
2
votes
0answers
26 views

What is human-level performance for semantic segmentation?

I see so many papers claim to have an algorithm that beats 'human-level performance' for semantic segmentation tasks, but I can't find any papers reporting on what the human-level performance actually ...
2
votes
1answer
2k views

What are some good alternatives to U-Net for biomedical image segmentation?

Soon I will be working on biomedical image segmentation (microscopy images). There will be a small amount of data (a few dozens at best). Is there a neural network, that can compete with U-Net, in ...
2
votes
0answers
37 views

Tversky Loss paper implementation: Recall/Precision do not improve as stated

I have been trying to implement this paper and I am very much intrigued. I am working on a medical image problem where I have to segment very small specimens on Whole Slide Images (gigapixel ...
2
votes
0answers
25 views

What are the current tools and techniques for image segmentation in order of pragmatism?

To explain what I mean I'll depict the two extremes and something in the middle. 1) Most pragmatic: If you need to just segment a few images for a design project, forget AI. Go into Adobe Photoshop ...
2
votes
0answers
128 views

What is the difference between using a backbone architecture and transfer learning?

I'm super new to deep learning and computer vision, so this question may sound dumb. In this link (https://github.com/GeorgeSeif/Semantic-Segmentation-Suite), there are pre-trained models (e.g., ...
2
votes
0answers
74 views

Is there a deep learning-based architecture for digit localisation?

I'm new to object detectors and segmentation. I want to localize digits on a plate as fast as possible. All images of the dataset are normalized to $300 \times 60$. There are different approaches to ...
2
votes
0answers
28 views

Confidence Maps and Non-Linearity

I am currently trying to improve a CNN architecture that was proposed for generating depth images. The architecture was originally proposed for autonomous driving and it looks like following : The ...
1
vote
1answer
100 views

Best approach for 2D Grid Image Segmentation

I'm working on a project where I need to extract text from grocery discount flyers like the Costco announcement below (retrieved in a random google search, Costco is not the deal here): If I just run ...
1
vote
1answer
56 views

Have I understood the loss function from the original U-Net paper correctly?

In the original U-Net paper, it is written The energy function is computed by a pixel-wise soft-max over the final feature map combined with the cross entropy loss function. ... $$ E=\sum_{\mathbf{x} ...
1
vote
1answer
49 views

Training a classifier on different datasets with different image conditions for different labels causes the model to infer using the background

I have an interesting problem related to training the model on two different datasets for the target feature on images taken on different conditions, which might affect the model's ability to ...
1
vote
1answer
46 views

How does general image background removal AI work?

I'm well aware of the inner workings of CNN models for object detection, and although I've not worked on a semantic segmentation problem I can imagine how it works. With these types of models, we need ...
1
vote
1answer
25 views

How to create vector representation of roadmap like scans

What would be the best way to create a vector representation of roadmap like scans? The goal I am trying to achieve is illustrated below. The left side represents the source image, the right side the ...
1
vote
1answer
61 views

How do I generate a feature representation of a saliency map (or mask)?

Generally, CNNs are used to extract feature representations of an image. I'm right now dealing with the class of CNN that produces saliency maps, which are generally in the format of a mask. I'm ...
1
vote
1answer
40 views

What does 'downsampling' and 'upsampling' mean in coarse-to-fine segmentation?

The paper here in section 2.1 Coarse-to-fine prediction: To increase the field of view presented to the CNN and reduce the redundancy among neighboring voxels, each image is downsampled by a factor ...
1
vote
0answers
20 views
1
vote
0answers
27 views

How can I improve the performance on unseen data for semantic segmentation using an auto-encoder?

I am using simple autoencoders for the task of semantic segmentation on the VOC2012 dataset. I am currently using a simple autoencoder based model. It is trained on adam optimizer with cross-entropy ...
1
vote
0answers
25 views

Could the data augmentation lead to the model learning features which corresponds to data augmented data and not to the real data?

I am trying to train a Unet network with Synthetic data to do binary segmentation due to the fact that is is not easy to collect real data. And there is something in the training process that I do not ...
1
vote
0answers
235 views

Getting bounding box/boundaries from segmentations in UNet Nuclei Segmentation

From my understanding, in a tissue where nuclei are present and need to be detected, we need to predict bounding boxes (either rectangular/circular or in the shape of the nucleus, i.e. as in instance ...
1
vote
0answers
46 views

Training a CNN for semantic segmentation of large 4600x4600px images

I am trying to implement a CNN (U-Net) for semantic segmentation of similar large grayscale ~4600x4600px medical images. The area I want to segment is the empty space (gap) between a round object in ...
1
vote
0answers
18 views

Model output segmentation maps which are not full

I created a VGG based U-Net in order to perform image segmentation task on yeast cells images obtained by a microscope. There are a couple of problems with the data: There is inhomogeneity in the ...
1
vote
0answers
48 views

Extending patch based image classification into image classification

I am trying to classify tampered, pristine images from set of images, in that I have built a network in which I would divide the image into multiple overlapping patches and then classify them into ...
1
vote
0answers
67 views

How can the FCNN reduce the dimensions of the input from $1048 \times 100$ to $523 \times 100$ with max-pooling?

I am trying to implement a paper on Image tempering detection and localization, the paper is Image Manipulation Detection and Localization Based on the Dual-Domain Convolutional Neural Networks, I was ...
1
vote
1answer
53 views

How to quickly change hand-drawn shapes to symmetrical polished shapes?

Given a hand-drawn shape, I'd like to generate the corresponding symmetrical polished shapes such as circle, rectangle, triangle, trapezoid, square, parallelogram, etc. A short video demonstration ...
1
vote
0answers
76 views

Is it necessary to label the background when generating the labelled dataset for semantic segmentation?

When I label images for semantic segmentation (using u-net, if that matters), is labeling the background (anything I am not interested in) necessary? Will it improve the network's performance?
1
vote
0answers
46 views

Suppress heatmap non-maxima in segmentation with UNet

I'm using U-Net for image segmentation. The model was trained with images that could contain up to 4 different classes. The train classes are never overlapping. The output of the UNet is a heatmap (...