Questions tagged [computer-vision]

Questions related to image representation, segmentation, visual object categorization and image processing algorithms in general.

Filter by
Sorted by
Tagged with
4
votes
1answer
1k views

Blind deblurring: Can you train a neural network on artificially blurred images?

I'm reading the paper "Blind Image Blur Estimation via Deep Learning" which was published in IEEE Transactions on Image Processing in 2016. As I understand it, the blind deblurring algorithm presented ...
4
votes
1answer
2k views

Simple way for histograms classification

I'm trying to classify a histogram. I have 4 classes and I generate 4 histograms (h1, h2, h3 and h4) for each class. Each histogram contains 10 bins (attributes describing an object) on the x-axis and ...
4
votes
2answers
2k views

Adjusting Grid Size in YOLO?

I was going through the YOLO Object Detection Paper by Joseph Redmon. The authors use a grid size of $S = 7$. If I am not wrong, the network architecture has carefully been curated for this specific ...
4
votes
0answers
149 views

Neural Network or Differentiable Graph Matching

Searching for: Neural Network solutions or implementations (learnable algorithm) for inexact graph matching. Graph matching: Given two graphs GM = (VM , EM) and GD = (VD, ED), with |VM| = |VD|, ...
4
votes
0answers
60 views

Metrics to identify the presence of more than one circle in a set of (x,y) coordinates

I have a set of $(x,y)$ coordinates that represent any number of circles in a plane. What I am trying to do is determine whether there is 1 or more circles present in the data set. This would normally ...
4
votes
0answers
408 views

Train Neural Network For Handwritten Chinese Characters

The article here: http://novanoid.github.io/2014/09/26/training-a-neural-network-to-recognize-handwritten-digits/ discusses and implements a way to recognize handwritten digits. For images with a ...
3
votes
1answer
52 views

Are there any other image classification methods besides using neural networks?

When reading about image classification, the only occurring terms are "neural networks", "deep learning" and "CNN". It seems like there are no other methods for this task. I have worked with neural ...
3
votes
1answer
104 views

What Percent of Neural Network is used while processing a single image [closed]

What percent (on average) of entire Neural network (say, AlexNet) is actually used while processing a single image. There should only a very small amount of network that should actually be utilized ...
3
votes
2answers
3k views

Classifer for unbalanced dataset?

Is there any classifer that can natively support unbalanced datasets? Or what best practices you can suggest to handle such datasets? For example I want to solve task called "pedestrian detection" ...
3
votes
1answer
7k views

Fine Tuning vs. Transferlearning vs. Learning from scratch

In my master thesis, I am researching on transfer learning on a specific use Case, a traffic sign detector implemented as a Single Shot Detector with a VGG16 base network for classification. The ...
3
votes
2answers
517 views

Scale-invariant feature transform explanation

How do I explain the scale-invariant feature transform (SIFT) to a layman?
3
votes
2answers
192 views

What are the state of the art methods for person segmentation and person pose identification

I have tried asking this on another forum, but after 4 months there are no posted answers, so I am asking it here: What is the current state of the art approach for determining the pose of a person (...
3
votes
1answer
1k views

What is a multimodal embedding?

I don't have computer vision background, yet when I read some image processing and convolutional neural networks related articles and papers, I constantly face the term, multimodal embedding. Can ...
3
votes
1answer
919 views

cross channel parametric pooling layer in the architecture of Network in Network

While reading the paper of Network in Network, I feel confusing about some points. The following figure shows the network architecture, looks like to me the two layers with red circle are just fully ...
3
votes
1answer
181 views

Should I ever manually modify training data?

TL;DR: I'm reviewing a computer vision + machine learning module that someone else wrote, and I've discovered that she is manually cleaning up training data. Is that ever a good idea? The Details ...
3
votes
1answer
536 views

maximum a posteriori vs squared loss

I am unclear about max a posteriori and squared loss. Let me assume I have $N$ images and $\mathbf{y}_i$ is the label of the image $i$, where, $\mathbf{y}_i\in \mathbb{R}^{C\times 1}$ - a binary ...
3
votes
1answer
136 views

Same value of min and max in min-max normalisation

By the definition of min-max normalisation, the value is divided by max - min, what if the max and ...
3
votes
1answer
2k views

How Single Shot Detectors (SSD) object detection calculates it's class scores and bbx locations?

As in the paper I can understand SSD try to predict object locations and their relevant class scores from different feature maps . So for each layers there can be different predictions with respect ...
3
votes
1answer
3k views

How are bounding box proposals generated in Google's paper “Deep Neural Networks for Object Detection”?

Paper mentioned in the question title deals with localization of certain objects in images. Paper mentions generating multiple types of object masks using deep neural network based on ImageNet, ...
3
votes
1answer
4k views

max pooling layer and number of feature channels

When reading some deep learning papers, which sometimes mentioned that max-pooling layer for downsampling can also be used for increasing the number of feature channels(maps). This confused me a lot. ...
3
votes
1answer
2k views

kernel size and stride value for fully convolutional network for semantic segmentation

I am not very clear about some technical details in implementing Fully Convolutional Networks for Semantic Segmentation. The paper discusses three models: fcn32, fcn16 and fcn18. According to this ...
3
votes
2answers
295 views

Poorness of Kernel methods on visual pattern recegnition?

I am currently reading the recent papers mainly written by Y. Bengio [1],[2],[3]. There are very strong claims about poorness of Kernel methods on recognizing handwritings in many general cases but ...
3
votes
1answer
173 views

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 ...
3
votes
2answers
2k views

How are YOLO anchor boxes generated?

I am recently trying out darkflow, a Tensorflow implementation of Darknet written by Joseph Redmon. Looking at the configuration files, I noticed a section called region as shown below. ...
3
votes
1answer
69 views

Quantitative evaluations for image classification

Hello I am working on the classification of different weed categories. I want to know what quantitative evaluation I can do other than find the accuracy?
3
votes
1answer
722 views

What is a poselet?

I've seen the term "poselet" mentioned a few times (e.g. A and B) as some sort of construct used in facial recognition.
3
votes
1answer
838 views

Why are linear SVMs used with HoG feature descriptors?

Ok, almost all applications I have seen that use HoG features use linear svm as classifier. Can someone explain for me why linear svm are chosen and why they give good performance? Are linear svm ...
3
votes
0answers
16 views

Extreme Image Noise Removal

I've been trying to solve a noise removal (from images) problem using deep learning and I've tried a lot of the newer architectures for noise removal including FFDNet, NLRN and MWCNN. The problem is, ...
3
votes
1answer
203 views

Custom Loss Function - Inducing sparsity

From the comments, I realized that my question wasn't clear enough, so I'll start with a short background. I am trying to construct an attention model that performs classification based on just a ...
3
votes
1answer
641 views

Facenet: Using Ensembles of Face Embedding Sets

The Facenet is a deep learning model for facial recognition. It is trained for extracting features, that is to represent the image by a fixed length vector called embedding. After training, for each ...
3
votes
0answers
341 views

How to draw bounding boxes to make comparisons?

I have a whole bunch of prediction bounding boxes for my test images. What is the best way to draw the bounding boxes so that I can use it to compare across different models? For example, for each ...
3
votes
0answers
538 views

Can I generate adjacency matrices from directed graph images? [closed]

I have some images of very simple directed graphs with just a few nodes and edges. I know there is lots of tools, which print out graphs with a adjacency matrix is an input, but I need to do it the ...
3
votes
1answer
139 views

regarding the convolutional network structure of FCNN

The paper of Fully Convolutional Networks for Semantic Segmentation , gives the following image, . What do those numbers represent, 96, 256, 384, etc? Are them ...
2
votes
4answers
681 views

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 ...
2
votes
2answers
332 views

Why has deep learning only shown decent results in the fields of computer vision and speech recognition? [closed]

We all know about the success of ImageNet, AlphaGo etc which used deep neural networks in computer vision, or the use of RNNs in Google Translate. But why are we not seeing similar advances in other ...
2
votes
1answer
1k views

VGG and max pool layers

Why haven't VGG's config (https://arxiv.org/pdf/1409.1556.pdf) one max pooling layers after each conv layers?
2
votes
1answer
886 views

Is there an exhaustive dataset of just grayscale images or a CNN model ( preferably a caffe or tensorflow model ) Pre-trained on grayscale Images?

I have a very limited dataset of around 12k grayscale images and wanted to know if there is a CNN model that I can use for fine tuning or an grayscale image dataset that can be used for pre-training. ...
2
votes
2answers
2k views

What does it mean an histogram vector normalization with L1/L2 norms?

I was reading these slides about Bag of Features (BoF). At slide 23 you can read: each image is represented by a vector, typically 1000-4000 dimension, normalization with L1/L2 norm What does ...
2
votes
2answers
2k views

Is it acceptable to have a slightly lower validation loss than training loss

I have a dataset which I split as 80% training and %20 validation sets. (38140 images for training, 9520 for validation) Model that I train is a deeper (~45 layers) convolutional neural network. I ...
2
votes
1answer
777 views

Can CNN detect text in arbitrary position of image?

My task is that: there are some text in some position (left, right, top, bottom center, etc) of an images. The style (include size, orientation, font, etc) of text is arbitrary and the content length ...
2
votes
1answer
21 views

Are there any Non Neural Network models to do face detection in constrained domains?

In some constrained domains(eg: car driver), the camera is stationary which means the background will not change much. And we can sure when the car is running, there must be a driver. In this kind of ...
2
votes
1answer
75 views

What would be the ideal dataset to train a model to detect advertisements in an image?

I am thinking of the requirements for training a model that would be able to detect if there is any kind of ad in an image. I know that this sound too broad not just for a question on CV but for ...
2
votes
3answers
1k views

Which image format is better for machine learning .png .jpg or other?

I'm trying to train a neural network with images. Since I'm extracting images from a video feed I can convert them either to .png or .jpg. Which format is preferred for machine learning and deep ...
2
votes
1answer
48 views

Mode-collapse problem in GAN: How to grasp the full entropy of the distribution we want to model in GAN

In pix2pix GAN paper( https://arxiv.org/abs/1611.07004), authors found that the noise vector and the dropout are not efficient in grasping the full entropy of the data distribution we want to model. ...
2
votes
2answers
612 views

Object detection : is deep learning the only way to go?

It seems that deep learning based approaches are currently more superior to the more "traditional" methods in the domain of object detection. Methods like YOLO, for example, seem to be doing something ...
2
votes
1answer
210 views

Benchmarks and state-of-the-art methods for semantic segmentation of 3D meshes?

I'm wondering what benchmarks there exist for semantic segmentation of 3D meshes? I have already found "A Benchmark for 3D Mesh Segmentation"; is this currently the only benchmark that exists for 3D ...
2
votes
1answer
104 views

Is it technologically feasible to identify and recognize gas prices from Google Street View?

I just had an idea for an economics research project and would like to know your thoughts. Is this feasible using something like OpenCV? Please forgive my ignorance in terms of the current state of ...
2
votes
2answers
654 views

Difference between scale-space transform and wavelet transform

What is actual difference between scale-space and wavelet transform? It seems that wavelets require an orthonormal basis of kernels, whereas scale-space does not. Is it the only difference? Can scale-...
2
votes
2answers
1k views

Automatic background removal from images without user interaction

I am trying to develop an image search application. I have crawled through e-commerce websites and obtained a data set of images (about 2.5 Million). Now I want to identify the object of interest from ...
2
votes
2answers
1k views

Pretext Task in Computer Vision

I am new to Computer Vision. I am reading many papers and i see the term "pretext task". Can anyone explain what exactly it means. Thanks in Advance.

1
2
3 4 5
7