Questions tagged [computer-vision]
Questions about algorithms for processing and analyzing images and videos.
265
questions
25
votes
5answers
37k views
What is the difference between object detection, semantic segmentation and localization?
I've read those words in quite a lot of publications and I would like to have some nice definitions for those terms which make it clear what the difference between object detection vs semantic ...
21
votes
3answers
46k views
What are the differences between computer vision and image processing?
What are the differences between computer vision and image processing? For example, in object recognition, what are the roles of computer vision and image processing?
12
votes
1answer
305 views
Google DeepDream Elaborated
I've seen a few questions on this site about Deep Dream, however none of them seem to actually speak as to what DeepDream is doing, specifically. As far as I've gathered, they seem to have changed the ...
11
votes
3answers
13k views
What is the difference between the fundamental matrix and the essential matrix?
Could someone, in plain english, explain the distinction between the fundamental matrix and the essential matrix in multi-view computer vision?
How are they different, and how can each be used in ...
11
votes
1answer
3k views
Deriving the Sobel equations from derivatives
Many sites give the Sobel operators as the convolution mask for smoothing an image. However, I haven't found a single site that describes how you can derive the operators from partial first ...
9
votes
3answers
1k views
Intuition for convolution in image processing
I have read many documents about convolution in image processing, and most of them say about its formula, some additional parameters. No one explains the intuition and real meaning behind doing ...
8
votes
1answer
8k views
What is the difference between 'features' and 'descriptors' in computer vision / machine learning?
I've read multiple time sentences similar to
Finally, for standard image classification bag-of-words
features based on SIFT descriptors have been found
critical for high performances. We first ...
7
votes
3answers
10k views
Shannon's entropy for an image
Shannon's entropy [plog(1/p)] for an image is a probabilistic method for comparing two pixels or a group of pixels.Suppose an image with a matrix of 3x3 has pixel intensity values
...
7
votes
1answer
817 views
Computer vision: Why do random filters perform similar to edge detectors?
I read here that "a randomly initialized filter acts very much like an edge detector!". I want to know if there are any papers describing and explaining this phenomenon.
7
votes
2answers
315 views
Automated lip-reading: inferring what someone is saying, based upon video of them speaking
Some humans can lip-read fairly well: by watching someone who is speaking, they can tell what the speaker is saying (even without hearing the speech).
Has there been any work on building computer ...
7
votes
1answer
2k views
Computer vision: object detection with labels that are single coordinates
Are there papers in the literature that address the following object detection task ?
The task can be described as follows:
Given a set of images, the labels are just coordinates (x,y) that ...
7
votes
0answers
2k views
Detecting the damaged regions in cars
Detecting the regions where a car has been damaged and the extent to which it has been damaged is a very interesting problem. It has potential applications in automatic auto insurance claims. ...
6
votes
3answers
236 views
In lieu of neural networks and deep learning, what are some approaches to computer vision?
So much software related to computer vision relies on AI and neural networks, I wonder some of the approaches which don't use those methods. How could some of the mainstays of computer vision (eg. ...
6
votes
1answer
157 views
using orientation sensor data to predict image points
I want to use Android's gyro/accelerometer/magnetometer to predict (over a very short time interval) how image points corresponding to a fixed object will change (without trying to scan for them in ...
6
votes
1answer
2k views
How to compare SURF points in two images
I know how to find SURF feature points and have code to find them, but I have no idea how to find the same point in 2 different images, I have
laplacian, scale, orientation, descriptor, response and ...
6
votes
1answer
5k views
Does there exist a data compression algorithm that uses a large dataset distributed with the encoder/decoder?
If my goal were to compress say 10,000 images and I could include a dictionary or some sort of common database that the compressed data for each image would reference, could I use a large dictionary ...
6
votes
1answer
288 views
Why is Scale Space Needed to Detect Scale Invariant Features?
I have been doing research on the SIFT (scale invariant feature transform) algorithm, and while I have repeatedly read that in order to detect image features that do not vary with respect to scales of ...
5
votes
2answers
672 views
Segmenting a human body point cloud into limbs
I have a human body point cloud taken through a Kinect (v1). Now, I want to segment the point cloud into different parts, namely hands, lower arms, upper arms, torso, upper legs, lower legs, feet and ...
5
votes
1answer
108 views
What is the point of an active shape model in facial recognition?
From what I understood, the Active Shape Model (ASM) is used in facial recognition. I figured out how the ASM works but I don't get why we use it.
How this shape is suppose to be interpreted for ...
5
votes
1answer
619 views
Advantages of adaboost over gentleboost in applications, or vice versa?
I've been researching on AdaBoost and GentleBoost classifiers, but can't seem to find a clear answer to the question:
What is Adaboost better at classifying in computer vision?
What is GentleBoost ...
5
votes
1answer
15k views
Convert HSV to RGB colors
HSV colors are composed of a triple of numbers: hue $\in [0, 360)$ (in degrees), saturation $\in [0, 1]$ and value or brightness $\in [0, 1]$. RGB colors instead are more well-known and are also ...
5
votes
2answers
8k views
find the actual size of an object from pixel coordinates
I am quite new to vision and OpenCV, so forgive me if this is a stupid question but I have got really confused.
My aim is to detect an object in an image and estimate its actual size. Assume for now ...
5
votes
1answer
706 views
How to choose the number of HOG pyramid layers?
Reading Histograms of Oriented Gradients for Human Detection, I cannot see any discussion of how many layers there should be in the HOG pyramid. OpenCV offers a scaling factor of 1.05 which would mean ...
4
votes
4answers
3k views
How to generate stereo image pair from a stationary mono camera?
I have a stationary mono camera which captures a single image frame at some fps. Assume the camera is not allowed to move,how do i generate a stereo image pair of the acquired frame? Is there any ...
4
votes
2answers
2k views
Object recognition - given an image, does it contain a particular 3D object of interest?
I have in mind a particular 3D object. Given an image taken by a camera, I want to check whether that image contains an instance of my object.
For instance, let's say that the object is a bathroom ...
4
votes
4answers
1k views
Which algorithm for counting the occurrences of a certain pattern (spots) in an image?
The Problem :
Finding the number of occurrences of a certain pattern (or shape) in an image. In my example, the problem is about finding the number of spots (in variety of sizes) in an image. See ...
4
votes
4answers
1k views
Efficiently labelling training data in machine learning
Obviously it always depends on the specific case. However, my question is how to label data efficiently without writing a source code from scratch which solves the final problem itself?
For example, ...
4
votes
1answer
239 views
Machine learning: do the benefits of more data plateau after a certain point?
This question is both general in nature and also specific to computer vision. If this is the wrong forum, apologies in advance and suggestions on where to post would be much appreciated.
After a ...
4
votes
2answers
299 views
Is there a metric for the similarity of two image filters?
Definitions
An image filter is a matrix $m \in \mathbb{R}^{k_1 \times k_2 \times k_3}$ which gets applied to an image $I \in \mathbb{R}^{l_1 \times l_2 \times l_3}$ as a discrete convolution
$$I'(...
4
votes
3answers
175 views
Is there an efficient algorithm to extract the farthest ends of a thin contour?
Let's say you have pixel bitmaps that look something like this:
From this I can easily extract a contour, which will be a concave polygon defined by a set of 2D points. The question is what is the ...
4
votes
1answer
1k views
Training and testing image sizes for classification in computer vision
When training a classifier for object detection using features extracted from images (eg HoG features), how important is it that the images used for training fed into the classifier in their natural ...
4
votes
1answer
723 views
Difference between Image Analysis and Computer Vision
I have searched the web and I have only found the differences between Image Processing and Computer Vison (also in this website too). In addition, sometimes Image Analysis is confused with Image ...
4
votes
1answer
617 views
Register images containing objects with varying distance to the cameras
I'm learning about using image registration to align two images, e.g., two photographs of the same scene taken from a slightly different location. What factors influence how well we can align the ...
4
votes
1answer
62 views
Feature detector that doesn't use corners
I'm trying to use computer vision to identify objects an image. I am currently using the SURF algorithm, but Harris and SURF both find virtually no points on our objects (a paper ball and a deodorant ...
4
votes
1answer
38 views
Inverting radial distortion
I'm trying to understand the math behind correcting a radial distortion (caused by a lens), but I'm failing to have it explained in simple terms.
I found several examples that proceed this way: a ...
3
votes
4answers
2k views
How can I sum pixel values over a rotated rectangle?
I have an optimization problem in which I need to sum pixel values in an image over a rectangular region. This is a core component of the optimization so it will be done often and the naive solution ...
3
votes
1answer
197 views
How does facial recognition work?
I'm interested in learning about how facial recognition works. I'm especially interested in the algorithms or approach that is used. What are the leading methods for facial recognition? Is there a ...
3
votes
3answers
190 views
How center the eyes of human face at specific pixels?
I am facing a problem with processing some frontal facial images.
I need to adjust the centers of the eyes (irises) to be at certain specific pixels in the image. In other words, i need to transform ...
3
votes
2answers
160 views
How to detect facial landmarks - using haar and other way?
I have done some projects using haar cascade(Ex.- Face-detection,Eye inside face detection,shoe detection etc), I also have some knowledge about it. I have trained my own models learning from youtube, ...
3
votes
3answers
614 views
Is the Tomasi-Kanade factorization still commonly used as a modern computer vision technique?
My understanding is that, in very rough terms, the Tomasi-Kanade algorithm published in 1992 describes a way to reconstruct the 3D structure of an object from multiple images of that object, given ...
3
votes
1answer
846 views
Given a low resolution video, is it possible to create a higher resolution image
This question is purely theoretical as I've not been able to find anyone who's done such a thing, so my question is - is it possible, and if not why?
Say you have a short video (CCTV) of a face, or ...
3
votes
1answer
168 views
Multi object image segmentation methods
I want to survey the state-of-the-art in image segmentation. Is there a paper on how to segment multiple objects in an image? The segmentation papers I read, normally identify one of the many objects ...
3
votes
1answer
97 views
What is the name of this problem in Computer Vision?
My google skills have failed me during research for a college project. Our task is write a program that describes an image in spacial terms, e.g. "Cat on the left of a chair", or for a simple image "...
3
votes
1answer
2k views
Similarity between two geometric shapes
I have two shapes in a 2D space, not necessarily convex, and I'd like to compare how similar they are. How can I define a robust distance metric to measure their similarity, and how can I compute it?
...
3
votes
1answer
113 views
Environment requirement in training image dataset for classifier
I have a question about preparing the dataset of positive samples for a cascaded classifier that will be used for object detection.
As positive samples, I have been given 3 sets of images:
a set of ...
3
votes
3answers
326 views
Handwritten character recognition as characters are being traced
I'm looking for an OCR technique (PCA or SVM or anything else) in a peculiar setting. I want to detect the motion of the finger so that if someone writes something in front of the camera in the air, I ...
3
votes
1answer
151 views
Which Is a Better Way of Obtaining Scales, Gaussian Blur or Down Sampling?
In computer vision, scales are important when we carry out a scene analysis. Choosing different scales affect the result of the analysis. For example, if a face is relatively small in the scene, then ...
3
votes
1answer
52 views
Finding a method to classify pixels according to how drastic their intensity change
I am looking for a method to classify pixels into three groups: (1) Pixels which does not change their intensity much in general (the slight changes may be due to noise only), (2) Pixels which change ...
3
votes
1answer
1k views
Removing common background in image processing phase for classification
I'm trying to build a machine learning classifier that can detect which object is in an image. I have a labled training set of images and am currently in the image processing phase. Each of these ...
3
votes
1answer
166 views
Image Comparison tuned to Human Perception
Say I have two systems that take the same drawing commands and starts drawing on their respective platforms (i.e. HTML Canvas). After this is done, I want to save and compare these two images to ...