The Stack Overflow podcast is back! Listen to an interview with our new CEO.

Questions tagged [computer-vision]

Computer vision includes methods of processing, analyzing, images and high-dimensional data to form high level understanding and recognition of the scene or images.

Filter by
Sorted by
Tagged with
5
votes
2answers
341 views

Function for response over image scales

I want to write code in matlab to find a characteristic scale of an image patch. I have an image patch X, I need to maximize function F(X,sigma) so that sigma is ...
5
votes
2answers
558 views

How do we distinguish between Image Recognition,Detection and Segmentation?

I am reading image processing book.while reading i am getting terms like image detection,image recognition and image segmentation. it seems that all above terms are one and the same.i am totally ...
5
votes
1answer
4k views

Convolution Kernels for Image Filtering

As I understand it, in image processing, when it is desired to apply a filter of some sort to an 2D image, a kernel is applied to all the pixels of the 2D image in a process called convolution. Median,...
5
votes
2answers
2k views

Commonly used test image sets

In the image analysis literature there are a variety of ways people show the usefulness of their method. For example, performance on an ideal signal corrupted by noise, an artificial signal ...
5
votes
2answers
93 views

Viewpoint dependant deformation of objects in photos

I have a question concerning the deformation of objects in photos. Which deformations can an object depicted on a photo undergo through viewpoint and condition changes? Some deformations I have in ...
5
votes
2answers
458 views

How do you measure the accuracy of a stereo system?

I have a philosophical question of sorts for users familiar with a multi-view stereo setup. Imagine that I need to measure the dimensions of a large building and I take several photos of the building ...
5
votes
1answer
1k views

Ambiguous results of phase correlation in pattern recognition

We are using phase correlation to find pattern on image and what we get is 15% of results is spurious. Ours pattern has 32x32 pixels and image for research has 32x512 pixels. So we put Pattern to ...
5
votes
1answer
499 views

Online boosting (training on the fly) for face detection

I want to implement an on-the-fly training process for face detection. I'm not sure but it seems it's called online boosting. Вefore, I have used OpenCV face detection with my own cascades, but I'm ...
5
votes
3answers
2k views

How to remove text region in a document image? or extract image from a document image

Given a document image (i.e. newspaper), how to extract photos in it or remove text region? I think traditional OCR methods may not be suitable here, as I don't need to recognize the text, and OCR is ...
5
votes
1answer
587 views

Compare image segmentation approaches

I've got a question related to a comparison of image segmentation algorithms. I'd like to compare two algorithm results to each other in step one. In another step I'd like to compare the two ...
5
votes
1answer
398 views

image feature extraction

We are given a set of grayscale image patches obtained from images after edge detection. Each patch is 10x10 pixels with intensity varying between 0 and 255 for each pixel. This set may contain a very ...
5
votes
1answer
520 views

Can you detect circles only using the hough line transform?

I'm not talking about the Hough Circle Transform (where you replace the representing eqns, hence the parameters with a 3D set) but a Hough Line Transform. My solution to this: A hough line transform ...
5
votes
1answer
3k views

Translation invariance in max-pooling and cascading with convolutional layer

I am reading through this page about convolutional neural networks and I am confused about the part about max-pooling (downsampling a signal/image with the maximum value in a block). Apparently, one ...
5
votes
2answers
1k views

Finding similar pictures in a database

I have large database of pictures, about a few million. I need an algorithm to find pictures which are similar to those in the database, up to a scale factor or a crop and shift (I have only these ...
5
votes
2answers
4k views

Opencv color segmentation of traffic signs: HSV ranges

I am working on a project to detect and recognize signs in images from the LISA Traffic Sign Dataset. Since the images are very noisy (in regard to background) I am trying to segment the signs based ...
5
votes
1answer
791 views

Estimating Plane Pose Without Knowledge of Intrinsic Camera Parameters

Assume a camera has no skew, and has square pixels, that is, its camera-calibration matrix, $K$, looks like: $$ K = \left[\begin{matrix} \alpha&0&u_x\\0&\alpha&u_y\\0&0&1 \end{...
5
votes
2answers
3k views

Sequentially get the outer contour of an Edge Image

Hi CV/Pattern Recognition Community, because my last thread was concerning the segmentation as BLOB and started to getting too big, with no clear results. I would like to reconcider the last step of ...
5
votes
1answer
2k views

Pose from Homography matrix - Zhang method

this post also contributes to the post at Step by Step Camera Pose Estimation for Visual Tracking and Planar Markers by Jav_Rock (since I cannot add any comment there and I don't know why) It can be ...
5
votes
1answer
218 views

How to amplify regions with specific color in an image?

I want to amplify regions with a specified color in an image. For this purpose I have defined a simple function $B(x,y)=s_r(x,y) \cdot w_r + s_g(x,y) \cdot w_g + s_b(x,y) \cdot w_b$ which produces a ...
5
votes
0answers
186 views

Red eye detection [closed]

Project: Red eye detection Description: I want to remove red-eye from images. I am not able to use face detector because, the faces in the images are not always frontal and also the images are of ...
5
votes
0answers
2k views

Jacobian Matrix of a Quaternion $q$ respect to Angular Velocity $\omega$

In the context of visual tracking and video processing I need to estimate variations of the orientation related to the angular velocity. I am trying to calculate the Jacobian matrix of a quaternion $\...
4
votes
3answers
999 views

Resources for an introduction to computer vision

Does anyone have any suggestions on good resources or sites for learning about computer vision?
4
votes
2answers
157 views

Struggling to find a good definiton for Gabor-Descriptor

I am attempting to implement the Gabor Descriptor based on the following paper Image Copy Detection Using a Robust Gabor Texture Descriptor. It is the best paper that I have found on the subject. It ...
4
votes
2answers
7k views

Can deep neural networks achieve real-time video analysis?

Recently, convolutional neural network based, deep architectures (DNN) such as AlexNet and VGGnet have been very successful in image classification challenges (e.g. ImageNet) and action recognition/...
4
votes
2answers
9k views

Licence plate detection with different backgrounds

I just studied the Algorithm of ANPR (Automatic Number Plate Recognition) from the chp 5 of book Packtpub.Mastering.OpenCV.with.Practical.Computer.Vision.Projects in which they detect the vehicle ...
4
votes
4answers
3k views

Detect lanes from a filtered image

I am working on lane detection system and I would like some suggestions from you as to how to detect lanes from a filtered image which I got after performing certain operations. Firstly, I should ...
4
votes
5answers
257 views

Determine when a constant signal changes to another constant value

As a novice to digital signal processing I have a scenario that probably seems trivial but I dont know the answer to. I want to detect when a signal changes but ignore noise. 255 255 255 255 255 ...
4
votes
2answers
360 views

Convex Optimization in Signal and Image Processing

In signal processing, convex optimization plays a useful role in problems such as sparse signal recovery and filter design. What other places does convex optimization appear? For example, in ...
4
votes
2answers
350 views

What is the rate of expansion of an image as it aproaches the human eye?

My intuition about the scaling (x,y) of the 2d representation of the 3d object generated by our native visual processing system tells me it accelerates as it ...
4
votes
2answers
380 views

Detection periodic elements in image

I am working on a university project in which I need to find a periodic net element in an image. The net is a set of diagonal lines in a specific angle ( which I don't know in advance ) on a noisy ...
4
votes
2answers
1k views

Confused about HSI and HSL color spaces

I am reading a book for image processing algorithms (Andreas Koschan, Mongi Abidi: Digital Color Image Processing) and for the contrast algorithm it says that I can either go ...
4
votes
2answers
3k views

how can i perform a registration to 2D images using ''rigid " transformation in matlab?

i need to perform registration to 2D image using"rigid transformation" in matlab .i need this for measuring the similarity between my images .any one know how this can be done using matlab? an ...
4
votes
1answer
1k views

How are Object Recognition and Content-based Image Retrieval interlinked?

I need help on understanding the linkage between Object Recognition and Content-based Image Retrieval. Does OR use CBIR to find similar objects with the help of algorithms like SIFT etc or does CBIR ...
4
votes
1answer
13k views

Image comparison using MATLAB

I want to compare a bunch of depth images coming from Kinect and eliminate the similar ones. Those images present posture of a single user sitting on the chair (depicted in). My idea is to create a ...
4
votes
1answer
731 views

Feature Detection on a Circular Metal Surface for Character Recognition

Hello I'm trying to recognize characters on the circular metal surface. Without any preprocessing I could match cropped features with original image. I've actually cropped 2 characters together to ...
4
votes
1answer
1k views

Corner detection using Chris Harris & Mike Stephens [duplicate]

I am not able to understand the formula, What is $W$ (window) and intensity in the formula mean, I found this formula in opencv doc http://docs.opencv.org/trunk/doc/py_tutorials/py_feature2d/...
4
votes
1answer
3k views

Base line detection of text lines

I came across various works in the literature of document analysis addressing the problem of detecting base lines in multi-oriented texts. But no amount of search could give me satisfactory answer to ...
4
votes
2answers
2k views

Recover myself from Dilate and Erode for noise reduction

i have obtained some skin detection map (i post below two example of detection map). but, i'm using a normal webcam and the map is noisy. Not a lot, just a bit. I think i can remove noise only with ...
4
votes
2answers
8k views

Image Shadow Removal Using OpenCV and Python

How do I remove a shadow after MOG2 background subtraction using OpenCV Python? I used all morphological operations, gaussian and median blur, thresholding. it removes noises but deep shadow is ...
4
votes
2answers
347 views

How can I learn image processing in a practical way?

I am a beginner in image processing and I have to learn to program in MATLAB as soon as possible. I started with Rafael Gonzalez book, but understanding this theoretical knowledge and mathematical ...
4
votes
1answer
933 views

Topological skeleton matching techniques

What are the most common and best topological skeleton matching techniques? Suppose I have skeletonized object and corresponding 2D model of this object. What are the next steps to match pattern? ...
4
votes
2answers
2k views

blur detection using opencv

I'm writing a script to detect blur images using OpenCV by applying Laplacian filter and calculate the std but there is a problem the std for images that contain motion blur is very close to those ...
4
votes
2answers
4k views

Why optical flow ? why not tracking

I have a question that might be stupide ! Supposing that I try to detect object moving in a video or human action. Many works are based on optical flow computation. My question is why using OF is ...
4
votes
1answer
5k views

Iterative Lucas-Kanade algorithm

How is iterative refinement is applied to the estimate obtained by Lucas-Kanade algorithm? I am familiar with the following steps: Estimate velocity at each pixel using one iteration of Lucas and ...
4
votes
1answer
195 views

What scale should a detected SIFT point be extracted at?

I've heard this from a few different researchers but I can't find a definitive value. Given the "scale" extracted by David Lowe's SIFT detector, we need to extract a descriptor at a specific scale. ...
4
votes
1answer
131 views

How to get to shoulders localization on image photo? [closed]

I have a project on my university. I have to localize from video where are shoulders of person in movie. Do have any advise how to get to this? I thought about corner detection or some kind of ...
4
votes
1answer
73 views

How to calculate performance of your object recognition algorithm and compare results with others?

I am working on a novel object recognition algorithm with BoF implementation for my MSc project and it performs fairly well. I am using it on Caltech101 dataset. I want to compare the results with ...
4
votes
1answer
128 views

Fourier Transform Computer Vision Textbook

I am required extremely fast to fill the gap and learn Fourier Transform with application in Computer Vision. It was easy to find mathematical aspects of Fourier Transform, but I am more interested ...
4
votes
1answer
2k views

How are the scaling parameters included (extracted from) an essential matrix?

An essential matrix relates corresponding points between two images assuming that a camera satisfies the pinhole camera model, and can be expressed as: $$E=K'^TFK$$ where K is the calibration and F ...
4
votes
2answers
2k views

Face Detection + Cropping

Project: Face Detection Description: I want to detect and crop a face in an image. The image is captured through webcam and only one face per image.I used OpenCV face detector, but I was not ...