Stack Overflow
Stack Overflow

Questions tagged [computer-vision]

Use this tag for questions related to Computer Vision -- any aspect of software that enables computers to perceive, understand and react to their environment using cameras. For questions related to image filtering and quantification, use the tag [image-processing] instead.

Computer vision enables images, or sequences of images, to be processed by a computer using algorithms. There are many aspects to computer vision, including mathematics, physics (especially optics), imaging hardware, , and .

Some basic techniques used in computer vision are:

  • Image acquisition
  • Pre-processing
  • Feature Extraction
  • Detection/Segmentation
  • High-Level processing
  • Decision making
13127 questions
4
votes
1 answer

OpenCV 2.4 - Playing Video from file on OSX

I install Open CV and all the deps with brew Following this tutorial: http://docs.opencv.org/3.1.0/dd/d43/tutorial_py_video_display.html#gsc.tab=0 I'm able to have it working with my webcam but unable to read a AVI or MP4 file. Every time, when I…
Philippe Remy
  • 1,741
  • 2
  • 13
  • 19
4
votes
2 answers

Use large dataset in Tensorflow

I would like to train a CNN with a large dataset. Currently I load all data into tf.constant and then loop through it with a small Batch size in tf.Session(). That works fine for a small fraction of the dataset, but when I increase the input size I…
arm712
  • 107
  • 2
  • 11
4
votes
1 answer

type of recognition of convolution neural network

I was trying to create a convolution neural network for the recognition of animals, vehicles, buildings, trees, plants from a large data-set having the combination of these objects. At the time of training I got a doubt about the way in which the…
Arun Sooraj
  • 687
  • 9
  • 20
4
votes
4 answers

Find eyes and mouth in an face image

I'm curious about finding the eyes from an image. Let's say I have an thresholded image and I have 3 blobs representing two eyes and the mouth. Is there a way to detect which of the region of pixels is eye region and approximate it's center?
Madalin
  • 355
  • 5
  • 14
4
votes
2 answers

How to merge two .obj files after texture mapping process?

After applying texture on 3D mesh, three files (including a .obj, .mtl and an atlas file) are generated. I have mapped textures on 2 objects and now I want to merge these objects together, but I do not know how to merge their files. Is there any…
Alireza Parvizimosaed
  • 197
  • 2
  • 12
4
votes
1 answer

Color histogram for multiple images in a directory using cv2.calcHist in python

I am new to computer vision and this is my first assignment. I am trying to create rgb histogram corresponding to each image in a folder. Let's assume I have 10 images in test folder (which is inside my current working directory). And I want to…
Dheeraj Singh
  • 625
  • 1
  • 11
  • 20
4
votes
2 answers

Why do we have normally more than one fully connected layers in the late steps of the CNNs?

As I noticed, in many popular architectures of the convolutional neural networks (e.g. AlexNet), people use more than one fully connected layers with almost the same dimension to gather the responses to previously detected features in the early…
Ali Sharifi B.
  • 545
  • 1
  • 5
  • 14
4
votes
1 answer

How is full convolution performed using MATLAB's conv2 function?

I am trying to get some input on MATLAB's conv2 function. Suppose that we have an image I of dimensions 5 x 5 and a kernel K that is 3 x 3. conv2(I,K) would return a 7 x 7 matrix. What extra operations are being done that I am not aware of? I can…
Dstn Pk.
  • 43
  • 1
  • 3
4
votes
3 answers

Transform a frame to be as if it was taken from above using OpenCV

I am working on a project for estimating a UAV (quadcopter) location using optical-flow technique. I currently have a code that is using farneback algorithm from OpenCV. The current code is working fine when the camera is always pointing to the…
A. Sarid
  • 3,716
  • 2
  • 23
  • 48
4
votes
1 answer

Any ideas on real life rocks 3d Reconstruction from Single View?

So in general, when we think of Single View Reconstruction we think of working with planes, simple textures and so on... Generally, simple objects from nature's point of view. But what about such thing as wet beach stones? I wonder if there are any…
Rella
  • 59,216
  • 102
  • 341
  • 614
4
votes
2 answers

How to do object detection using CNN's features in tensorflow?

I am trying to make an end to end unified model that detects(localizes) the object in an image. The object itself can be of many types, like "text in the wild", but the surrounding features of the object should determine where the region of…
iratzhash
  • 579
  • 9
  • 17
4
votes
1 answer

Different output of GoogLeNet Model in Virtual Machine and Ubuntu 14.04

I am using GoogleNet model for binary classification of images. Earlier, I was using the virtual machine and now I am using Ubuntu 14.04. Both are giving me different results. I tried to find out a lot where is the problem but couldn't pinpoint it.…
Ashutosh Singla
  • 691
  • 4
  • 12
  • 28
4
votes
4 answers

Object Detection for identifying object in image

I want to detect image contents ,what i need to do is find if image is of shirt or pant . Img 1 Img 2 If i provide image of t shirt then based on comparing the shape i need the result that the given image is of t shirt What i tried is…
usernan
  • 562
  • 6
  • 21
4
votes
1 answer

Is there a way in MATLAB to compute which discrete image regions enclose or are enclosed by another region?

Given the following image: I'd like to identify which colored regions are enclosed by or enclose which other colored regions. How might this be computed? Is there a way to create a sort of tree or table that shows this information? Example: All…
Gabriela Alberto
  • 45
  • 7
4
votes
1 answer

How can I measure distances in stereo images?

I Have two images( left and right ) I want to measure the real distance on image? When I click on the image, ı ll get real distance to clicked point to camera. Left Image: Right Image: I have calibrated the two images. I want to use EmguCV to get…
CbsHs
  • 73
  • 9
1 2 3
…
99
100