Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [image-processing]

The tag has no usage guidance.

1
vote
1answer
49 views

Convert RGB image to YUV420 using a hlsl shader

I am new to shaders and I need to convert efficiently an RGB image to YUV420. I can convert the RGB image to YUV420 with a simple c++ program that uses the ...
11
votes
0answers
237 views

Why does increasing simplex noise dimension wash it out?

I just tried using this approach to create a tiling 2d simplex noise function with Gustavson's java implementation. The result tiled, but the texture seemed muddy / washed out. I decided to compare ...
5
votes
0answers
127 views

CrazyBump Shape Recognition

I've recently been using CrazyBump, and I think I'm starting to understand how it works. But I'm confused about what it calls Shape Recognition. According to this website, that feature attempts to add ...
4
votes
0answers
129 views

Sinc interpolation and Ideal reconstruction example

I am trying to apply sinc interpolation on this data set. The patches in the left image is a snapshot of AutoCAD 3d faces. Lux values are calculated for centre of each patch that are in 0.3m x 0.3m ...
4
votes
0answers
66 views

Slope Based Texturing

On the main page for Allegorithmic's Bitmap2Material, it mentions that the software uses a Slope Based approach over a Luminance Based approach. What exactly does this mean?
4
votes
0answers
84 views

Recreating a font from a low-quality printout

I have a JPEG file with a 200 dpi scan of a sample printout from a badly maintained old drum printer. I was able to segment it and to collect all instances of each letter together, for example I ...
3
votes
0answers
32 views

Sub-pixel image registration using phase

Currently I'm trying to reproduce the result by the academic papers Sub-pixel Shift Estimation of Image based on the Least Squares Approximation in Phase Region by Fujimoto, Fujisawa and Ikehara (...
2
votes
0answers
136 views

Making an approximately constant color or brightness image

I've been working on implementing the technique from the paper "Designing look-and-feel using generalized crosshatching" which can be found at: http://dl.acm.org/citation.cfm?id=3085054 The paper ...
2
votes
0answers
350 views

how to overcome tracking jitter

I'm working with a object tracking project. Steps: Preprocessing the image and achieve some candidates regions of interest. For each region, test if it is the target by ORB/BF. After the target ...
2
votes
0answers
94 views

SIFT Feature Extraction

I am trying to implement the SIFT feature extraction algorithm. I have a few questions which are not very clear from the paper: When interpolating the extrema with 2nd order functions, do we upscale ...
2
votes
0answers
73 views

Bilinear Transformation not working

I implemented this algorithm to fit given image to specified quadrilateral but the output is blank. I implemented it in C# as follows ...
2
votes
0answers
310 views

Template matching subpixel accuracy

I use template matching to detect a specific pattern in image.The shift determined is very shaky. Currently I apply it to R,G,B channel separately and average the result to obtain float values.Please, ...
1
vote
0answers
49 views

Why don't discretization errors occur with compute-shaded kernel filters?

An efficient compute-shaded image filter would be emitted with (screenX / [kernel width], screenY / [kernel height], 1) groups and one kernel in each group, allowing texels to pass into groupshared ...
1
vote
0answers
46 views

Tanget plane of an image

My problem is about tangent plane. I have an image (m by n). I obtain surface normal vector using machine learning methods. Then i would like to obtain tangent plane for this surface normal. To ...
1
vote
0answers
74 views

Ray Tracer Shadowing

So I'm working on an assignment where we have to design a simple ray tracer. The program has two objects that it can use, sphere and cube. It can render the cube and spheres, it also does shading on ...
1
vote
0answers
56 views

How to make Convolved Diffuse and Specular image in C#

I am trying to take either a HDR panoramic or HDR cubeMap and from that create a Lambert Irradiance environment map and a Cook-Torrence Specular environment map. I am stuck at the proper ...
1
vote
0answers
35 views

3D reconstruction using 2D matched points

I have 2 images, called left and right images. I have some matched points $[c_l,r_l]$ and $[c_r,r_r]$ in both of them (these points are in pixel coordinates). For a 3D point in the real world, they ...
1
vote
0answers
234 views

Getting improper undistorted images for stereo calibration

I am trying to calibrate stereocamera using left and right chessboard images available at github.com->opencv/opencv/tree/master/samples/data After undistorting them, left images seem to look right ...
1
vote
0answers
65 views

How to merge multiple exr into a single multilayer exr?

Are there some tools or softwares to merge multiple exr into a single multilayer exr? I only find a tool to split a multilayer exr into multiple exr. And it seems that Blender, Mitsuba, Darktable ...
1
vote
0answers
107 views

Finding Segments in Continuous line

I'm trying to break a continuous line segment into multiple, straight segments. I've tried using the Hough transform but have found it unreliable for getting the line segments I'm looking for and ...
1
vote
0answers
152 views

Octave matrix to image pixels too small (do not have 1 pixel per integer)

I am working on a project which plots points over a checkerboard (representing seats for people). I would like each pixel in the image to represent each integer matrix entry. After updating my ...
1
vote
0answers
113 views

image warping, given the rotations/translations

in OpenCV there is functions to warp any 2D image using a homography matrix (3x3), e.g. cv2.warpPerspective. These matrices are generally constructed using point ...
1
vote
0answers
163 views

Feature detection for embedded platform OpenCV

I'm trying to do object recognition in an embedded environment, and for this I'm using Raspberry Pi (Specifically version 2). I'm using OpenCV Library and as of now I'm using feature detection ...
1
vote
0answers
82 views

Image cleaning - removing all regular shapes ( circles, squares, text, icons etc. )

I'd like an automatic method to clean images. I've been looking at the GIMP, and its command line (cli) interface, in scheme / lisp. It looks very promising, but I'm a complete novice, so I'd be ...
1
vote
0answers
49 views

Removing a darkened caption with text on it in an image

Alright so I'm a complete n00b at image processing so forgive me if my question sounds vague. I'll try to supplement it with what I have learnt until now and also a couple of images. See the caption ...
1
vote
0answers
74 views

How to enhance scans of golden emboss?

I am looking for smooth way to enhance scans of golden emboss on. For now it takes sometimes hours to select out the golden part and then manipulate into suitable color. But I hope to learn some more ...
0
votes
0answers
38 views

Prefered gpu for deep learning

Im planning to buy a custom build pc for computer vision because I want to make a career switch in it. So Im still confused about the choice of gpu. Should I go with nvdia(cuda) or amd(opencl)? Also ...
0
votes
0answers
25 views

Using Hough Transform to detect lines in an image

I am using hough transform on the following image after canny edge detection ...
0
votes
0answers
45 views

How to ensure that the raytrcing coordinate system is teh same as the projection one?

I have 2 shading models right now, one is using voxels the other one is the standard projection absed renderization method. Putting them side by side I have noticed that no matter what I do one is ...
-1
votes
0answers
35 views

what is the limit of Triangulation Matting?

I am studying triangulation matting in computer graphic. It seems very simple but very cool to identify the foregrouand and background. However, I didn't find what's the limit of it. Besides the ...