Software Engineering Stack Exchange
Software Engineering Stack Exchange

Questions tagged [image-processing]

57 questions
12
votes
1 answer

Computational Complexity of Correlation in Time vs Multiplication in Frequency space

I am working with 2d correlation for image processing techniques (pattern recognition etc...). I was wondering if there is a theoretical approach on how to tell when to use multiplication in frequency space over correlation in time space. For sizes…
Moe
  • 223
  • 2
  • 5
7
votes
1 answer

Best practice for Restful API that perform heavy calculations (Image Processing)

We are currently developing an image processing restful api. Server performs some CPU-heavy computations image processing upon request and return the image to the client. We want to make this a single http request (all computation should be…
Tom Peach
  • 209
  • 2
  • 8
6
votes
2 answers

How are dynamic images programmed?

I have two friends that want to create a jewelry store, focused on customized jewels. The core feature is the jewelry designer, based on a jewel model. Here's an example of the sort of thing I am looking to create :…
Fabrício
  • 199
  • 1
  • 4
6
votes
1 answer

How to "de-dupe" similar lines (detected using the Hough Transform as rho/theta pairs)

I'm trying to identify an object (a cube) in a set of photos. Using Canny/Sobel/Hough I've managed to get the photo down to a set of lines that are pretty accurate; however if I plot these lines on my image there are a lot of duplicates where the…
Danny Tuppeny
  • 896
  • 6
  • 13
6
votes
1 answer

Kth selection routine - Floyd Algorithm 489

I have recently come across a promising Kth selection routine that reportedly outperforms quickselect the Floyd, Rivest Select routine. This Wikipedia article provides a pseudocode version which I tried to translate to C. The link to the actual…
Andy Dansby
  • 141
  • 8
5
votes
0 answers

Counting Barrels / Hough Transform

i'm trying to find a way to count barrels on an image. For this I'm using Hough Transformation. I tried my code first recognising eyes and it works excellent. But now the problems is when i try to find more than one center on the image. For the eye…
Ignacio
  • 67
  • 2
4
votes
0 answers

How to OCR and/or recreate lines of Egyptian Hieroglyphs in Unicode/HTML?

I am wondering how to take these Hieroglyphs and make them into Unicode. I read through the Tesseract docs on how to create training data, but it seems largely tailored toward "traditional" writing, that goes in one direction and has only one…
Lance
  • 2,537
  • 15
  • 34
4
votes
3 answers

How to process large image with a minimum time lag

I am trying to create a web UI for image processing, with some operations similar to what a site like fotor.com offers. However, I have problems to achieve a similar performance. For example, lets say I uploaded an image on fotor.com of around 3+ MB…
BJ Patel
  • 151
  • 4
4
votes
1 answer

Getting started with object detection - Image segmentation algorithm

Just getting started on a hobby object-detection project. My aim is to understand the underlying algorithms and to this end the overall accuracy of the results is (currently) more important than actual run-time. I'm starting with trying to find a…
Dev Kanchen
  • 143
  • 4
4
votes
1 answer

How to maintain standard quality of images uploaded by many users?

We're developing a site where individuals (store owners) will be able to take pictures and upload to the site. Our biggest concern is the variance in quality of pictures across the site. The options we are considering are: Minimum image cleaning…
rami
  • 41
  • 3
4
votes
1 answer

Stereo images rectification and disparity: which algorithms?

I'm trying to figure out what are currently the two most efficent algorithms that permit, starting from a L/R pair of stereo images created using a traditional camera (so affected by some epipolar lines misalignment), to produce a pair of adjusted…
TheUnexpected
  • 221
  • 1
  • 5
3
votes
1 answer

How to guess which pieces of text belong to which lines in a scanned document?

I want to be able to analyze a five-years archive of supermarket receipts. The receipts are scanned, and thanks to Google Cloud Vision API, the result of an OCR is available. Google's API, however, gives only the text and its geometrical position on…
Arseni Mourzenko
  • 134,780
  • 31
  • 343
  • 513
3
votes
1 answer

How to Define the Bandwidth in Mean Shift Clustering?

I am making a program using Java todo colo quantization using mean shift clustering algorithm and the image is RGB with resolution of 512x512. I want to reduce the image file size by reducing the total color in the input image. I have a problem with…
user10057710
  • 73
  • 1
  • 3
3
votes
2 answers

Parallel Image Processing Best Practices

When doing (possibly heavy) pixel processing on a large image, multithreading becomes a must. The standard practice is to initiate a loop whose indices are partitioned into multiple threads within a thread pool. The performance benefits become…
MathuSum Mut
  • 219
  • 1
  • 7
3
votes
0 answers

Rotation logic for MNIST Handwritten Digit Dataset

I am currently applying some pre-processing to this dataset. Some of the digits are extremely rotated and I would like to know how others managed to get them 'upright'. I have implemented something on matlab which finds the difference between (most…
Norman Bentley
  • 131
  • 1
1
2 3 4