Computer Vision Jobs

13 were found based on your criteria {{ paging.total|number:0 }} were found based on your criteria

show all
  • Hourly ({{ jobTypeController.getFacetCount("0")|number:0}})
  • Fixed Price ({{ jobTypeController.getFacetCount("1")|number:0}})
Fixed-Price - Expert ($$$) - Est. Budget: $250 - Posted
HI im looking for an expert to help me in the image processing project and the requirements are as follows: 1. Use Chehra Tracker on stereo pair facial image. Note: you can use toys 2. Apply stereo depth finding algorithms and disparity algorithms ( state of art algorithms ) 3. Get depth of noise by using chehra tracker points and then but artificial noise on it and see what is the difference in depth. this is the link https://sites.google.com/site/chehrahome/add-ons i have all the required documents and code and i can share with you , it is C++
Skills: Computer vision Digital Signal Processing Image Processing
Fixed-Price - Expert ($$$) - Est. Budget: $2,000 - Posted
We are looking for a senior developer to finalize an mobile application that shall capture images with the mobile camera to stitch images into a panoramic image. WE have a codebase from a previous version made to an older mobile that worked fine and now we want to to work better and to newer mobile devices. This code will be released to developer to review and rebuild. We have a company with 5 developers that are in the computer vision that can support you if any questions on the more tech side.
Skills: Computer vision MySQL Programming PHP
Fixed-Price - Intermediate ($$) - Est. Budget: $150 - Posted
Hi, We have developed an android application that records short videos of smiles threw the smartphone’s front camera. These low quality videos (see the attached example) are being sent to a remote server, analyzed (the analysis is the essence of this current job proposal) and report is being sent back (also, part of this proposal) The requirements are as follows: 1. Develop the remote server algorithm for analyzing the “smile asymmetry”, which is a comparison between the right and left sides of the lips when smiling. We would like you to implement an algorithm for detecting the lips and calculate the “smile asymmetry” on every frame of the input video (Please note that the remote server is a desktop computer). 2. Run consistency check (see below “Algorithm Testing method”). 3. Produce several graphs that present the lips asymmetry behavior along the video. 4. Produce an automatic report presenting graphs (point 3) and generic text. Please note: a. The algorithm should be implemented in our system in collaboration with our team. b. Signing NDA is essential. c. All the files and algorithms will be submitted to us and will be our property once we pay for the job. Illustration image: Algorithm Testing method: You should check video results of these three scenarios: • not smile —> smile • not smile —> smile in the left side only. • not smile —> smile in the right side only. Please note, the asymmetry calculation result has to be correct according to scenario expectations.
Skills: Computer vision Image Processing
Fixed-Price - Intermediate ($$) - Est. Budget: $1,500 - Posted
This project is about achieving a 10x performance improvement on our target detection code when running on an Arm A9 1GHz processor. We've designed a visual target (see attached), and written code to find the 4 corners of the outer square using the open source library OpenCV. This code runs really slowly on our drone (3DR Solo), with a 1GHz Arm A9 chip from 2008. (The code runs on any OS though, we develop on OSX). This project is about finding a way to detect the target's 4 corners 10x faster on the drone. Background: Once our code finds the corners, it then uses the corners to do POSE detection, do determine the drone's 3d location and orientation relative to the target. I can share the Python code we use that detects the target (its mostly calls to OpenCV), its something like: 1. Make image grayscale 2. cv2.GaussianBlur(gray, (3, 3), 0) 3. edged = cv2.Canny(gray, 25, 100) 4. kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (7, 7)) 5. img_search = cv2.morphologyEx(edged, cv2.MORPH_CLOSE, kernel) 6. contours, hierarchies = cv2.findContours(img_search, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE, offset=offset) Then we loop through the contours and apply a few checks to find our target contours. Step #3 is often the slowest. Optimizations we've already implemented: - resize image smaller before looking for target - cropping image based on where we think the target is Requirements: 1. Code needs to run/compile on the 3DR Solo - If coding in C, need to provide assistance to get it compiled for solo - http://dev.3dr.com/advanced-linux.html 2. Ideally no changes to the target, but, we're open to suggestions if they will help perf 3. Performance improvements need to work in both positive and negative cases 3. No reduction in accuracy of detection Optimization ideas: 1. Recompile openCV more aggressively for the A9? (wild guess, might not help) 2. Write replacements for the methods we call in OpenCV (our python code doesn't change much) 3. Step back, consider alternate approach for detection, and write faster algorithm
Skills: Computer vision ARM C OpenCV
Fixed-Price - Intermediate ($$) - Est. Budget: $600 - Posted
We have the requirements of developing some scientific papers in C++ by using openCV and boost (if needed but better to avoid). The papers are based on the concepts of Image Processing and Pattern Recognition techniques. Persons having good background knowledge in these domains would be capable to understand these projects/papers and to implement them in C++. Some of the examples of such papers are mentioned below: 1) A Two-Step Dewarping of Camera Document Images: N. Stamatopoulos, B. Gatos, I. Pratikakis and S. J. Perantonis 2) Flattening Curved Documents in Images: Jian Liang, Daniel DeMenthon, David Doermann 3) A Model-based Book Dewarping Method Using Text Line Detection: Bin Fu, Minghui Wu, Rongfeng Li, Wenxin Li, Zhuoqun Xu, Chunxu Yang 4)Automatic Borders Detection of Camera Document Images: N. Stamatopoulos, B. Gatos, A. Kesidis 5) Page Frame Detection for Double Page Document Images: N. Stamatopoulos, B. Gatos, T. Georgiou Please note that, our experts would help you to understand the papers (if you face problems in understanding). Code for some of the basic functions would be provided also. In the case of some papers, we would ask you to implement only one part of the algorithm/paper. Please keep in mind that if the desired implementations are not achieved or attained then no money would be provided to the developer. I would like to request you to look into the some of the papers (which are freely available) before responding to this call. Please don’t hesitate to mention if you are not able to implement certain part of the paper but you could implement some other part of the algorithm. If you prefer, then our experts could explain you the algorithms and then you need to develop them by respecting our coding convention. But, if would preferable if you could understand them by yourself.
Skills: Computer vision Image Processing Mathematics Pattern recognition
Fixed Price Budget - Intermediate ($$) - $100 to $120 - Posted
Looking for experienced ML/CV person to create an algorithm in Python for the this purpose: I want to implement the feature in my Django app. The feature will based on this: User uploads a selfie picture and I want to get the tags from the selfie on whether a person has dark or light skin and whether it has dark or light hair. I will provide data in terms of selfies. If I'm satisfied with work I will also offer continues collaboration. Thanks
Skills: Computer vision Machine learning Python
Fixed-Price - Intermediate ($$) - Est. Budget: $1,500 - Posted
This project is to construct an end-to-end pipeline with Renderscript, Allocations, and Java (as necessary), in order to provide real-time (30fps+) hardware-independent face detection and tracking on Android devices. This will involve writing RenderScript code to extract relevant visual features for Haar Cascades or other methodologies at multiple resolutions, then clustering/classifying image segments as representing facial regions or not. Further adaptations of this pipeline may be discussed, based on the same underlying features. I am able to provide greyscale facial training data in the order of 10k's images, as well as guidance on parameterization and engineering considerations. Candidates should have demonstrated experience with computer vision, RenderScript projects (whether together or separately), clear communication, and clean coding/testing practices. This will be an excellent portfolio project, as well as leading to continued engagement on similar and more sophisticated pipelines in future, depending on performance.
Skills: Computer vision Java