Computer Vision Jobs

24 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 Budget - Expert ($$$) - $50 to $100 - Posted
I have some X-ray images from different angles of a aluminium model. I want to get a cross-sectional CT images. there is one opensource toolbox named as ASTRA Toolbox. I want some expat who can use the toolbox and do the job for me
Skills: Computer vision C++ Image Processing MATLAB
Hourly - Expert ($$$) - Est. Time: More than 6 months, 10-30 hrs/week - Posted
We are looking for a senior engineer versed in computer vision, machine learning, and image analysis to join our team. You should have Strong math skills Machine learning, particularly in the context of computer vision Good intuition for real-world systems; Good proposal writer and presentation skills Can develop working prototype code, preferably in C++ Qualifications MS degree in Robotics, Computer Vision, or Computer Science; PhD preferred. Five or more years of work experience in developing advanced computer vision / machine learning / artificial intelligence applications.
  • Number of freelancers needed: 3
Skills: Computer vision Artificial Intelligence Machine learning
Hourly - Intermediate ($$) - Est. Time: 1 to 3 months, Less than 10 hrs/week - Posted
I am currently a student in University of Chicago. I am working on a fashion project and would like to build a tool where from a click on a page, it opens the camera of the phone or laptop, person takes a photo of his full body and inputs his height. Then the tool would use the height (which is the scale of the image) + the body picture to take a few measurements from his body using image processing, then compare them to a size chart, and recommend the size for that person.
Skills: Computer vision Image Processing
Fixed-Price - Expert ($$$) - Est. Budget: $400 - Posted
Hello Dear Sir or Madam, I have attached a paper for object segmentation. The authors of this paper have published their MATLAB code in the following website: http://bryanrussell.org/projects/mult_seg_discovery/index.html * What’s needed? 1- Using the published MATLAB code, I need a professional freelancer to perfectly segment faces from a database that just contains images of faces and then crop and resize them as shown in the attached document. I am going to send the database to you later after discussing the project with you. 2- Also, I need you to prepare a pdf document (written by Latex) to explain the algorithm shown in the paper in details step by step (i.e. Step 1, …, Step 2, …, etc.) in parallel with the MATLAB code. That means when I read the pdf document, I must know everything in the paper step by step in parallel with the MATLAB code without reading the paper itself. * Who’s needed? You must be professional in MATLAB, image processing, and computer vision. Also, you have to show me some samples of your previous work. When you be awarded the project, the previous requirements must 100% be met; otherwise, I will not accept the project at all. Therefore, if you think that 1% you will not meet the previously mentioned requirements then simply do not bid on the project.
Skills: Computer vision Algorithms Artificial Intelligence Computer Engineering
Fixed-Price - Expert ($$$) - Est. Budget: $3,000 - Posted
We are looking for someone to write a C++ library that can do automatic tennis ball detection when a camera is positioned on the net post of a tennis court looking into the service box. We are building an iPhone application that will allow users to approximate the speed of a ball after they have served it, along with some other features. This initial project requirements will be: - Write a library that uses OpenCV to detect a tennis ball in frames of a video, and then estimate the speed of ball depending on how far the ball has traveled in two frames of video. - Library should also analyze and record where ball bounces in service box. We will be writing a wrapper for this in Objective-C and use it in an iPhone application, but that is outside of the scope of this contract (you will not be responsible for that). Please feel free to reach out to me if you have any questions. Work will start in 1-2 weeks. Project plan will be given to qualified candidates after Skype interview.
Skills: Computer vision C++ OpenCV
Fixed Price Budget - Expert ($$$) - $100 to $1,000 - Posted
Need skilled software developer to create algorithms to detect and characterize valleys. Input data will be (a) raster image(s) of the valley as well as a point cloud encompassing the valley to be characterized. Preferred algorithms will be in c/c++ and will run on a Linux based system. Sample data to be processed will be provided to successful candidates. Desired algorithm will be supplied the input image(s) and point cloud and will determine and return minimum / maximum values for depth and width as well as average depth and width. Key Skills: - Machine Vision - Point Cloud Manipulation - C/C++ - Linux Please include applicable experience in your application. Work will be phased and initial budget is for specific work item to be discussed with successful applicant(s). All work created as a result of this assignment will be the sole property of ICE, inc. Applicants must be willing to sign a Non-Disclosure Agreement.
  • Number of freelancers needed: 2
Skills: Computer vision Algorithm Development C++
Fixed-Price - Intermediate ($$) - Est. Budget: $198 - Posted
Good day! I am looking for a computer/software engineer to write a technical report/research proposal of how a micro video-camera can track flying mosquitoe(s) with image recognition software. Deadline: 1 week as I need this soon. I need a fair number of revisions. Please share your quote. Technical report/research proposal must be professionally written and must include at least the below but I can ask for reasonable additions: • Video-camera must be able to spot and track a small and fast flying mosquito • Video-camera must be very small, in fact, as small as possible; how small can such a video-camera be? • Please provide full technical specifications of such a video-camera • Please provide url link as to where 1 can purchase such a micro video-camera • IMPORTANT: This micro video-camera is synced with image recognition software and is attached to a pivot which can rotate; when it detects a mosquito it MUST direct the pivot to move the camera such that it maintains line of sight with the mosquito. Example if mosquito flies left, camera must turn left to maintain line of sight with the mosquito. • Please give concise literature review of how such image recognition software work in general • Is such image recognition software already available in the market? If yes, please give url link to where it can be bought. • IMPORTANT: If not commercially available, this part may be the most difficult. Of course I don't expect the programming code for such an image recognition software; but please describe in technical detail the R&D of how such an image recognition software can be developed. • Please list all references clearly. • What is the range of such a video-camera + image recognition software? 30cm? • How much is R&D expected to cost? • What is the limitation of such a system? • Please include all other useful information. Please note I can ask for more reasonable information. Thanks very much! Regards, Clement
Skills: Computer vision Circuit Design CodeWarrior Computer Engineering
Hourly - Expert ($$$) - Est. Time: Less than 1 week, 30+ hrs/week - Posted
We need a small addition to the dlib c++ library. The dlib library provides a facial key point detection algorithm with the following API: face_points = find_face_keypoints(image, face_rectangle) Where'face_rectangle' is a region of the image where a face is located, 'face_points' here refers to facial keypoints detected by the algorithm. We need this new API: face_points = find_face_keypoints_with_previous(image, previous_face_points) Where 'previous_detection' is simply the result from a previous call to 'find_face_keypoints' This new addition will allow for better initialization of the key point detection. Note: this does not require tracking points over frames, it is simply another method of initializing the key point localization. The function 'find_face_keypoints_with_previous' should be stateless and so will not have access to the previous frame. The work will require digging in to dlib's shape_predictor and it's data structures, and writing a one or more utility functions to transform the data. ( e.g. estimating affine transforms -- though dlib provides the heavy lifting related to things like that ) You should have a solid grasp of c++ and data structures. Your result should include a small patch to the dlib file 'shape_predictor.h', The relevant function to look at is: ..dlib/image_processing/shape_predictor.h line 323 and an example program in c++ demonstrating that the new function works, including: - show that you can call your new function with a face image + a previous detection from a slightly translated image and you get the correct facial keypoint predictions. -- however you want to visualize the results is OK.. provided it's reproducible and easy to prove it's working. - instructions for compiling If you have read this far, congratulations.. please indicate you have done so by including 'dlib' in somewhere in your reply so we can filter out the robots. If you know what you're doing, this job could be completed in a matter of hours. P.S. If we like working together, we have many other opportunities where computer vision expertise is required. Thanks for your time!
Skills: Computer vision C++ Mathematics OpenCV
Hourly - Expert ($$$) - Est. Time: Less than 1 week, Less than 10 hrs/week - Posted
I have a list of URLs which contain brand logos, I need a box around these logos and i need to know the coordinates of that box. I need to know the x,y location of the top left corner as well as the width and length. I can have humans draw the box. So perhaps all you need to identify is the box and not the logo. I have the URLs, I need to add the boxes and i need to know the box coordinates. This is an extremely urgent task, and I need it today. Here is an example of the URLs I have. http://tinyurl.com/jcgjpf3 http://tinyurl.com/hj6x9qx http://tinyurl.com/h85k27z Each of which shows the PayPal logo in a natural setting. I dont have the box around them yet.
Skills: Computer vision
Hourly - Intermediate ($$) - Est. Time: 3 to 6 months, Less than 10 hrs/week - Posted
Title: Computer Vision, Video Analysis & Algorithm IntelliVision is looking for Computer Vision, Algorithm and Video Analysis experts. Multiple projects are available and positions are open for both Full-time and part-time professionals. Contracts can be short or long term, based on mutual agreement. Required Computer Vision / Algorithm skills: 1: Prior Computer Vision, pattern recognition and algorithm experience (min 5 yrs) 2: Prior expertise in R&D and new algorithm creation or implementation based on technical papers 3: Good knowledge in dealing with videos, analytics, pattern recognition and mathematical concepts and algorithms (min 10 yrs) 4: Proficient in one or some of these tools: Open CV, Mathlab etc. (min 5 yrs) 5: Machine Learning, DNN, CNN - will be a plus About IntelliVision IntelliVision is leading technology provider of intelligent camera, imaging and video solutions to multiple markets. jobs at Intelli-Vision.com www.Intelli-Vision.com
  • Number of freelancers needed: 3
Skills: Computer vision Algorithms Image Processing Mathematics