Computer Vision Jobs

NOTED: This project cannot be solved with OCR or letter segmentation. We are looking for an experienced developer that can build a customized captcha recognition system. We only need to solve one specific type of captcha, of which we have over 50,000 samples + solutions, stored as {solution}.jpg files. We also have another 20k dataset available, plus can generate more if needed. It might sound e...

a. COCO-Text (link) b. Kaggle Text detection (link) C. Common Coco (link) Take any of the following dataset 2. Choose a Neural Net for the problem Even I can send the model file just need to comment out the codes Will share details.

The user should be able to select an object on the frame and then the bounding box should keep tracking the particular object. Integration of OpenCV code into android app is must.

I have about 10k images here, I need people to help me draw people annotation manually. You can use some deep learning methods to pre process, but as far as I know, the result is not as perfect as manual result. So please do them manually. Please attach your annotation result of my attached image with your proposal. Proposal without annotation result will not be accepted. The deliverable would b...

Looking to create a business around a business model + POC concerning Computer Vision + Deep Learning in Wildlife Conservation. Need to have a discussion to further my understanding on the topic.

Need Computer Vision Expert Required I can provide help but you have do things by own.

We are a Malaysia-based company looking for a person or team with technical know-hows to build a document verification system that would integrate into our existing eKYC system / flow. With the input of an image, the module is expected to: 1. Verify that the image is indeed a government-issued identity card, driving license, or passport 2. Verify that the image is undoctored and genuine 3. Verify...

Machineearning technical person to extract exist model into web inference .(tensorflowjs, knowledge on architecture and inference on web browser.)

Milestone 1: Implement a customized CNN (reference material will be provided for guidance). To implement the customized CNN the video footage (8 videos of roughly 90 minutes long) are split into annotated-, validation-, and test-material, where the test-material is approximately 5 minutes of each 90 minutes video. The test-material is not shared to the seller. The buyer provides customized annotat...

We are a group of passionate engineers young in experience. We are working to solve an image composition problem using classic computer vision techniques. When we are overlaying 2 different images, we wanted the composition of 2 images to look natural. Problem is explained in the attached document. We wanted to apply the solution in real-time in a mobile app. So an expert advise required to choos...

I need computer vision expert who can perform complex [login to view URL] see the attached description

Help me jump start playing with coco/opencv. I need a little support getting a docker container going to play with an opencv/coco data set. I'd like to be able to visually see what's happening with matches e.g. bounding boxes. I've hit a few road blocks with getting a USB camera to be viewable with docker. Using ubuntu. I'd have you shadow what I'm doing and help out t...

Help me jump start playing with coco/opencv. I need a little support getting a docker container going to play with an opencv/coco data set. I'd like to be able to visually see what's happening with matches e.g. bounding boxes. I've hit a few road blocks with getting a USB camera to be viewable with docker. Using ubuntu. I'd have you shadow what I'm doing and help out t...

I need you to develop some computer vision algo for me. A camera is placed in a box and it should give me a flag , when an item is put in the box and when it is removed. We can talk more about it once we connect