Freelancer logo How It Works Browse Jobs Log In Sign Up Post a Project Profile cover photoundefined
You're now following .
Error following user.
This user does not allow users to follow them.
You are already following this user.
Your membership plan only allows 0 follows. Upgrade here.
Successfully unfollowed user.
Error unfollowing user.
You have successfully recommended
Error recommending user.
Email successfully verified.
User Avatar
$30 USD / hour
Flag of TRINIDAD AND TOBAGO
san fernando, trinidad and tobago
$30 USD / hour
It's currently 6:31 AM here
Joined November 8, 2020
1 Recommendation

Milind K.

@MilindAI1976

annual-level-four.svgpreferred-freelancer-v2.svgverified.svg
0.0 (12 reviews)
6.0
6.0
$30 USD / hour
Flag of TRINIDAD AND TOBAGO
san fernando, trinidad and tobago
$30 USD / hour
100%
Jobs Completed
100%
On Budget
90%
On Time
18%
Repeat Hire Rate

AI/Computer vision/Embedding Software/Mobile App

A Deep learning/Computer vision/Embedding software developer. I'm graduated in Computer Science, and I have more than 10 years of experience in machine learning/computer vision product development plus acquired skills in embedding software integrated with AI techs. I love to think about myself as a perfectionist: in my opinion, at the base of a solid product, there must be concepts like scalability, security, maintainability, and a perfect UI/UX design, but all of them need to receive the right priority to make sure an MVP oriented development process could be followed. SERVICES SUPPORTS: I am an expert in Deep learning/computer vision-based products developments, an AI Marketing Strategy with python/JS, DAPP development, etc. GOLD GOLD services: - DL/ML-based Object detection/recognition/Classification(Tensorflor, Pytorch, Caffe...) - Sementic segmentation/Removing Background/Video Analysis skill(Detectron2, MMDetection, Yolact, ClippingMagic) - Image generation using GAN - DAPP/coin development, transaction automation(Solidity, Java Script, deep learning coin prediction and automation.) - 24/7 support(UTC -4). Let's begin the glorious journey of working with you.
Freelancer Python Developers Trinidad and Tobago

Contact Milind K. about your job

Log in to discuss any details over chat.

Portfolio Items

- FFmpeg, Video player, supports most of video format
- Video/audio track split/merge
- Add computer vision/AI tech to video player
- Video clipping/splitting/merge manually and automatically. 
- Cross platform desktop application. 
- Image processing/machine learning technique
QT Desktop application, Video Player integrated with AI/Imag
- FFmpeg, Video player, supports most of video format
- Video/audio track split/merge
- Add computer vision/AI tech to video player
- Video clipping/splitting/merge manually and automatically. 
- Cross platform desktop application. 
- Image processing/machine learning technique
QT Desktop application, Video Player integrated with AI/Imag
- FFmpeg, Video player, supports most of video format
- Video/audio track split/merge
- Add computer vision/AI tech to video player
- Video clipping/splitting/merge manually and automatically. 
- Cross platform desktop application. 
- Image processing/machine learning technique
QT Desktop application, Video Player integrated with AI/Imag
- FFmpeg, Video player, supports most of video format
- Video/audio track split/merge
- Add computer vision/AI tech to video player
- Video clipping/splitting/merge manually and automatically. 
- Cross platform desktop application. 
- Image processing/machine learning technique
QT Desktop application, Video Player integrated with AI/Imag
RAEL TIME VOICE CLONING GLOABLLY CONDITIONED WITH SPEARKER VERIFICATION EMBEDDING BECTOR
Multi-Speaker text2speech running on jetson-nano
GlowTTS voice embedding + HifiGan voice decoding
Customized Training on Librispeech + LibriTTS
Unified toolkit to test the voice clonning
REAL TIME VOICE CLONNING AND MULTISPEAKER TTS(TEXT TO SPEECH
RAEL TIME VOICE CLONING GLOABLLY CONDITIONED WITH SPEARKER VERIFICATION EMBEDDING BECTOR
Multi-Speaker text2speech running on jetson-nano
GlowTTS voice embedding + HifiGan voice decoding
Customized Training on Librispeech + LibriTTS
Unified toolkit to test the voice clonning
REAL TIME VOICE CLONNING AND MULTISPEAKER TTS(TEXT TO SPEECH
Pose estimation, Athletics Training Assistance
- Bounding box labelnig
- Keypoint lableing 
- Polygon/segmentation labeling
- support  coco format/cytespace foramt 
- compatable with other CNN model(Tensorflow, Pytorch, Onnx, Openvino)
- Convinent to use and extendable
- Pyqt5/Kivy application
- support GPU computing
Automatic Labeling via pretrained CNN model
- Bounding box labelnig
- Keypoint lableing 
- Polygon/segmentation labeling
- support  coco format/cytespace foramt 
- compatable with other CNN model(Tensorflow, Pytorch, Onnx, Openvino)
- Convinent to use and extendable
- Pyqt5/Kivy application
- support GPU computing
Automatic Labeling via pretrained CNN model
- Bounding box labelnig
- Keypoint lableing 
- Polygon/segmentation labeling
- support  coco format/cytespace foramt 
- compatable with other CNN model(Tensorflow, Pytorch, Onnx, Openvino)
- Convinent to use and extendable
- Pyqt5/Kivy application
- support GPU computing
Automatic Labeling via pretrained CNN model
- Jetson-Nano/Xavier reltime plate detection and recognition.
- TensorRT+Onnx+int8 Quantization for Realtime Processing
- Capture images of the license plate through a camera
- Optical Character Recognition (OCR) extracts the number of the vehicle from captured images
-  Decoded text is forwarded to the central control room for checking the license plate against vehicle database, to take appropriate actions
- Red Light Violation Detection(RLVP)
- Speed Violation Detection
ANPR,SVSpeed Detection), Red (RLVD)Light Violation Detection
- Jetson-Nano/Xavier reltime plate detection and recognition.
- TensorRT+Onnx+int8 Quantization for Realtime Processing
- Capture images of the license plate through a camera
- Optical Character Recognition (OCR) extracts the number of the vehicle from captured images
-  Decoded text is forwarded to the central control room for checking the license plate against vehicle database, to take appropriate actions
- Red Light Violation Detection(RLVP)
- Speed Violation Detection
ANPR,SVSpeed Detection), Red (RLVD)Light Violation Detection
- Jetson-Nano/Xavier reltime plate detection and recognition.
- TensorRT+Onnx+int8 Quantization for Realtime Processing
- Capture images of the license plate through a camera
- Optical Character Recognition (OCR) extracts the number of the vehicle from captured images
-  Decoded text is forwarded to the central control room for checking the license plate against vehicle database, to take appropriate actions
- Red Light Violation Detection(RLVP)
- Speed Violation Detection
ANPR,SVSpeed Detection), Red (RLVD)Light Violation Detection
- Jetson-Nano/Xavier reltime plate detection and recognition.
- TensorRT+Onnx+int8 Quantization for Realtime Processing
- Capture images of the license plate through a camera
- Optical Character Recognition (OCR) extracts the number of the vehicle from captured images
-  Decoded text is forwarded to the central control room for checking the license plate against vehicle database, to take appropriate actions
- Red Light Violation Detection(RLVP)
- Speed Violation Detection
ANPR,SVSpeed Detection), Red (RLVD)Light Violation Detection
- Jetson-Nano/Xavier reltime plate detection and recognition.
- TensorRT+Onnx+int8 Quantization for Realtime Processing
- Capture images of the license plate through a camera
- Optical Character Recognition (OCR) extracts the number of the vehicle from captured images
-  Decoded text is forwarded to the central control room for checking the license plate against vehicle database, to take appropriate actions
- Red Light Violation Detection(RLVP)
- Speed Violation Detection
ANPR,SVSpeed Detection), Red (RLVD)Light Violation Detection
- Diverse Image Synthesis for Multiple Domains- StarGAN2
 A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties
- AnimeGAN: A Novel Lightweight GAN for Photo Animation
- Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation(minivision)
- Super resolution using Sharpen AI
GAN for style-transfer, fake face, face animation, starGAN
- Diverse Image Synthesis for Multiple Domains- StarGAN2
 A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties
- AnimeGAN: A Novel Lightweight GAN for Photo Animation
- Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation(minivision)
- Super resolution using Sharpen AI
GAN for style-transfer, fake face, face animation, starGAN
- Diverse Image Synthesis for Multiple Domains- StarGAN2
 A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties
- AnimeGAN: A Novel Lightweight GAN for Photo Animation
- Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation(minivision)
- Super resolution using Sharpen AI
GAN for style-transfer, fake face, face animation, starGAN
- Diverse Image Synthesis for Multiple Domains- StarGAN2
 A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties
- AnimeGAN: A Novel Lightweight GAN for Photo Animation
- Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation(minivision)
- Super resolution using Sharpen AI
GAN for style-transfer, fake face, face animation, starGAN
- Diverse Image Synthesis for Multiple Domains- StarGAN2
 A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties
- AnimeGAN: A Novel Lightweight GAN for Photo Animation
- Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation(minivision)
- Super resolution using Sharpen AI
GAN for style-transfer, fake face, face animation, starGAN

Reviews

Changes saved
Showing 1 - 5 out of 12 reviews
Filter reviews by: 5.0
₹77,500.00 INR
Good knowledge and Sincere to work on problem
JavaScript Python Software Architecture Machine Learning (ML) C++ Programming
User Avatar
Flag of Deepak A. @ITgarage
2 months ago
5.0
$300.00 USD
100% as expected. wonderful overall experience!!!!
D
Flag of Wayne P. @dplaprrg
3 months ago
5.0
$1,200.00 USD
Really good freelancer, would like to work with him again. My customer was not clear on what they wanted and Milind gave them what they asked for. But they could not agree on how to make it work better than their current solution. So we decided to just stop and pick it up later if they came back with any other ideas or thoughts.
T
Flag of Thomas V. @tomvarghese
4 months ago
5.0
$1,000.00 USD
He is a real boss of ASR and speech to text.
Machine Learning (ML) Artificial Intelligence Deep Learning
User Avatar
Flag of Aziz A. @paladmin
6 months ago
5.0
$1,500.00 USD
Delivered satisfactory work on time on a very good budget. Looking forward to working with him again.
Android App Developer OpenCV iOS Development React Native
D
Flag of Arthur N. @davidndossi2014
6 months ago

Experience

AI-based ALPR system developemnt

Republic Bank
Jan 2014 - Mar 2017 (3 years, 2 months)
ALPR(Automatic License Plate Recognition) system development ASR(Automatic Speech Recognition) system development

Education

Computer Science, Master of Degree

University of the West Indies, St. Augustine Campus, Trinidad and Tobago 2004 - 2008
(4 years)

Qualifications

PCTC

UWI, St. Augustine Campus
2009
We did a lot of maintenance and also continued workflow

Publications

Software in 2015

Michele Cimmino
The objective of this project is as follows: High quality software, design congenial and tailor-made care of the small details in both the algorithms and design, social software, clean, durable, maintainable, modern, eco-friendly.

ICT 2015 - Lisbon

Antonio Cimmino
The biggest event of the research in Europe, linked also to the Framework Programme H2020 2016-2017 of the European Commission, has registered around 7000 participants worldwide last week in Lisbon. The agenda of the event has been organised, as usual, with plenary, parallel thematic sessions and exhibition stands by projects currently in execution in H2020 and FP7.

Contact Milind K. about your job

Log in to discuss any details over chat.

Verifications

Preferred Freelancer
Identity Verified
Payment Verified
Phone Verified
Email Verified
Facebook Connected

Certifications

preferredfreelancer-1.png Preferred Freelancer Program SLA 1 97%

Top Skills

Python 7 C++ Programming 7 C Programming 4 Software Architecture 4 .NET 3

Browse Similar Freelancers

Python Developers in Trinidad and Tobago
Python Developers
C++ Programmers
C Programmers

Browse Similar Showcases

Python
C++ Programming
C Programming
Software Architecture
Previous User
Next User
Invite sent successfully!
Registered Users Total Jobs Posted
Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)
Copyright © 2022 Freelancer Technology Pty Limited (ACN 142 189 759)
There is no internet connection
Loading preview