Peri Akiva's Projects
Bag of Words implementation using SVM and SIFT
Using OpenCV
This program built on the VGG practical by Oxford. The data sets are changed as well as the prediction methods for an easier understanding.
A HackRU winner project. a user-friendly web-interface robo-adviser for novice traders that want to focus on day and short term trading. Project is using candlestick and moving average algorithms to predict suggestions (buy, sell, hold) for users. Product is also notifying users via SMS when the suggestion is changed; users are able to subscribeโฆ
Matlab implementation for a digital equalizer.
Matlab implementation to face detection using eigenmathods
Using pre-trained CNN model for facial recognition.
PyTorch implementation of the paper "Finding Berries: Segmentation and Counting of Cranberries using Point Supervision and Shape Priors". Peri Akiva, Kristin Dana, Peter Oudemans, Michael Mars. CVPRW2020.
generating random dots on an image and the option to save it
Python solutions to google dev guide solutions
cropping and stitching images
Rutgers ECE Capstone Project - Spring 2017
PyTorch code for "Locating objects without bounding boxes" - Loss function and trained models
Official implementation of Self-Supervised Material and Texture Representation Learning for Remote Sensing Tasks
OpenMMLab Pose Estimation Toolbox and Benchmark.
Cuda implemendation to cubing every variable in an integer array
Parallel implementation for quicksort using pthreads
Geometry Processing Library for Python
A HackRU winner project. a user-friendly web-interface robo-adviser for novice traders that want to focus on day and short term trading. Project is using candlestick and moving average algorithms to predict suggestions (buy, sell, hold) for users. Product is also notifying users via SMS when the suggestion is changed; users are able to subscribe to multiple stocks in order to get real time suggestions on those chosen stocks. The algorithm is using real time data and provides real time visualization flowing chart for chosen stocks. Used Python, Flask, MongoDB, Node.js.