* Director of computer vision and machine learning at "Gauss Surgical" [Feb 12--Feb15] to build the core technical algorithms and software architect to design a mobile-based computer vision application to estimate hemoglobin mass and concentration measurements in surgery rooms. [7 patents] [FDA approved for two product] * Algorithm manager and software architect at 3VR Inc (Dec 13-Nov 14) to build and support video analytic for the retail stores and security applications e.g. face recognition, tracking, queue analysis. [1 patent] * Computer vision and machine learning scientist lead at Set Media Inc. (Aug09-July12). The Designed and developed the core technology to label and filter webpages (text/video/image) from scratch. The labeling system was used to put right ad-placement based on the webpage content. My innovations (through the company) provided the full-automation of content-based video filtering, labeling and training using cloud computers and crowd-source [3 patents]. The company is acquired on Feb 6, 2014 by Conversant inc. * Senior computer vision scientist at Novafora Inc. (Mar 08-Aug09) to develop algorithms for video indexing and search, interactive object segmentation, tracking, and annotation. [1 patent]. We built the first-ever video shazam technology even before video surf. Unfortunately, the company got insolvent. At Epson R&D Lab [Sept 04-Mar08] in the Silicon Valley, I dedicated my time to camera calibration and image registration in visual inspection systems, and on printed text watermarking, project-based calibration and document unwarping. [15 patents] I have generated 27 US patents during the last 10 years of work in industry and 15 are granted Specialties:Video/image content-based filtering, Interactive video analytics, feature extraction and description , Large-scale internet-based vision, Video/image finger-printing, computer vision for medical applications, document camera analysis, Object detection and recognition, Face detection and recognition, Image segmentation, machine learning/large data analytics Python, C/C++, PyQT, Opencv, Matlab, linux, script, amazon web services, boto, mechanical turk, automatic launch machine

Senior software engineer @ video effect team at youtube From April 2015 to Present (7 months) San BrunoConsultant: Director of Computer Vision and Machine Learning team [FDA approved] [funded series A] @ GAUSS is developing a mobile vision platform for the OR. We develop beautiful apps for iOS/Glass backed by sophisticated algorithms and a robust, HIPAA-compliant technical stack to enable real-time monitoring during surgery. Our first product, THE TRITON SYSTEM, leverages computer vision and machine learning algorithms to measure surgical blood loss - simply using an iPad. Built up the system from scratch. FDA approved the two product related to blood loss measurements. http://www.streetinsider.com/Press+Releases/Gauss+Surgical+Announces+FDA+Approval+of+First+Mobile+Platform+for+Real-Time+Estimation+of+Surgical+Blood+Loss/9505775.html http://www.erietvnews.com/story/28528041/gauss-surgical-announces-fda-510k-clearance-of-triton-canister-app-for-accurate-surgical-blood-loss-monitoring Read more: http://www.crunchbase.com/company/gauss-surgical http://www.gausssurgical.com From February 2012 to February 2015 (3 years 1 month) Los Altos, CAAnalytics Research Manager @ 3VR products include hybrid network video recorders, video management and investigation software, comprehensive dashboards and reports and a robust suite of video analytics and APIs. Build up a framework for prototype to product plugin from python-->C++-->Clr-->C# and DB people Build up a diagnostic framework for enterprise analytic plugins Fully automatic and scale-able log parsing, report and anomaly detector for retail stores Build or improve people counting, queue, face recognition, tracking and motion direction analysis Mentorship and management of algorithm team From December 2013 to November 2014 (1 year) San FranciscoConsultant: Computer Vision and Machine learning software architect @ Viblio is founded to make managing videos as easy as watching them. https://viblio.com/ The algorithms are based on: image/video content-based categorization, low-level, mid-level and high-level features and descriptors, machine learning over the EC2 instances. From June 2013 to June 2014 (1 year 1 month) Palo Alto, CAComputer vision and machine learning innovator and executioner [acquired Feb 2014] @ SET Media is a video technology company that connects brand advertisers with their audiences through high quality, targeted, and brand safe campaigns at scale. By leveraging computer vision with proprietary object, facial, and motion detection, SET’s discovery and targeting platform enables advertisers to run ads on only the most relevant content to their brand. Exclusive to SET is the ability to provide campaign reporting at the level of inventory, showing customers each video they’ve sponsored while ensuring complete brand safety and performance optimization. SET is the only company to offer this level of clarity and brand control over digital video advertising. I built up the backend algorithm for computer vision and machine learning of video contents from scratch. [from angel.co] Westlake Village-based Conversant--the online advertising company which until a few days ago was known as ValueClick--said it has acquired Set Media on feb 6, 2014, a digital video technology advertising company. http://finance.yahoo.com/news/conversant-acquires-digital-video-technology-210500631.html See more at: http://www.set.tv/technology From July 2009 to July 2012 (3 years 1 month) San Francisco, CASenior Member of Technical Staff @ Interactive video analytics, video fingerprinting, indexing, image segmentation, video annotation, object tracking, visual similarity and benchmark design From March 2008 to July 2009 (1 year 5 months) Senior Member of Tech Staff @ visual inspection, document images watermarking, camera calibration, object detection, scanned document images rectification From September 2004 to February 2008 (3 years 6 months) Graduate Research Assistant @ video-based interface to access textual information access for the visually impaired backed by computer vision algorithms From 1999 to 2004 (5 years)

Ph.d., Electrical Eng./Computer Vision @ University of Maryland College Park From 1999 to 2004 Masters, EE-Control @ Sharif University of Technology From 1994 to 1997 Ali Zandifar is skilled in: Computer Vision, Video Analytics, OpenCV, Object Recognition, Image Segmentation, Fingerprinting, Watermarking, Video Analysis, Internet Video, Research Experience, Face Recognition, Optimization Algorithms, Machine Learning, Crowdsourcing, Python, C++, Matlab, HTML/XML, Amazon Web Services, Medical Imaging, Video Search, Image Search, Data Scientist, Algorithms, Research, Machine Vision, image segmentatio, Visual recognition, applied estimation, Entrepreneurship, Amazon Web Services..., Linux, C, Git, Pattern Recognition, Signal Processing, Digital Signal..., Programming, Artificial Intelligence, Cloud Computing, Simulations, Data Mining, Computer Science, Software Engineering