Software Development Engineer

Software Development Engineer


  • Permanent
  • USA Work Ready
  • MS Visual Studio 2010

  • C

  • Image Processing

  • Java

  • openCV

  • C++

  • Matlab

  • Job Posted: Wednesday, March 12, 2014

  • Expires On: Saturday, August 09, 2014

  • Job Type: Permanent

  • Desired Salary: $60000/yr

  • Ideal Start Date: Thursday, March 13, 2014

  • Work Authorization: EAD

 I am very much interested in full time opportunities in the field of digital signal processing, computer vision and image processing algorithm development at your company. My study interests are in the field of signal and image processing, computer vision and computer graphics. I would like to mention both academic as well as work experience in these areas. To start with, the Digital image processing course at University of Southern California really gave me exposure to many relevant image processing algorithms and also gave the chance to implement them all using C programming language. I would like to mention here that we implemented basic and advanced edge detection algorithms including the Canny Edge Detector, Optical Character Recognition algorithm, Face morphing algorithm, Image Denoising algorithms including the recent Non Local Mean(NLM) Filtering. We also implemented Texture segmentation and classification algorithms, Morphological image processing algorithms using C. I am really fortunate enough to take the course of Computer Vision under Professor Gerard Medioni, who is one of the pioneers in the area of artificial intelligence and Computer Vision. I am currently working on two main projects in Computer Vision. The first project is the Panoramic Image Stitching which involves extracting the features using Scale Invariant Feature Transform (SIFT), feature matching using Nearest Neighbor Algorithm, Homography Estimation using RANSAC Algorithm to automatically align the images, Camera Pose Estimation to determine the overlap and relative positions of camera, and finally image warping onto cylindrical coordinates and image blending. In this project I make use of openCV as well as Sparse Bundle Adjustment (SBA) libraries. The second project is the 3-D Face Recognition which involves the initial alignment of 3-D canonical face point cloud with the gallery face point cloud using Iterative Close Point Algorithm, projection from 3-D face point to 2-D depth map, Segmentation of the 2-D depth map into different areas (eyes,nose,cheeks) and conversion to 2-D Feature vector, and identification using minimum Euclidean distance. The third major project in computer vision is the Planar Augmented Reality which involves the placement of a virtual object on a planar surface in the input video. The system involves extracting features of the image frames using SIFT, Homography computation using RANSAC Algorithm, Plane Estimation using the decomposition of the homography, Perspective-n-Point Camera Pose Estimation and finally rendering the images using estimated camera pose and plane estimate. My experience in Computer Graphics involved developing program using openGL libraries for generating Height Fields from terrain maps. Also I got chance to simulate camera movement along roller coaster track and to render the roller coaster track by fitting to a Catmull Rom Spline. Also another project in Computer Graphics using openGL involved building a Ray Tracer which handled Ray-(Sphere, Triangle) intersections, shadow rays and using the concept of Phong Shading.
My experience in audio signal processing includes the projects that I have worked on in Advanced DSP laboratory at University of Southern California. I have worked on adaptive noise cancellation project using TMS320C6713 DSK Digital Signal Processor using Normalized Least Mean Square algorithm. Also I have worked on mini projects such as audio ring modulator system and voice scrambler - descrambler system using TMS320C6713 DSP.
I would also like to highlight my work experience during my summer internship at Sigza Authentication Systems. I had the opportunity to design DSP algorithms for noise filtering, smoothing etc of accelerometer and gyroscope sensors in Android and iPhone mobile devices. Also I was involved in the implementation of Google Android’s open source implementation of sensor fusion in C++. Currently I am interning at Doheny Eye Institute as an Image Processing Research Engineer. I am working on a project to implement Image Montage(Retinal image stitching ) with graphical user interface. I am using Qt for GUI development along with Insight Toolkit library, Visualization Toolkit, openCV and openGL libraries. Also my programming skills include C, C++, Java, MSSQL, MATLAB, openGL. I strongly think I will be able to
contribute to your company with the above mentioned skills and experience and also gain a lot of new
experience at the same time.
Thanks and Regards,
Kiran Nandanan
  • Los Angeles, CA

  • San Francisco, CA

  • San Jose, CA