Discover @nehay06 Open Source projects

Neha Yadav (@nehay06)

nehay06

Stars
42
Global Rank 385,755 (Top 14 %)
Followers 5
Registered about 8 years ago
Most used languages

MATLAB
60.0 %

Jupyter Notebook
20.0 %

Python
20.0 %

Computer-Vision-Shape-From-Shading-Photometric-stereo

Photometric stereo The input to the algorithm is a set of photographs taken in known lighting directions and the output of the algorithm is the albedo (paint), normal direction, and the height map.

Computer-Vision-demosaicingImage

in digital cameras the red, blue, and green sensors are interlaced in the Bayer pattern (Figure 2). The missing values are interpolated to obtain a full color image

CrossDomainImageMatching

Images of same objects across different visual domains like sketches, paintings, photographs in varied environment, tend to show large difference at raw pixel level.This makes it difficult to match such images. We propose a simple and efficient method to compute cross domain image similarity by utilizing standard object detection framework to find relative importance of features. These weighted features are then used to find image matches, based on visual and contextual similarity. For robust experimentation analysis, we test our approach on UFU-DDD[6], PASCALVOC[ 18], INRIA Holidays[19], Random Flickr images[20] and Sketchy datasets[21].

Computer-Vision-Image-WhiteBalance

White Balance is based on \gray world" assumption that states the average color of the image under white light is gray

QuoraQuestionPairs

Predicting whether two sentences are a paraphrase of one another is an active re- search problem with many real life ap- plications. One such application is min- imizing duplicate questions and answers on question answering websites such as Quora or Yahoo! Answers. We used the Quora Question pairs dataset (Iyer et al., 2017) which consists of question pairs tagged as duplicate and not dupli- cate. Among the methods tried, the best accuracy achieved was 82%.

Jupyter Notebook