Paper Title
Grain Size Distribution using Photographic Analysis

Abstract
This paper describes the development, validation, and application of a new algorithm for the detection of soil particles in digital soil images intelligently and accurately. The method introduced offers several improvements over existing algorithms by overcoming many limitations concerning the proper filling of the detected grains in images. Currently, digital image processing plays an important role in many applications by providing a fast and accurate method to extract data from images or videos and process them for a specific purpose. A number of different soil samples were prepared in the lab for validation process. The paper verifies the degree of accuracy of using this new algorithm by comparing the results obtained from image analysis to that of using mechanical sieving in the lab. Furthermore, this research proposed using a newly developed algorithm for edge detection called holistically nested edge detection which gives much better results to extract the border of the grains in the images when compared to previous algorithms. Rock particles were analyzed to estimate their size in order to encourage using image analysis methods for large scale grains. Keywords - Grain size, digital image processing, soil samples, image analysis