1. 1. Graphics extraction from heterogeneous online documents with hierarchical random fields – 2015 - Published: Friday, 25 December 2015 - Graphical objects are important elements of freely handwritten notes but their segmentation from the document is challenging due to their irregular properties. This project introduces an original solution for automatically segmenting diagrams and drawings from unstructured online documents (Basic logic of this project got from this project approach.)
   2. Context-Aware Patch-Based Image In-painting Using Markov Random Field Modeling – 2015 - Published: Friday, 25 December 2015 - where textural descriptors are used to guide and accelerate the hunt for wellmatching (candidate) patches. A completely unique highdown splitting procedure divides the image into variable size blocks consistent with their context, constraining thereby the rummage around for candidate patches to nonlocal image regions with matching context. (This part of logic used to split images and its text context)
   3. Semi supervised Biased Maximum Margin Analysis for Interactive Image Retrieval – 2012 - Published: Thursday, 27 September 2012. - With many potential practical applications, content-based image retrieval (CBIR) has attracted substantial attention during the past few years. A variety of relevance feedback (RF) schemes have been developed as a powerful tool to bridge the semantic gap between low-level visual features and high level semantic concepts, and thus to improve the performance of CBIR systems. (Using this approach we implement content based 8 images extraction logic using xml and xslt/xsl)
   4. Image Super resolution Using Support Vector Regression - Published: Monday, 25 June 2012 - Support vector machine (SVM) is a statistical learning algorithm that is capable of estimating high-dimensional functions. Recently, support vector regression (SVR) - the use of SVM for regression - has been used to generate superresolution images. In this paper, we propose to apply the SVR algorithm on edge pixels only so as to reduce the emboss effect that would appear in the edge region of an enlarged image if the SVR is applied on the entire input image. Image vector processing principle and logic used by this approach.