Improved Vertex Chain Code Based Mapping Algorithm for Curve Length Estimation

Abstract

Problem statement: Image representation has always been an important and interesting topic in image processing and pattern recognition. However, curve tracing and its relative operations are the main bottleneck. Approach: This research presents the mapping algorithm that covers one of the vertex chain code cells, the rectangular-VCC cell. The mapping algorithm consists of a cell-representation algorithm that represents a thinned binary image in rectangular cells, a transcribing algorithm that transcribes the cells into vertex chain code and a validation algorithm that visualizes vertex chain code into rectangular cells. Results:The algorithms have been tested and validated by using three thinned binary images: L-block, hexagon and pentagon. Conclusion/Recommendations: The results show that this algorithm is capable of visualizing and transcribing them into vertex chain code.

Implications of E-learning systems and self-efficiency on students outcomes: a model approach

“…They include human factors and design factors. Human factors include personality Characteristics [9,10], learning styles [11][12][13][14], and instructor's attributes [15]). Design factors include a wide range of constructs that affect effectiveness of e-learning systems such as technology [5,[16][17][18], learner control, learning model [19,20], course contents and structure [21][22][23], and interaction [23][24][25][26].…”

Light microscopic iris classification using ensemble multi‐class support vector machine

“…Features extraction is an important stage of image classification; selecting the best feature descriptor leads to classification accuracy (Haron, Rehman, Wulandhari, & Saba, 2011; Harouni et al, 2014; Sadad, Munir, Saba, & Hussain, 2018) and sometimes only few features perform best (Mughal, Muhammad, et al, 2018; Mughal, Sharif, et al, 2018; Mughal, Muhammad, Sharif, Saba, & Rehman, 2017; Neamah, Mohamad, Saba, & Rehman, 2014). Several features descriptors, such as LBP, HOG, SURF, and SIFT, ORB, and so forth.…”

Crowd region detection in outdoor scenes using color spaces

“…A dense group has an extremely specific angle, made of an interwoven of hues, that is the main inspiration of this work to consider this feature to detect crowd in a scenario. While color features have been used for object detection, but the need to visualize crowd as a cluster of the high variance color textured region needs to be studied and explored [49][50][51]. Fig.…”