Advanced Stroke Labeling Technique Based on Directions Features for Arabic Character Segmentation

Underwater Fish Detection and Counting Using Mask Regional Convolutional Neural Network

“…Hence, computer vision has become vital in place of many manual inspection systems. They were beginning from hyperspectral images until nano images such as a satellite in a study by Anahita et al [1], cell detection by Yazan et al [2], optical character recognition by Tarik et al [3], vehicle counting by Abbas et al [4], and rice diseases diagnosis by Abdullah et al [5]. Furthermore, machine learning enhancement that can reverse feature engineering, namely deep learning, has attracted many researchers to explore the computer vision research area in place of handcrafted feature engineering.…”

“…Calculating geometrical features is a suitable manual inspection method in the industry or agriculture sector. Many researchers imitate how human vision encapsulates the optical property of the continuous [2,3,5] or discontinuous [4,6] pattern or shape. Usually, continuous property involves the characteristic and structured properties of the line and circularity.…”

“…Previous authors also use a statistical approach [2][3][4][5] to indicate discontinuous geometrical properties. Yazan et al [2] propose an iterative randomized irregular circular algorithm (IRIC) that detects irregular and overlapping cells by initiating dynamic initialization to determine the best circle candidate with a lower probability of incorrectly detecting circles.…”