Detecting Direction of Pepper Stem by Using CUDA-Based Accelerated Hybrid Intuitionistic Fuzzy Edge Detection and ANN

Abstract

In recent years, computer vision systems have been used in almost every field of industry. In this study, image processing algorithm has been developed by using CUDA (GPU) which is 79 times faster than CPU. We had used this accelerated algorithm in destemming process of pepper. 65 percent of total national production of pepper is produced in our cities, Kahramanmaras and Gaziantep in Turkey. Firstly, hybrid intuitionistic fuzzy algorithm edge detection has been used for preprocessing of original image and Otsu method has been used for determining automatic threshold in this algorithm. Then the multilayer perceptron artificial neural network has been used for the classification of patterns in processed images. Result of ANN test for detection direction of pepper has shown high accuracy performance in CPU-based implementation and in GPU-based implementation.

GPU Accelerated Intuitionistic Fuzzy and Otsu Algorithms for Foreign Leaf Detection in Cotton

“…Also, speed ratio in all patterns are obtained between 186 times and 260 times. According to literature studies, the successful systems that hundreds of times accelerated with GPU were found (Bahri, 2017), (Faujdar, 2017), (Gunes, 2016). When 260 times speed is taken into consideration, it is seen that a very successful result is obtained according to the studies in the literature.…”

Evaluating the optimal working parameters of the color sensor TCS3200 in the fresh chili destemming system

“…This current system conveys chilies by a V-shaped trough with a pitch of 40 mm. In comparison to a previous computer vision system that could detect the stem's position of the chili to acquire the same arrangement function (Gunes & Badem, 2016), the color sensor could generate the same yield of 2.5 fruits per second at a running speed of 100 mm/s. However, this current method has the advantage that it does not require high-cost equipment as well as complex image processing algorithms.…”

“…The stem removal is a necessary stage in the processing process (Vo, 2016). Several studies have been done to automate this important step (Gunes & Badem, 2016;Herbon et al, 2010;Kodali, 2015).…”

PINFI – Ferramenta para classificação de imagens com redes neurais artificiais e lógica fuzzy

“…Assim sendo, para essa pesquisa foram utilizadas duas técnicas de IA: redes neurais artificiais (RNAs) e lógica fuzzy em conjunto com técnicas de processamento de imagens visando aplicação em automação e instrumentação em ambiente industrial ou agrícola. A combinação destas técnicas tem apresentado resultados promissores como visto em: Beluco et al (2015); Ros and Pasero (2013); Taghadomi-Saberi et al (2014); Geetha (2015); Bouzalmat et al (2011); Silva et al (2014); Soares and da Silva (2013); Yen et al (2019); Sabanci et al (2017); Gunes and Badem (2016); Tyryshkin and Belyaev (2016); Rao et al (2018).…”