Multi-class SVM Based Classification Approach for Tomato Ripeness

Abstract

Abstract. This article presents a content-based image classification system to monitor the ripeness process of tomato via investigating and classifying the different maturity/ripeness stages. The proposed approach consists of three phases; namely pre-processing, feature extraction, and classification phases. Since tomato surface color is the most important characteristic to observe ripeness, this system uses colored histogram for classifying ripeness stage. It implements Principal Components Analysis (PCA) along with Support Vector Machine (SVM) algorithms for feature extraction and classification of ripeness stages, respectively. The datasets used for experiments were constructed based on real sample images for tomato at different stages, which were collected from a farm at Minia city. Datasets of 175 images and 55 images were used as training and testing datasets, respectively. Training dataset is divided into 5 classes representing the different stages of tomato ripeness. Experimental results showed that the proposed classification approach has obtained ripeness

Automatic Fruit Image Recognition System Based on Shape and Color Features

“…SVM tries to find an optimal separating hyperplane which effectively separates between classes for solving the classification problem [19]. SVM aims to maximize the margin around a hyperplane that separates a positive class from a negative class [3,20,21,22]. Consider a training dataset with n samples (x 1 ,y 1 ), (x 2 , y 2 ), ...., (x n ,y n ).…”

“…The Support Vector Machine (SVM) classifier is a theoretically superior machine learning methodology that used for classification and regression of highdimensional datasets with great results [3,19,20,21,22]. SVM tries to find an optimal separating hyperplane which effectively separates between classes for solving the classification problem [19].…”

“…Several image processing methods are applied to analyze the agricultural images for monitoring crop ripeness [3], detecting crop diseases [4], and recognition fruit and vegetables [5]. Fruit recognition and classification systems can be used by many real life applications.…”

Fuzzy classification of pre-harvest tomatoes for ripeness estimation – An approach based on automatic rule learning using decision tree

“…Correlation was obtained between histogram of each color system and maturity. In the study, highest value were showed at G(36) and R (35) in RGB color space and at L(50) in L*a*b* color space. The experiments also revealed that with increase of maturity the level of a* increases and b* remains unchanged.…”

“…Authors Elhariri et al [35], investigated the multiclass support vector machine (SVM) approach and random forest (RF) for the estimation of tomato and bell pepper ripeness. A dataset of total 250 images for tomato and 175 images of bell-pepper has been collected from farm.…”