期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2019
卷号：7
期号：3
页码：1985-1992
DOI：10.15680/IJIRCCE.2019. 0703074
出版社：S&S Publications
摘要：Depending on the type of the date fruit, dates have many features that should help in recognizing and
classifying a date. The main features of the date fruit are the color, texture and the shape of date fruit. This article thus
analyzes image based date fruit classification and recognition. In this regards, this paper has two contributions, firstly,
as there is no standard dataset available, a dataset of 9 date’s classes is constructed. This dataset presents an interesting
challenge for computer vision algorithms. Secondly, Gabor features and Color Layout features are used. These features
are then fused to increase the classification performance. The proposed approach takes into account different types of
fruits. The main goal is to come up with a method for classifying these different types of fruits accurately and
efficiently. Images are preprocessed in order to separate the fruit in the foreground from the background. Texture
features from Gray-level Co-occurrence Matrix (GLCM) and statistical color features are extracted from the segmented
image. Two types of features are combined in a single feature descriptor. A Support Vector Machine (SVM)
classification model is trained using these feature descriptors extracted from the training dataset. Once trained, the
model can be used to predict the category for an unlabeled image from the validation set. The proposed approach also
works best for embedded systems and single board computers as it realizes the trade-offs of these devices.
