Extraction of object image features with gradation contour

Abstract

Image retrieval using features has been used in previous studies including shape, color, texture, but these features are lagging. With the selection of high-level features with contours, this research is done with the hypothesis that images on objects can also be subjected to representations that are commonly used in natural images. Considering the above matters, we need to research the feature extraction of object images using gradation contour. From the results of the gradation contour test results, there is linearity between the results of accuracy with the large number of images tested. Therefore, it can be said that the influence of the number of images will affect the accuracy of classification. The use of contour gradation can be accepted and treated equally in all image types, so there is no more differentiation between image features. The complexity of the image does not affect the method of extracting features that are only used uniquely by an image. From the results of testing the polynomial coefficient savings data as a result of the gradation contour, the highest result is 81.40% with the highest number of categories and the number of images tested in the category is also higher.

Perbandingan Metode Random Forest Classifier dan SVM Pada Klasifikasi Kemampuan Level Beradaptasi Pembelajaran Jarak Jauh Siswa

“…Pada penelitian ini jenis penelitian yang dilakukan adalah jenis Eksperimen komparatif akan membandingkan dua objek yang berbeda, misalnya membandingkan dua algoritma yang berbeda dengan melihat hasil statistik masing-masing mana yang lebih baik [7]- [10]. Dimana Melibatkan penyelidikan hubungan kausal menggunakan tes yang dikontrol sendiri [11].…”

Network and layer experiment using convolutional neural network for content based image retrieval work

“…Deep learning is the latest, modern and robust technique [8], [11]- [13], while the progress and application of deep learning in other domains shows great potential [14]- [17]. The fact, that currently there are at least 40 studies that use deep learning to overcome various agricultural problems with excellent results [18], encourage the writer to prepare this research [19], [20].…”