Efficient texture image retrieval of improved completed robust local binary pattern

Abstract

Improved Completed Robust Local Binary Pattern is one of the robust texture extraction for image retrieval that rotation invariant (ICRLBP). ICRLBP has proven that can increase the precision, recall, and computation time from its previous work by 21.14%, 20.03%, and 56 times, respectively, on four different texture image dataset. ICRLBP, however, has a lot of feature, thus require more time during recognition process. Moreover, it leads to high time consuming and curse of dimensionality. To overcome those issues, in this paper, we try to reduce insignificant or unnecessary ICRLBP attributes and examine the effect of reducing number of attributes on precision and recall of the retrieving images. The methods we used to reduce the ICRLBP attributes are Correlation-based Feature Selection (CFS) and Pearson's-basedCorrelation.The experiment results show that those feature selections not only can reduce number of attributes but also can improve precision, recall, and computation time. For S_M_C feature (sign, magnitude, and center features of ICRLBP are ploted on histogram jointly), CFS can reduce up to 95% number of attributes and improve precision, recall, computation time up to 7.5%, 7.1%, 11.42 times, respectively. For M_C feature (magnitude and center features of ICRLBP are ploted on histogram jointly), CFS can reduce up to 4.2% number of attributes and improve precision, recall, computation time up to 4.2%, 4%, 1.1 times, respectively. It indicated that Correlation-based Feature Selection (CFS) and Pearson's-basedCorrelation can reduce the ICRLBP attributes effectively.

Pengaruh Ciri Tekstur Pada Metode Klasifikasi LVQ Untuk Hasil Akurasi Identifikasi Citra Batik Tradisional Solo

“…Demikian juga dengan Batik tradisional Surakarta. Ciri yang digunakan untuk menjadi pembeda dengan ciri batik dari wilayah lain antara lain ciri bentuk [1] [2] [3][4] [5], ciri tekstur [6] [7] [8][9] [10], dan juga ciri warna [11] [12]. Dari berbagai ciri yang digunakan untuk identifikasi batik daerah satu dengan yang lain ada yang memiliki kesamaan namun ada juga yang memiliki perbedaan.…”

CBIR of Batik Images using Micro Structure Descriptor on Android

“…An example of a batik image is shown in Figure 1. In general, there are two patterns of batik drawings, geometric and non-geometric patterns [12]. Dataset is available download at https://github.com/agusekominarno/batik.…”

“…This knowledge needs to be introduced to the general public through an easily accessible application. Several studies on batik have been proposed, such as the Content Based Image Retrieval (CBIR) technique for retrieving batik images using Color Difference Histogram (CDH) [8], enhanced micro-structure descriptor [9], Multi Texton Co-Occurrence Descriptor [10], Multi Structure Co-occurrence Descriptor [11], improved completed robust local binary pattern [12], Texture Fusion [13]. However, all those studies are build for desktop.…”

“…An example of feature texture is the use of texton proposed [24]. In practice, CBIR often incorporates several types of features in order to obtain satisfactory results, for example merging texture and color features or edge and color features [12]. One of the combined feature extraction methods that has been proven to provide satisfactory results for CBIR batik is the Micro-Structure Descriptor (MSD) [9].…”

Application System for Identification of Surakarta Traditional Batik Images (SABATARA)

“…The equation of size and image improvement needs to be done to get better results, the method used in image improvement is contrast stretching (I Made Dwi Putra Asana, 2017;Purba, 2017;Sianturi, 2015). The improved image results are grouped and measured, the adaptive thresholding method is used to measure and get the characteristics of its image (Sinaga, 2017;Kurniawardhani, 2017). To get more optimal results, it is necessary to localize the desired object so that only the desired results are obtained (Alibeigi, 2015;Ambarwati, 2016).…”