Ekstraksi Fitur Tekstur dan Warna pada Kulit Katak Menggunakan GLCM dan Momen Warna

Anura is an order in the Amphibian class consisting of frogs and toads. Anura is very important in the ecosystem, especially its role as part of the food chain. Anura's main role is to maintain the balance of the ecosystem and as a bioindicator agent for changing environmental conditions such as water pollution, habitat destruction, disease and parasites, and climate change. This research applies digital image processing technology which is expected to assist in detecting types of frogs based on color and texture. This research uses 5 types of frogs, namely kongkang gading, kongkang poison, striped trees, small trees and flying trees with 20 images of each type of frog. This research uses the color feature extraction methods such Color Moment and texture extraction GLCM (Gray Level Co-occurance Matrix), then classified using K-Star. The results of the K-Star performance evaluation to classify the 5 types of frogs obtained the Accuracy (Acc) value of 0.93, Precision (Prec) of 0.94, Recall (Rec) of 0.93 and F-measure of 0.93. So that the classification results of frog species on texture and color feature extraction using the GLCM method and the Color Moment with the K-Star classification method have high performance and can work well.

Comparison of color-based feature extraction methods in banana leaf diseases classification using SVM and K-NN

In Malaysia, banana is a top fruit production which contribute to the economy growth in agriculture field. Hence, it is significant to have a quality production of banana and important to detect the plant diseases at the early stage. There are many types of banana leaf diseases such as Banana Mosaic, Black Sigatoka and Yellow Sigatoka. These three diseases are related to color changes at banana. This research paper is an experiment based and need to identify the best color feature extraction method to classify banana leaf diseases. Total of 48 banana leaf images that are used in this research paper. Four types of color feature extraction methods which are color histogram, color moment, hue, saturation, and value (HSV) histogram and color auto correlogram are experimented to determine the best method for banana leaf diseases classification. While for the classifiers, support vector machine (SVM) and k-Nearest neighbors (k-NN) are used to evaluate the performance and accuracy of each color feature extraction methods. There are also preliminary experiments to identify accurate parameters to use during classification for both classifiers. Our experimental result express that HSV histogram is the best method to classify banana leaf diseases with 83.33% of accuracy and SVM classifier perform better compared to k-NN.

Person Re-Identification by Low-Dimensional Features and Metric Learning

Person re-identification (Re-ID) has attracted attention due to its wide range of applications. Most recent studies have focused on the extraction of deep features, while ignoring color features that can remain stable, even for illumination variations and the variation in person pose. There are also few studies that combine the powerful learning capabilities of deep learning with color features. Therefore, we hope to use the advantages of both to design a model with low computational resource consumption and excellent performance to solve the task of person re-identification. In this paper, we designed a color feature containing relative spatial information, namely the color feature with spatial information. Then, bidirectional long short-term memory (BLSTM) networks with an attention mechanism are used to obtain the contextual relationship contained in the hand-crafted color features. Finally, experiments demonstrate that the proposed model can improve the recognition performance compared with traditional methods. At the same time, hand-crafted features based on human prior knowledge not only reduce computational consumption compared with deep learning methods but also make the model more interpretable.

Reference-guided structure-aware deep sketch colorization for cartoons

Digital cartoon production requires extensive manual labor to colorize sketches with visually pleasant color composition and color shading. During colorization, the artist usually takes an existing cartoon image as color guidance, particularly when colorizing related characters or an animation sequence. Reference-guided colorization is more intuitive than colorization with other hints, such as color points or scribbles, or text-based hints. Unfortunately, reference-guided colorization is challenging since the style of the colorized image should match the style of the reference image in terms of both global color composition and local color shading. In this paper, we propose a novel learning-based framework which colorizes a sketch based on a color style feature extracted from a reference color image. Our framework contains a color style extractor to extract the color feature from a color image, a colorization network to generate multi-scale output images by combining a sketch and a color feature, and a multi-scale discriminator to improve the reality of the output image. Extensive qualitative and quantitative evaluations show that our method outperforms existing methods, providing both superior visual quality and style reference consistency in the task of reference-based colorization.

Klasifikasi Mutu Telur Burung Puyuh Berdasarkan Warna dan Tekstur Menggunakan Metode K-Nearest Neighbor (KNN) dan Fusi Informasi

<p>Kualitas produk merupakan faktor utama untuk menjamin keberlangsungan satu usaha peternakan. Perusahaan telur puyuh yang memiliki ribuan burung Puyuh seperti CV. NS Quail Farm mampu memproduksi ribuan telur dalam sehari karena seekor burung Puyuh mampu menghasilkan 250-300 butir telur per tahun. Penyeleksian ribuan telur-telur tersebut dilakukan secara tradisional oleh para pekerja peternakan sehingga kualitas telur-telur hasil seleksi bergantung pada perspektif masing-masing pekerja. Guna memperoleh telur hasil seleksi dengan kualitas yang sama, maka dibangun sebuah sistem pencitraan digital untuk pemilihan telur burung Puyuh berdasarkan fitur warna dan tekstur kulit telur menggunakan metode klasifikasi K-<em>Nearest Neighbor</em> (KNN) yang dikombinasikan dengan fusi informasi. 300 data citra telur burung Puyuh diolah menggunakan normalisasi <em>Red, Green, Blue</em> (RGB) dan <em>Otsu thresholding</em> guna memperoleh fitur warna dan fitur tekstur yang kemudian difusikan menjadi fitur terfusi tunggal sebagai masukan pengklasifikasi KNN. Dari hasil-hasil penelitian, disimpulkan bahwa sistem berhasil mengklasifikasikan mutu telur Baik, Sedang, dan Buruk dengan akurasi rata-rata sebesar 77,78%. Disamping itu, klasifikasi dengan fusi informasi mampu mengungguli klasifikasi tanpa fusi informasi sebesar 11,11% pada nilai yang sama yakni 7 dan fusi informasi juga mampu mempercepat proses klasifikasi sebesar 0,22 detik dibandingkan terhadap klasifikasi tanpa fusi informasi.</p><p><strong><em>Abstract</em></strong></p><p><em>The quality of product us a primary factor to ensure the sustainability of a farm business. A company which has thousands of quail such as CV. NS Quail is capable of producing thousand quail eggs in a day because a quail is able to produce 250-300 eggs per year. The selection of the eggs is carried out traditionally by the farm workers so that the quality of the selected eggs are depended on the perspective of each worker. In order to obtain the same quality of the selected eggs, a digital imaging system for quail egg selection based on color feature and texture feature using K-Nearest Neighbor (KNN) combined with information fusion is developed. 300 image data of quail egg was processed using Red, Green, Blue (RGB) and Otsu thresholding to obtain color feature and texture feature which then were fused to become single fused feature as the input to KNN classifier. From the research results, it is concluded that the system was managed to classify egg quality as good, medium, and bad with an accuracy of 77,78%. In addition, the classification with information fusion was able to outperform the classification without information fusion by 11.11% at the same value of 7 and information fusion is also able to accelerate classification process by 0.22 seconds compared to that of without information fusion.</em></p>

Dynamic Hybrid Filter for Vision-Based Pose Estimation of a Hexa Parallel Robot

One of the problems with industrial robots is their ability to accurately locate the pose of the end-effector. Over the years, many other solutions have been studied including static calibration and dynamic positioning. This paper presents a novel approach for pose estimation of a Hexa parallel robot. The vision system uses three simple color feature points fixed on the surface of the end-effector to measure the pose of the robot. The Intel RealSense Camera D435i is used as a 3D measurement of feature points, which offers a cheap solution and high accuracy in positioning. Based on the constraint of three color feature points, the pose of the end-effector, including position and orientation, is determined. A dynamic hybrid filter is designed to correct the vision-based pose measurement. The complementary filter is used to eliminate the noise of image processing due to environmental light source interference. The unscented Kalman filter is designed to smooth out the pose estimation of the vision system based on robot’s kinematic parameters. The combination of two filters in the same control scheme contributes to increased stability and improved accuracy of robot’s positioning. The simulation, experiment, and comparison demonstrate the effectiveness and feasibility of the proposed method.