Line Segment-Based Clustering Approach With Self-Organizing Maps

Clustering techniques are used widely in computer vision and pattern recognition. The clustering techniques are found to be efficient with the feature vector of the input image. So, the present paper uses an approach for evaluating the feature vector by using Hough transformation. With the Hough transformation, the present paper mapped the points to line segment. The line features are considered as the feature vector and are given to the neural network for performing clustering. The present paper uses self-organizing map (SOM) neural network for performing the clustering process. The proposed method is evaluated with various leaf images, and the evaluated performance measures show the efficiency of the proposed method.

Polarity Determination in EBSD Patterns Using the Hough Transformation

Currently, the automated electron backscatter diffraction (EBSD) technique only allows the differentiation of the Laue groups based on an electron backscatter pattern (EBSP). This article shows that information concerning the lattice plane polarity is not only stored in the EBSP, but also in the Hough transformed EBSP where it can be easily accessed for automated evaluation. Polar Kikuchi bands lead to asymmetric peaks during the Hough transformation that are dependent on the atomic number difference of the involved atoms. The effect can be strong enough to be detected when evaluating the intensities of the regular excess and deficiency lines. Polarity detection from the Hough transformation of an EBSP cannot only enhance the utility of the EBSD technique and expand the information gained from it, but also illustrates a path toward automated polarity determination during EBSD scans.

Semi-automated fault extraction and structural analysis from DEM data of the Magadi and Natron basins, East African Rift System

<p>Continental rifts show surface expressions of deep crustal processes, such as faulting and volcanism. The East African Rift System (EARS) is one of the most prominent examples of an active continental rift driven by tectonics and magmatism. Nonetheless, we still struggle to quantify the amount of extension due to these processes on a kyr- to Myr-time-scale. In particular, the distribution of extension within low-offset normal fault networks within rift basin interiors is challenging to determine.</p><p>To address these issues, we develop a semi-automated workflow to extract normal faults from the TanDEM-X science DEM data (12 m horizontal resolution, 0.4 m average height error) of the Magadi-Natron Region of the Eastern branch of the EARS, limited to the north by the Suswa caldera (1.15°S) and to the south by Gelai and Oldoinyo Lengai volcanoes (2.75°S). This data allows us to quantify brittle surface deformation that occurred since the last deposition of widespread volcanic lavas in  these basins. Our workflow consists of five steps: (1) gradient calculation, (2) thresholding, (3) skeletonization, (4) Hough transformation, and (5) clustering. Because the surface faults appear as topographic discontinuities, we first calculate the gradient of the DEM to detect them. Then we use an adaptive threshold (Otsu) to distinguish faults from unfaulted areas. Next, we skeletonize the threshold to extract line segments and perform a Hough transformation to determine the orientation of these segments. Finally, we use a density-based clustering algorithm (DBSCAN) to group these segments into faults. This algorithm is considering proximity between the segment, similarity in dip and strike direction.</p><p>A strike analysis applied on the fault data of the whole basin shows four main directions from distinct fault populations. Each direction cluster corresponds to a geological layer and a time interval. For example, the azimuth N20°, corresponds to present and recent rift direction, mostly on the ~1Myr old Magadi trachyte. A direction of N170° is mostly represented in earlier,  Mio-Pliocene volcanic units of the rift. Moreover, we derive the fault displacement distribution throughout the basin.This allows us to calculate the total extension of each geological unit and to compute the overall amount of extension of the region during geologically recent times.</p><p>We provide a new high-resolution fault map that depicts strike direction and throw even of small-offset normal faults. This characterization helps us increase our understanding of recent brittle deformation within the Magadi-Natron region and thus the propagation of rifting in the eastern branch of the East African Rift System.</p>

3D Reconstruction with circular light field by using 3D hough transformation

Aiming at the issue of incomplete trajectories in the 2D epipolar image of circular light field, this paper proposes a 3D reconstruction method by using 3D Hough transformation. This method computes 3D point clouds by computing the parameters of feature trajectories in 3D image volume. By analyzing the 3D distribution of circular light field trajectories, binary curves in image volume are extracted, and their local orientation are further estimated by the 3D structure tensor. The 3D Hough space generation and the parameter selection method are proposed to the 3D curves detection. The parameters of these curves are converted to 3D point clouds on each view and then merged to final 3D reconstruction. The ambiguity of Hough transformation solution on 2D epipolar image is overcome by the 3D analyzing method. The experiments are carried out on both synthetic and real datasets. The experiment results show that this method can improve the reconstruction performance compared with the state-of-the-art in circular light field.

Sistem Identifikasi Biometrik Ekpresi Wajah Menggunakan Metode Transformasi Hough

The movement of the eye ball affects the condition of the pupil to dilate to become smaller or vice versa, it indicates a person's mood changes very quickly. The image of the eyeball is not necessarily in accordance with the condition of a person's heart, so it is necessary to analyze the movement of the pupil of the eye. Facial expression using the Hough Transformation Method focuses on the movement of the pupil of the eye. The Hough transform works by looking for the neighbor relationship between pixels using straight line equations to detect lines and circular equations to detect circles. Hough line transform is a technique most commonly used to detect curved objects such as lines, circles, ellipses and parabolas. The detection accuracy of the pupil is influenced by the accuracy of the extraction of the edges of the eye. If the outer circle identification is not detected, Hough Transform will be identified. The segmentation step carried out can identify the pupil circle region with a detection success of 80-85%.

Metode Pusat dan Circular Hough Transformation untuk Mendeteksi Lingkaran pada Sebuah Citra

Tulisan ini membahas tentang penerapan metode pusat dan Circular Hough Transformation(CHT) untuk mendeteksi semua lingkaran yang terkandung dalam citra baik lingkaran tunggal maupun lingkaran yang tumpang tindih. Metode pusat dan CHT memainkan peran penting dalam mendeteksi lingkaran yang terkandung dalam citra melalui array akumulator dua dimensi A(a, b) yang memiliki memori berurutan dengan titik pusat dari lingkaran yang tumpang tindih sehingga dapat dihitung untuk setiap titik pada kurva menggunakan nilai parameter jari-jari yang dipilih untuk mendapatkan nilai triplet (a, b, r) pada Circular Hough Transformation (CHT). Metode pusat merupakan alternatif lain untuk mendetekasi lingkaran dalam sebuah citra, melalui pre-processing seperti, input citra, deteksi objek, ambang batas tepi, skala abu-abu. Kemudian digunakan metode pusat untuk CHT. Akhirnya adalah mengimplementasikan metode pusat dan Cricular Hough Transformation menggunakan Matlab R2020b. Dengan sisitem yang dibangun dapat dideteksi seluruh lingkaran yang terdapat pada citra dengan akurasi 100% dengan memberikan intensitas cahaya 0.93 dan ambang batas 0.33 dan polarisasi objek gelap dan terang serta rentang jari-jaroi antara 16px dan 110px. Tentunya ini tidak berlaku untuk citra yang memuat lingkaran dengan jari-jari yang lebih dari 110px atau kurang dari 16px. Kata kunci: Metode Pusat, Lingkaran, Jari-Jari, Citra, CHT Abstract This paper discusses the application of the center method and Circular Hough Transformation (CHT) to detect all circles contained in an image, both single circles and overlapping circles. The center and CHT methods play an important role in detecting the circle contained in the image via a two-dimensional accumulator array A (a, b) which has sequential memory with the center points of the overlapping circles so that it can be calculated for each point on the curve using parameter values. the radius selected to obtain the triplet values (a, b, r) of the Circular Hough Transformation (CHT). The center method is another alternative for detecting circles in an image, through pre-processing such as image input, object detection, edge threshold, grayscale. Then the central method for CHT was used. Finally is to implement the central method and the Cricular Hough Transformation using the Matlab R2020b. With the built system it can be detected all the circles in the image with 100% accuracy by providing a light intensity of 0.93 and a threshold of 0.33 and polarization of dark and light objects and a radius range between 16px and 110px. Of course this does not apply to images that contain circles with radii greater than 110px or less than 16px. Keywords: Center Method, Circle, Radii, Image, CHT.