Бидний тухай
Багш ажилтан
Энэхүү судалгаагаар бид К-мийнс кластерингд (K-Means Clustering) суурилсан шуугианыг ялгах алгоритмыг танилцуулж байна. Энэ арга нь түүхий өгөгдөл дээр шууд боловсруулалт хийх ба гадаргуун цэгүүдийг шуугиантай болон шуугиангүйгээр ялгаж зөвхөн шуугиантай гадаргуун цэгүүдийн шуугианыг арилгадгаараа бусад аргаас давуу талтай юм. Бидний арга нь гадаргуун цэг бүрийн хөрш цэгийн тоон өөрчлөлт дээр К-мийнс кластеринг хийж шуугиантай гадаргууг ялгах юм. Энэхүү судалгаанд дөрвөн чиглэлд хэмжилт хийн сканерддаг төхөөрөмжөөр үүсгэгдсэн чулуун зэвсгийн цэгэн үүлний хэсэгчилсэн шуугианыг арилгасан ба үр дүнг үзүүлэв.
In this paper, we introduce the Surface Universality Rating (SUR) method to accurately measure surface sharpness from a point cloud. Moreover, this study represents the first attempt to distinguish edge points automatically. The easy and accurate evaluation of surface sharpness is a critical challenge associated with point cloud processing. Although surface sharpness is an essential property for shape analysis, local analytical methods for the evaluation of surface properties exhibit limitations in terms of geometric shape. Furthermore, local analyses are insufficient for evaluating the sharpness of edge points owing to the scarcity of neighboring points. These challenges require more accurate assessments of surface sharpness, as well as more efficient thresholding for feature points. Although many methods have been developed to evaluate surface sharpness, they are generally difficult to use and require many parameters. We conducted experiments to verify the effectiveness of our method.
The 3D object has many different shapes. However, it is a difficult challenge to develop an exemplary method for calculating the feature points suitable for various shapes of objects. This study aims to estimate feature points from 3D objects with various shapes optimally. The study conducts to extract feature points from point clouds using the Feature correlation. First, the Covariance features of all points are estimated. Then the most significant feature is defined from the estimated Covariance features using the Principal Components attribute selection method. After that, the Feature correlation of the most significant feature is estimated. Finally, combining the relevant important features estimates the feature point. This study tested two different algorithms based on the relevant important features. The proposed algorithm was tested on publicly available objects with various shapes.
Цэгэн үүлний (Point cloud) ашиг тусыг хүртэж байгаа судалгааны нэг бол чулуун зэвсгийн судалгаа юм. Жишээлбэл археологийн салбарт чулуун зэвсгийг судлахдаа гадаргуугаас онцлог шинжийг ялгах, гадаргууг хэсэгчлэн таних ба тааруулах зэрэгт цэгэн үүлийг ашигладаг. Чулуун зэвсгийн судалгаанд нурууны шугамыг (Ridge line) гаргах нь чухал ач холбогдолтой. Чулуун зэвсгийн хэлбэр нь нарийн төвөгтэй бөгөөд нурууны шугамын хэлбэр нь хоёрдмол утгатай байдаг. Мөн түүнчлэн сканердсан технологиос үүссэн шуугиан (noise) зэрэг нь онцлог цэгийг (feature point) нарийн ялгахад бэрхшээл учруулдаг. Энэ судалгааны ажлаар чулуун зэвсгийн нэг төрөл болох ялтсан зэвсгийн (Flake stone tool) ирмэгийн цэгүүдэд (Ridge points) ковариац шинжилгээ хийж ялтасны онцлог цэгүүдийг (feature points of Flake surface) оновчтой илрүүлэв. Тулгуур Компонентад суурилсан атрибиут-сонголтын (ТКСАС) аргыг анх удаа ялтсан зэвсгийн ирмэгийг илрүүлэхэд ашиглав. Туршилтын үр дүнд ялтсан зэвсгийн ирмэгийг үнэлэх чухал атрибиутуудыг тодорхойлов.
Цэгэн үүлний (Point cloud) ашиг тусыг хүртэж байгаа судалгааны нэг бол чулуун зэвсгийн судалгаа юм. Жишээлбэл археологийн салбарт чулуун зэвсгийг судлахдаа гадаргуугаас онцлог шинжийг ялгах, гадаргууг хэсэгчлэн таних ба тааруулах зэрэгт цэгэн үүлийг ашигладаг. Чулуун зэвсгийн судалгаанд нурууны шугамыг (Ridge line) гаргах нь чухал ач холбогдолтой. Чулуун зэвсгийн хэлбэр нь нарийн төвөгтэй бөгөөд нурууны шугамын хэлбэр нь хоёрдмол утгатай байдаг. Мөн түүнчлэн сканердсан технологиос үүссэн шуугиан (noise) зэрэг нь онцлог цэгийг (feature point) нарийн ялгахад бэрхшээл учруулдаг. Энэ судалгааны ажлаар чулуун зэвсгийн нэг төрөл болох ялтсан зэвсгийн (Flake stone tool) ирмэгийн цэгүүдэд (Ridge points) ковариац шинжилгээ хийж ялтасны онцлог цэгүүдийг (feature points of Flake surface) оновчтой илрүүлэв. Тулгуур Компонентад суурилсан атрибиут-сонголтын (ТКСАС) аргыг анх удаа ялтсан зэвсгийн ирмэгийг илрүүлэхэд ашиглав. Туршилтын үр дүнд ялтсан зэвсгийн ирмэгийг үнэлэх чухал атрибиутуудыг тодорхойлов.
-
A method will be examined for automatically detecting protruding patterns on the surface of Jomon potteries using the Watershed method based on the curvature of three-dimensional measurement point clouds.
One of the research that benefits from point clouds are the study of stone tools. In archaeology, the study of stone tools is performed in the order of feature extraction, flake surface recognition, and flake surface matching. Boundaries represented by ridge lines of a flake surface are required to recognize a flake surface. Especially it is important to construct a closed area bounded by ridge lines. In previous work, the precision of a ridge line recognition is lower, and it is difficult to construct boundaries from extracted ridge lines. Because the hape of the stone tool is complex and the shape of the ridge line may be ambiguous. This study proposes to extract the ridge line of the stone tool. Therefore, the profitable features for flake surface segmentation are evaluated from its covariance features. Initially, the potential feature points are detected by the analysis of its surface variations estimated from the various neighbors. Then, the covariance features of the potential points are estimated. Next, profitable features are evaluated from the covariance features. Using profitable features of the stone tool, feature points on the ridge lines are extracted. After that, feature lines are extracted by potential features on the ridge lines. Finally, flake surfaces are segmented by the feature-line-based segmentation method. Our method is verified by applying to the point cloud of stone tools and confirmed the effectiveness of flake surface segmentation.
Point-cloud-based techniques play a very significant role in the archaeological application for stone tools. Measured point data involve small noises, which are overlaps obtained through measurement by laser devices. Such noisy data make it difficult to extract highly accurate segmented flakes, which will be used for the refitted flake matching process, because potential feature points lying on the boundary edges are hardly extracted. To overcome this issue, this paper describes a method of recognizing flake surfaces with noisy point clouds. First, the resampling method is applied to remove the noise in the input data. Then, the surface variation is calculated with a various number of neighbors and the potential feature points are detected by analyzing its surface variation. After that, feature lines are extracted from the potential feature points. The feature lines represent boundary edges of the flake surfaces. Finally, flake surfaces are extracted by the featureline-based segmentation method. The implementation of this work can recognize flake surfaces from noisy data.
Point-cloud-based technique plays a very significant role in 3D model restoration. In the archaeological application of stone tools, the scale drawing, which is hand-drawn from measured stone tools, is traditionally used. In the scale drawing creation, a base drawing which consists outline and ridge lines is initially drawn from geometric features of shape. After that other lines are extracted from knowledge of making stone tools and are added to the base drawing. It requires special knowledge to extract feature lines from stone tools so that scale drawing is time-consuming. Therefore, if the base drawing is automatically extracted, the working hours are reduced. To overcome this issue, this paper proposes a feature line extraction method using the Mahalanobis distance metric. First, the points on outline are extracted from a point cloud. Then, the surface variation is calculated with a various number of neighbors and thus the potential feature points are detected by the analysis of its surface variation. After that, the potential feature points are thinned towards the highest variation points by using Laplacian smoothing. Then, the thinned feature points are shrunk to the potential feature points. Finally, a feature line is extracted by connecting the nearest thinned feature points locating in the Mahalanobis distance field. To verify our method, the extracted feature lines are compared to the ground truth of base drawing drawn by archaeological illustrators. Our method is applied to stone tools, and we confirm the effectiveness of our method.
This paper proposes a flake surface segmentation method using ridge lines extracted from point clouds. First, ridge lines are extracted from a point set of a stone tool. Next, neighboring points of a ridge line are extracted by calculating the Euclidean distance from the ridge line. An area surrounded by the neighboring points of the ridge line is selected. Then, the area is expanded from the selected region to the ridge line to segment a flake surface.
The International Workshop on Advanced Image Technology (IWAIT) is a well-known international event that gathers researchers, professors, students and interested persons in the field of advanced image technology. Previous IWAIT events have been held annually since 1998 in Eastern and South Eastern Asian countries such as Japan (2000,2003,2006,2013), Korea (1998, 2001, 2005, 2009), Taiwan (1999, 2002, 2008, 2015), Japan (2000, 2003, 2006, 2013), Singapore (2004, 2019), Thailand (2007, 2014, 2018), Malaysia (2010, 2017), Indonesia (2011,2020).
