scholarly journals Pengenalan Pose Tangan Menggunakan HuMoment

2017 ◽  
Vol 9 (1) ◽  
pp. 100 ◽  
Author(s):  
Dina Budhi Utami ◽  
Muhammad Ichwan
Keyword(s):  
Computer Vision ◽  
Euclidean Distance ◽  
Region Of Interest

Computer vision yang didasarkan pada pengenalan bentuk memiliki banyak potensi dalam interaksi manusia dan komputer. Pose tangan dapat dijadikan simbol interaksi manusia dengan komputer seperti halnya pada penggunaan berbagai pose tangan pada bahasa isyarat. Berbagai pose tangan dapat digunakan untuk menggantikan fungsi mouse, untuk mengendalikan robot, dan sebagainya. Penelitian ini difokuskan pada pembangunan sistem pengenalan pose tangan menggunakan HuMoment. Proses pengenalan pose tangan dimulai dengan melakukan segmentasi citra masukan untuk menghasilkan citra ROI (Region of Interest) yaitu area telapak tangan. Selanjutnya dilakukan proses deteksi tepi. Kemudian dilakukan ekstraksi nilai HuMoment. Nilai HuMoment dikuantisasikan ke dalam bukukode yang dihasilkan dari proses pelatihan menggunakan K-Means. Proses kuantisasi dilakukan dengan menghitung nilai Euclidean Distance terkecil antara nilai HuMomment citra masukan dan bukukode. Berdasarkan hasil penelitian, nilai akurasi sistem dalam mengenali pose tangan adalah 88.57%.

scholarly journals Model of Multilevel Sub-Image to Find the Position of Region of Interest

2016 ◽  
Vol 3 (2) ◽  
pp. 189-196
Author(s):  
Budi Hartono ◽  
Veronica Lusiana
Keyword(s):  
Euclidean Distance ◽  
Region Of Interest ◽  
Image Data ◽  
Image Feature ◽  
Experimental Result ◽  
Main Attention ◽  
Image Content ◽  
Query Image ◽  
Image Object

Searching image is based on the image content, which is often called with searching of image object. If the image data has similarity object with query image then it is expected the searching process can recognize it. The position of the image object that contains an object, which is similar to the query image, is possible can be found at any positionon image data so that will become main attention or the region of interest (ROI). This image object can has different wide image, which is wider or smaller than the object on the query image. This research uses two kinds of image data sizes that are in size of 512X512 and in size of 256X256 pixels.Through experimental result is obtained that preparing model of multilevel sub-image and resize that has same size with query image that is in size of 128X128 pixels can help to find ROI position on image data. In order to find the image data that is similar to the query image then it is done by calculating Euclidean distance between query image feature and image data feature.

Computer Vision Based Asset Surveillance for Smart Buildings

2020 ◽  
Vol 17 (1) ◽  
pp. 456-463
Author(s):  
K. S. Gautam ◽  
Latha Parameswaran ◽  
Senthil Kumar Thangavel
Keyword(s):  
Computer Vision ◽  
Correlation Coefficient ◽  
Real World ◽  
Vision System ◽  
Region Of Interest ◽  
Detection And Tracking ◽  
Novel Approach ◽  
Ip Camera ◽  
Pros And Cons ◽  
Real World Problems

Unraveling meaningful pattern form the video offers a solution to many real-world problems, especially surveillance and security. Detecting and tracking an object under the area of video surveillance, not only automates the security but also leverages smart nature of the buildings. The objective of the manuscript is to detect and track assets inside the building using vision system. In this manuscript, the strategies involved in asset detection and tracking are discussed with their pros and cons. In addition to it, a novel approach has been proposed that detects and tracks the object of interest across all the frames using correlation coefficient. The proposed approach is said to be significant since the user has an option to select the object of interest from any two frames in the video and correlation coefficient is calculated for the region of interest. Based on the arrived correlation coefficient the object of interest is tracked across the rest of the frames. Experimentation is carried out using the 10 videos acquired from IP camera inside the building.

Research of Image Processing Algorithm Based on Region of Interest

2013 ◽  
Vol 798-799 ◽  
pp. 814-817
Author(s):  
Fang Wang
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Visual Attention ◽  
Region Of Interest ◽  
Processing Algorithm ◽  
Human Information Processing ◽  
Visual Attention Model ◽  
Attention Model ◽  
Starting Point ◽  
Image Zooming

With the further development of modern scientific study, it promotes the research of the image based on region of interest. By doing these studies, it satisfies the pressing needs in many fields such as military, production and living areas, etc. meanwhile, it is also the key problem in the fields of computer vision, image processing, artificial intelligence, video communication. Visual attention plays a very important role in the human information processing of the psychological adjustment mechanism. It is a conscious activity which chooses the useful information from large amounts of information. It owns the high efficiency and reliability in the process of human visual perception. Visual attention model, which is based on the visual attention and combined with the computer vision, builds a spatial feature of visual attention architecture. It is helpful not only to find out the visual cognition rule, but also to solve the problem of interested area selection and focus on improving the efficiency of the computer image processing. It has important application value in areas such as image extraction and image zooming. The paper has carried out the deeply study in the interested image region. With the improved visual attention model as a starting point, it combines with graph processing algorithm. And it uses the image extraction algorithm and image zooming algorithm to improve the visual attention model and detect the interested area.

scholarly journals N-D Linear Time Exact Signed Euclidean Distance Transform

2003 ◽  
Author(s):  
Nicholas J. Tustison ◽  
Marcelo Siqueira ◽  
James Gee
Keyword(s):  
Computer Vision ◽  
Euclidean Distance ◽  
Linear Time ◽  
Small Time ◽  
Direct Application ◽  
Distance Transform ◽  
Fast Computation ◽  
Distance Transforms ◽  
Euclidean Distance Transform ◽  
Image Pixels

Fast computation of distance transforms find direct application in various computer vision problems. Currently there exists two image filters in the ITK library which can be used to generate distance maps. Unfortunately, these filters produce only approximations to the Euclidean Distance Transform (EDT). We introduce into the ITK library a third EDT filter which was developed by Maurer {} . In contrast to other algorithms, this algorithm produces the exact signed squared EDT using integer arithmetic. The complexity, which is formally verified, is O(n) O(n) with a small time constant where n n is the number of image pixels.

Automatic Defect Detection and Classification of Terminals in a Bussed Electrical Center Using Computer Vision

2016 ◽  
pp. 241-266
Author(s):  
Osslan Osiris Vergara Villegas ◽  
Vianey Guadalupe Cruz Sánchez ◽  
Humberto de Jesús Ochoa Domínguez ◽  
Jorge Luis García-Alcaraz ◽  
Ricardo Rodriguez Jorge
Keyword(s):  
Computer Vision ◽  
Defect Detection ◽  
Nearest Neighbor ◽  
Region Of Interest ◽  
Morphological Operation ◽  
K Nearest Neighbor ◽  
Electrical Center ◽  
Salt And Pepper ◽  
Intelligent Computer

In this chapter, an intelligent Computer Vision (CV) system, for the automatic defect detection and classification of the terminals in a Bussed Electrical Center (BEC) is presented. The system is able to detect and classify three types of defects in a set of the seven lower pairs of terminals of a BEC namely: a) twisted; b) damaged and c) missed. First, an environment to acquire a total of 56 training and test images was created. After that, the image preprocessing is performed by defining a Region Of Interest (ROI) followed by a binarization and a morphological operation to remove small objects. Then, the segmentation stage is computed resulting in a set of 12-14 labeled zones. A vector of 56 features is extracted for each image containing information of area, centroid and diameter of all terminals segmented. Finally, the classification is performed using a K-Nearest Neighbor (KNN) algorithm. Experimental results on 28 BEC images have shown an accuracy of 92.8% of the proposed system, allowing changes in brightness, contrast and salt and pepper noise.

Research on Methods of Tire Sensory Measurement Based on Image Processing

2011 ◽  
Vol 230-232 ◽  
pp. 900-904 ◽  
Author(s):  
Rong Bao Chen ◽  
Jing Tao ◽  
Wu Ting Fan ◽  
Jun Jie Zhang
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Euclidean Distance ◽  
Traffic Accidents ◽  
Pressure Overload ◽  
Texture Features ◽  
Tire Pressure ◽  
Distance Method ◽  
Proportion Method

This paper proposes and analyzes sensory measurement of tire based on image processing, which uses tangent value method, proportion method and Euclidean distance method to detect tire pressure and overload and uses Tamura texture features to describe tire abrasion level. The research presents a contactless way to detect tire pressure, overload and abrasion level and has certain advantages and innovations in function and implementation compared with existing TPMS which can’t detect the tire abrasion level. This research is an application of image processing-based computer vision in tire sensory measurement; it makes the measurement of tire automatically and intelligently and can be used to prevent traffic accidents caused by tires effectively. There are practical values.

scholarly journals Detecção de Roubo de Computadores em Laboratório Usando Visão Computacional

2020 ◽  
Author(s):  
Gabriel Andrade Cordeiro ◽  
Giovani Grockotzki ◽  
Itamar Junior de Azevedo ◽  
João Mantovani ◽  
Matheus Henrique da Silva Santos ◽  
...  
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Real Time ◽  
Video Analysis ◽  
Region Of Interest ◽  
Background Information ◽  
Laboratory Monitoring ◽  
Exit Door ◽  
Definition Of ◽  
Computer Labs

Computer theft in computer labs causes academic damage to coursesthat require this resource and ends up directly harming students. Inthis context, this paper describes a methodology applied to detectcomputer removal through video analysis in real-time. For eachframe, image processing and computer vision techniques were used,subtracting background information, binarization, segmentationof the region of interest and definition of contours. The case studywas developed at a Brazilian university. For theft detection, it wasconsidered a black computer tower case carried by people leavingthe laboratory. Monitoring is carried out by a camera positioned infront of the lab exit door. The software developed alerts a suspiciousactivity that may indicate a possible computer theft.

scholarly journals Offline Signature Identification Using Deep Learning and Euclidean Distance

2021 ◽  
Vol 12 (2) ◽  
pp. 102
Author(s):  
Made Prastha Nugraha ◽  
Adi Nurhadiyatna ◽  
Dewa Made Sri Arsa
Keyword(s):  
Deep Learning ◽  
Euclidean Distance ◽  
Region Of Interest ◽  
Combination Method ◽  
Identity Recognition ◽  
Split Ratio ◽  
Image Conversion ◽  
Signature Recognition ◽  
The Right ◽  
Precision Rate

Hand signature is one of human characteristic that human have since birth, which can be used as identity recognition. A high accuracy signature recognition is needed to identify the right owner of signature. This study present signature identification using a combination method between Deep Learning and Euclidean Distance.  3 different signature datasets are used in this study which consist of SigComp2009, SigComp2011, and private dataset. Signature images preprocessed using binary image conversion, Region of Interest, and thinning. Several testing scenarios is applied to measure proposed method robustness, such as usage of various Pretrained Deep Learning, dataset augmentation, and dataset split ratio modifier. The best accuracy achieved is 99.44% with high precision rate.

scholarly journals PROTOTYPE REGION OF INTEREST (ROI) CITRA WAJAH MANUSIA BERBASIS BINARY LARGE OBJECT (BLOB) ANALYSIS

2020 ◽  
Vol 16 (2) ◽  
pp. 83
Author(s):  
Arief Bramanto Wicaksono Putra ◽  
Mirza Rafdi Rosada ◽  
Achmad Fanany Onnilita Gaffar
Keyword(s):  
Euclidean Distance ◽  
Region Of Interest ◽  
Large Object ◽  
Blob Analysis ◽  
Flood Fill

<p>Setiap manusia memiliki identitasnya masing-masing, dan tidak akan sama satu identitas seseorang dengan identitas lainnya. Biometrik suatu wajah tidak akan sama dengan wajah lainnya, oleh karena itu dirancang suatu <em>prototype </em>pengenalan identitas ciri wajah pada wilayah-wilayah tertentu atau <em>Region of Interest </em>(ROI). ROI yang digunakan merupakan biometrik-biometrik unik yang terdapat pada wajah. Untuk mendapatkan ROI, proses segmentasi yang digunakan diantaranya adalah: Morfologi, <em>Flood fill Algorithm </em>dan <em>Tresholding. </em>Kemudian dengan menggunakan <em>BLOB Analysis</em> jumlah area dan nilai piksel yang terdapat pada ROI yang telah tersegmentasi akan dijadikan sebagai ekstraksi ciri pengenalan yang kemudian akan teridentifikasi menggunakan pendekatan <em>Euclidean distance</em>. ROI yang diperoleh dari ekstraksi menggunakan <em>BLOB analysis</em> mencakup 6 sampai 9 area biometrik wajah seperti alis, mata, hidung, mulut dan telinga. Hasil performansi dari identifikasi kemiripan wajah menggunakan 3 data wajah dengan 5 data sampel berbeda pada masing-masing wajah adalah 33,3%.</p>

Sign in / Sign up

Export Citation Format

Share Document